Add files using upload-large-folder tool

.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024 McGill NLP
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -0,0 +1,139 @@
+# *AURORA: Learning Action and Reasoning-Centric Image Editing from Videos and Simulation*
+
+[![Website](https://img.shields.io/badge/Website-AURORA.svg)](https://aurora-editing.github.io/)
+[![arxiv](https://img.shields.io/badge/arXiv-2407.03471-b31b1b.svg)](https://arxiv.org/abs/2407.03471)
+[![HF Datasets: AURORA](https://img.shields.io/badge/HF%20Datasets-AURORA-FFD21E.svg)](https://huggingface.co/datasets/McGill-NLP/AURORA)
+[![HF Datasets: AURORA-Bench](https://img.shields.io/badge/HF%20Datasets-AURORABench-FFD21E.svg)](https://huggingface.co/datasets/McGill-NLP/aurora-bench)
+[![HF Demo](https://img.shields.io/badge/HF%20DEMO-FFD21E.svg)](https://huggingface.co/spaces/McGill-NLP/AURORA)
+[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://github.com/McGill-NLP/AURORA/blob/main/LICENSE)
+
+AURORA (Action Reasoning Object Attribute) enables training an instruction-guided image editing model that can perform action and reasoning-centric edits, in addition to "simpler" established object, attribute or global edits. Here we release 1) training data, 2) trained model, 3) benchmark, 4) reproducible training and evaluation.
+
+<p align="center">
+  <img src="aurora.png" width="75%" alt="Overview"/>
+</p>
+
+Please reach out to [[email protected]](mailto:[email protected]) or raise an issue if anything does not work!
+
+
+
+## Updates
+**5th December 2024**: uploaded cleaner (actually usable) human ratings on AURORA-Bench. This can be useful for evaluating metrics via human correlation across a wide range of tasks. It includes 2K human ratings on outputs from 5 models.
+
+## Data
+
+On the data side, we release three artifacts and a [Datasheet documentation](https://github.com/McGill-NLP/AURORA/blob/main/datasheet.md):
+1. The training dataset (AURORA)
+2. A benchmark for testing diverse editing skills (AURORA-Bench): object-centric, action-centric, reasoning-centric, and global edits
+3. Human ratings on AURORA-Bench, i.e. for other researchers working image editing metrics
+
+You can also check out our [Huggingface dataset](https://huggingface.co/datasets/McGill-NLP/AURORA).
+
+### Training Data (AURORA)
+
+The edit instructions are stored as `data/TASK/train.json` for each of the four tasks.
+
+For the image pairs, you can download them easily via zenodo:
+```
+wget https://zenodo.org/record/11552426/files/ag_images.zip
+wget https://zenodo.org/record/11552426/files/kubric_images.zip
+wget https://zenodo.org/record/11552426/files/magicbrush_images.zip
+```
+
+Now put them into their respective directory `data/NAME` and rename them images.zip.
+So in the end you should have `data/kubric/images` as a directory etc.
+
+For Something-Something-Edit, you need to go to the [original source](https://developer.qualcomm.com/software/ai-datasets/something-something) and download all the zip files and put *all* the videos in a folder named `data/something/videos/`. 
+
+Then run 
+```
+cd data/something
+python extract_frames.py
+python filter_keywords.py
+```
+
+For each sub-dataset of AURORA, an entry would look like this:
+
+
+```json
+[
+  {
+    "instruction": "Leave the door while standing closer",
+    "input": "data/ag/images/1K0SU.mp4_4_left.png",
+    "output": "data/ag/images/1K0SU.mp4_4_right.png"
+  },
+  {"..."}
+]
+```
+
+If you are interested in developing your own similar Kubric data, it takes some effort (i.e. Docker+Blender setup), but we provide some starting code under `eq-kubric`.
+
+### Benchmark: AURORA-Bench
+
+For measuring how well models do on various editing skills (action, reasoning, object/attribute, global), we introduce AURORA-Bench hosted here on this repository under `test.json` with the respective images under `data/TASK/images/`.
+
+### Human Ratings
+
+We also release human ratings of image editing outputs on AURORA-Bench examples, which forms the basis of our main evaluation in the paper.
+The output images and assocaciated human ratings can be downloaded from Google Drive and is straightforward to use e.g. for computing correlations with a new metric: [json](https://drive.google.com/file/d/1uWpVOit_eUvI6GnY_Bvaj_vPd3H8cTbT/view?usp=sharing), [images files](https://drive.google.com/file/d/1wUwlxN1ArqTlCQQgnsj7DoXNoPRX71Ao/view?usp=sharing)
+
+## Running stuff
+
+Similar to [MagicBrush](https://github.com/OSU-NLP-Group/MagicBrush) we adopt the [pix2pix codebase](https://github.com/timothybrooks/instruct-pix2pix) for running and training models.
+
+### Inference
+
+Please create a python environment and install the requirements.txt file (it is unfortunately important to use 3.9 due to taming-transformers):
+```
+python3.9 -m venv env
+pip3 install -r requirements.txt
+```
+
+You can download our trained checkpoint from Google Drive: [Link](https://drive.google.com/file/d/1omV0xGyX6rVx1gp2EFgdcK8qSw1gUcnx/view?usp=sharing), place it in the main directory and run our AURORA-trained model on an example image:
+```
+python3 edit_cli.py
+```
+
+### Training
+To reproduce our training, first download an initial checkpoint that is the reproduced MagicBrush model: [Google Drive Link](https://drive.google.com/file/d/1qwkRwsa9jJu1uyYkaWOGL1CpXWlBI1jN/view?usp=sharing)
+
+Due to weird versioning of libraries/python, you have to go to `env/src/taming-transformers/taming/data/utils.py` and comment out line 11: `from torch._six import string_classes`.
+
+Now you can run the the train script (hyperparameters can be changed under `configs/finetune_magicbrush_ag_something_kubric_15-15-1-1_init-magic.yaml`):
+
+```
+python3 main.py --gpus 0,
+```
+
+Specify more gpus with i.e. `--gpus 0,1,2,3`.
+
+
+## Reproduce Evaluation
+
+We primarily rely on human evaluation of model outputs on AURORA-Bench.
+However our second proposed evaluation metric is automatic and here is how you reproduce it.
+
+First, run `python3 disc_edit.py --task TASK` (i.e. `--task whatsup`). This will generate outputs in a folder called itm_evaluation, that will then be evaluated via `python3 eval_disc_edit.py`
+
+## Citation
+
+```bibtex
+@inproceedings{krojer2024aurora,
+  author={Benno Krojer and Dheeraj Vattikonda and Luis Lara and Varun Jampani and Eva Portelance and Christopher Pal and Siva Reddy},
+  title={{Learning Action and Reasoning-Centric Image Editing from Videos and Simulations}},
+  booktitle={NeurIPS},
+  year={2024},
+  note={Spotlight Paper},
+  url={https://arxiv.org/abs/2407.03471}
+}
+```
+
+## Acknowledgements & License 
+
+We use the [MIT License](https://github.com/McGill-NLP/AURORA/blob/main/LICENSE).
+
+We want to thank several repositories that made our life much easier on this project:
+
+1. The [MagicBrush](https://github.com/OSU-NLP-Group/MagicBrush) and [InstructPix2Pix](https://github.com/timothybrooks/instruct-pix2pix) code base and datasets, especially the correspondance with MagicBrush authors helped us a lot.
+2. The dataset/engines we use to build AURORA: [Something Something v2](https://developer.qualcomm.com/software/ai-datasets/something-something), [Action-Genome](https://github.com/JingweiJ/ActionGenome) and [Kubric](https://github.com/google-research/kubric)
+3. Source code from [EQBEN](https://github.com/Wangt-CN/EqBen) for generating images with the Kubric engine

app.py

@@ -0,0 +1,90 @@
+from __future__ import annotations
+import math
+import gradio as gr
+import torch
+from PIL import Image, ImageOps
+from diffusers import StableDiffusionInstructPix2PixPipeline
+
+def main():
+    pipe = StableDiffusionInstructPix2PixPipeline.from_pretrained("McGill-NLP/AURORA", safety_checker=None).to("cuda")
+    example_image = Image.open("example.jpg").convert("RGB")
+
+    def generate(
+        input_image: Image.Image,
+        instruction: str,
+        steps: int,
+        seed: int,
+        text_cfg_scale: float,
+        image_cfg_scale: float,
+    ):
+        width, height = input_image.size
+        factor = 512 / max(width, height)
+        factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
+        width = int((width * factor) // 64) * 64
+        height = int((height * factor) // 64) * 64
+        input_image = ImageOps.fit(input_image, (width, height), method=Image.Resampling.LANCZOS)
+
+        if instruction == "":
+            return [input_image, seed]
+
+        generator = torch.manual_seed(seed)
+        edited_image = pipe(
+            instruction, image=input_image,
+            guidance_scale=text_cfg_scale, image_guidance_scale=image_cfg_scale,
+            num_inference_steps=steps, generator=generator,
+        ).images[0]
+        return [seed, text_cfg_scale, image_cfg_scale, edited_image]
+
+    def reset():
+        return ["", 50, 42, 7.5, 1.5, None, None]
+
+    with gr.Blocks() as demo:
+        gr.HTML("""<h1 style="font-weight: 900; margin-bottom: 10px;">
+            AURORA: Learning Action and Reasoning-Centric Image Editing from Videos and Simulations
+        </h1>
+        <p>
+            AURORA (Action Reasoning Object Attribute) enables training an instruction-guided image editing model that can perform action and reasoning-centric edits, in addition to "simpler" established object, attribute or global edits.
+        </p>""")
+        
+        with gr.Row():
+            with gr.Column(scale=3):
+                instruction = gr.Textbox(value="move the lemon to the right of the table", lines=1, label="Edit instruction", interactive=True)
+            with gr.Column(scale=1, min_width=100):
+                generate_button = gr.Button("Generate", variant="primary")
+            with gr.Column(scale=1, min_width=100):
+                reset_button = gr.Button("Reset", variant="stop")
+
+        with gr.Row():
+            input_image = gr.Image(value=example_image, label="Input image", type="pil", interactive=True)
+            edited_image = gr.Image(label=f"Edited image", type="pil", interactive=False)
+
+        with gr.Row():
+            steps = gr.Number(value=50, precision=0, label="Steps", interactive=True)
+            seed = gr.Number(value=42, precision=0, label="Seed", interactive=True)
+            text_cfg_scale = gr.Number(value=7.5, label=f"Text CFG", interactive=True)
+            image_cfg_scale = gr.Number(value=1.5, label=f"Image CFG", interactive=True)
+    
+        generate_button.click(
+            fn=generate,
+            inputs=[
+                input_image,
+                instruction,
+                steps,
+                seed,
+                text_cfg_scale,
+                image_cfg_scale,
+            ],
+            outputs=[seed, text_cfg_scale, image_cfg_scale, edited_image],
+        )
+        reset_button.click(
+            fn=reset,
+            inputs=[],
+            outputs=[instruction, steps, seed, text_cfg_scale, image_cfg_scale, edited_image, input_image],
+        )
+
+    demo.queue()
+    demo.launch()
+    # demo.launch(share=True)
+
+if __name__ == "__main__":
+    main()

data-formatter.py

@@ -0,0 +1,69 @@
+import json
+import argparse
+import os 
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--dataset", type=str, required=True)
+    parser.add_argument("--training-format", type=str, required=True)
+    args = parser.parse_args()
+
+    # Load the input JSON file
+    with open("data/{s}/train.json".format(s=args.dataset), "r") as f:
+        data = json.load(f)
+
+    jsonl_data = []
+
+    # Convert the input JSON to JSONL format
+    for key, value in enumerate(data):
+
+        if args.dataset == "something":
+            input_path = value["input"]
+            output_path = value["output"]
+            file_check = os.path.exists(input_path) and os.path.exists(output_path)
+        else:
+            file_check = True
+
+        if file_check:
+        
+            if args.training_format == "sft-editing":
+                entry = {
+                    "id": f"{int(key):012d}",
+                    "images": ["AURORA/"+value["input"], "AURORA/"+value["output"]],
+                    "conversations": [
+                        {
+                            "from": "human",
+                            "value": f"<image>\nEditing the given image according to the following prompt: {value['instruction']}"
+                        },
+                        {
+                            "from": "gpt",
+                            "value": "<image>"
+                        }
+                    ]
+                }
+            elif args.training_format == "sft-action-verbolise":
+                entry = {
+                    "id": f"{int(key):012d}",
+                    "images": ["AURORA/"+value["input"], "AURORA/"+value["output"]],
+                    "conversations": [
+                        {
+                            "from": "human",
+                            "value": f"You are given two sequential observations in the form of images.\n\nPast observations:\n<image>\nNext observation after taking the action:\n<image>\n\nYour task is to infer and describe the most likely action that occurred between the past and next observations. The action should be described concisely in natural language, capturing key changes that explain the state transition."
+                        },
+                        {
+                            "from": "gpt",
+                            "value": "The most likely action that occurred between the observations is: "+value['instruction']
+                        }
+                    ]
+                }
+            else:
+                raise NotImplementedError
+            jsonl_data.append(entry)
+
+        else:
+            continue
+
+    # Save to a JSONL file
+    with open("data/{s}/{f}-train.jsonl".format(s=args.dataset, f=args.training_format), "w") as f:
+        for line in jsonl_data:
+            f.write(json.dumps(line) + "\n")

datasheet.md

@@ -0,0 +1,311 @@
+# Datasheet for dataset "AURORA"
+
+Questions from the [Datasheets for Datasets](https://arxiv.org/abs/1803.09010) paper, v7.
+
+Jump to section:
+
+- [Motivation](#motivation)
+- [Composition](#composition)
+- [Collection process](#collection-process)
+- [Preprocessing/cleaning/labeling](#preprocessingcleaninglabeling)
+- [Uses](#uses)
+- [Distribution](#distribution)
+- [Maintenance](#maintenance)
+
+## Motivation
+
+_The questions in this section are primarily intended to encourage dataset creators
+to clearly articulate their reasons for creating the dataset and to promote transparency
+about funding interests._
+
+### For what purpose was the dataset created? 
+
+We collected AURORA since there is no current high-quality dataset for instruction-guided image editing where the instruction is an action such as "move carrots into the sink". As a result, the current image editing are quite limited and not as "general" as one would hope. This is an important subtask of image editing and can enable many downstream applications. There have been few training datasets for these sort of edit instructions and the ones that exist have very noisy data, i.e. where the target image shows far more changes than described in the text, or the change described is not even properly shown.
+
+### Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)?
+It was developed primarily at "Mila - Quebec Artificial Intelligence Institute", specifically in Siva Reddy's lab by his PhD student Benno Krojer. Other collaborators on the paper were involved in the ideation, many of them also at Mila and one of them at Stability AI.
+
+### Who funded the creation of the dataset? 
+The dataset was funded by the PI, Siva Reddy.
+
+### Any other comments?
+None.
+
+## Composition
+
+_Most of these questions are intended to provide dataset consumers with the
+information they need to make informed decisions about using the dataset for
+specific tasks. The answers to some of these questions reveal information
+about compliance with the EU’s General Data Protection Regulation (GDPR) or
+comparable regulations in other jurisdictions._
+
+### What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)?
+
+Each datapoint is a triplet of (source image, prompt, target image), i.e. (an image of a dog, "make the dog smile", an image of a dog smiling).
+Our data consists of four sub-datasets:
+1. MagicBrush: **Source images** are diverse web-scrapped images ([MS-COCO](https://cocodataset.org/#home) which comes from websites like Flickr). **Prompt** and **target images** were previously crowd-sourced with humans using the DALL-E 2 editing interface.
+2. Action-Genome-Edit and Something-Something-Edit:** source** and **target images** are video frames depicting activities mostly at home; the **prompt** is human written (crowd-sourced by us or in the case of Something Something at the time of video recording in the original dataset).
+3. Kubric-Edit: **Source** and **target images** were generated in a simulation engine (Kubric), and depict non-human objects. The **prompt** is templated.
+
+### How many instances are there in total (of each type, if appropriate)?
+9K (MagicBrush) + 11K (Action-Genome-Edit) + 119K (Something-Something-Edit) + 150K (Kubric-Edit) = 149K + 150K = 399K
+
+### Does the dataset contain all possible instances or is it a sample (not necessarily random) of instances from a larger set?
+
+It is not really a sample, but we did have to filter out video frames that were too noisy or showed too much change such as camera movement.
+
+### What data does each instance consist of? 
+
+Two raw images (source & target), and a string (the prompt).
+
+### Is there a label or target associated with each instance?
+
+The **target image** is the structure that the model has to predict during training and test time.
+
+### Is any information missing from individual instances?
+
+No.
+
+### Are relationships between individual instances made explicit (e.g., users’ movie ratings, social network links)?
+
+In MagicBrush there are sequential edits, that are indicated by the json key "img_id".
+In Action-Genome edit, some datapoints can come from the same video clip, which can be checked in the filename.
+
+### Are there recommended data splits (e.g., training, development/validation, testing)?
+
+We release training data separately from the AURORA-Bench data. The test data is much smaller and the test split of each of our training sub-datasets contributes to it.
+
+### Are there any errors, sources of noise, or redundancies in the dataset?
+
+The main source of noise comes with the video-frame-based data where sometimes there can be more changes than described in language. Or the change described in the prompt is not shown clearly.
+
+### Is the dataset self-contained, or does it link to or otherwise rely on external resources (e.g., websites, tweets, other datasets)?
+
+Self-contained, except that we ask people to download the videos from the original Something Something website, instead of providing the actual image files.
+
+### Does the dataset contain data that might be considered confidential (e.g., data that is protected by legal privilege or by doctor-patient confidentiality, data that includes the content of individuals’ non-public communications)?
+
+No, it was crowd-souced with paid workers who agreed to work on this task.
+
+### Does the dataset contain data that, if viewed directly, might be offensive, insulting, threatening, or might otherwise cause anxiety?
+
+No.
+
+### Does the dataset relate to people? 
+
+Especially the Action-Genome-Edit data depicts people in their homes.
+
+### Does the dataset identify any subpopulations (e.g., by age, gender)?
+
+We do not know the exact recruitment for Action-Genome and Something Something videos (we build on top of these), but there are usually requirements such as speaking English.
+In our case, we only worked with 7 workers that had shown to produce high-quality data. We do not know their age or other personal details as this information is not direclty shown in Amazon Mechanical Turk.
+
+### Is it possible to identify individuals (i.e., one or more natural persons), either directly or indirectly (i.e., in combination with other data) from the dataset?
+
+If someone really tried, they might be able to identify some of the people in Action-Genome-Edit since they are shown fully and in their home. This would have to rely on advanced facial recognition and matching with other databases.
+
+### Does the dataset contain data that might be considered sensitive in any way (e.g., data that reveals racial or ethnic origins, sexual orientations, religious beliefs, political opinions or union memberships, or locations; financial or health data; biometric or genetic data; forms of government identification, such as social security numbers; criminal history)?
+
+No.
+
+### Any other comments?
+None.
+
+## Collection process
+
+_\[T\]he answers to questions here may provide information that allow others to
+reconstruct the dataset without access to it._
+
+### How was the data associated with each instance acquired?
+
+_Was the data directly observable (e.g., raw text, movie ratings), reported by subjects (e.g.,
+survey responses), or indirectly inferred/derived from other data (e.g., part-of-speech tags,
+model-based guesses for age or language)? If data was reported by subjects or indirectly
+inferred/derived from other data, was the data validated/verified? If so, please describe how._
+
+For the sub-datasets MagicBrush, Action-Genome-Edit and Something-Something-Edit the prompts were written by humans and in the case of MagicBrush, the edited images were also produced in collaboration with an AI editing tool (DALL-E 2).
+Only Kubric-Edit is fully synthetic.
+
+The data was verified for "truly minimal" image pairs (as described in the paper), i.e. that all the changes from source to target are also described in the prompt. Only for Something-Something-Edit, this was not done on an instance-level but based on categories/labels and thus there will be some non-minimal pairs.
+
+### What mechanisms or procedures were used to collect the data (e.g., hardware apparatus or sensor, manual human curation, software program, software API)?
+
+_How were these mechanisms or procedures validated?_
+
+For the data we collected ourselves with humans (Action-Genome-Edit), we used Amazon Mechanical Turk (see Appendix of the paper for screenshots of our interface).
+We recruited the best workers from previous test runs and had lengthy e-mail exchanges to verify everything makes sense for them and we get good quality.
+For Kubric-Edit we used a simulation engine called Kubric.
+
+### If the dataset is a sample from a larger set, what was the sampling strategy (e.g., deterministic, probabilistic with specific sampling probabilities)?
+
+### Who was involved in the data collection process (e.g., students, crowdworkers, contractors) and how were they compensated (e.g., how much were crowdworkers paid)?
+
+We worked with 7 workers from Amazon Mechanical Turk and paid them 0.22$ USD per example, resulting in an estimated 10-20$ per hour.
+
+### Over what timeframe was the data collected?
+
+_Does this timeframe match the creation timeframe of the data associated with the instances (e.g.
+recent crawl of old news articles)? If not, please describe the timeframe in which the data
+associated with the instances was created._
+
+Around a week at the end of April 2024 for the main collection of Action-Genome. For the others, we constructed it from March to May with refinements.
+
+### Were any ethical review processes conducted (e.g., by an institutional review board)?
+
+No.
+
+### Does the dataset relate to people?
+
+Only in the sense that the prompts were written by people and that 1-2 dataset we build on top of depicts people.
+
+### Did you collect the data from the individuals in question directly, or obtain it via third parties or other sources (e.g., websites)?
+
+We collected it directly from AMT.
+
+### Were the individuals in question notified about the data collection?
+
+_If so, please describe (or show with screenshots or other information) how notice was provided,
+and provide a link or other access point to, or otherwise reproduce, the exact language of the
+notification itself._
+
+Workers on AMT see the posting with details like price and task description. In our case, we simply emailed workers from previous collections, and also told them it is for a research publication (i.e. linking to similar papers to give them an idea of what they are working on).
+
+### Did the individuals in question consent to the collection and use of their data?
+
+They implicitly agreed to various uses through the terms of service by MTurk: https://www.mturk.com/participation-agreement
+
+### If consent was obtained, were the consenting individuals provided with a mechanism to revoke their consent in the future or for certain uses?
+
+I am not sure about that part of MTurk's legal agreement but would guess no. I could not find an exact passage describing this, perhaps the the section "Use of Information; Publicity and Confidentiality"
+
+### Has an analysis of the potential impact of the dataset and its use on data subjects (e.g., a data protection impact analysis) been conducted?
+
+No.
+
+### Any other comments?
+
+None.
+
+## Preprocessing/cleaning/labeling
+
+_The questions in this section are intended to provide dataset consumers with the information
+they need to determine whether the “raw” data has been processed in ways that are compatible
+with their chosen tasks. For example, text that has been converted into a “bag-of-words” is
+not suitable for tasks involving word order._
+
+### Was any preprocessing/cleaning/labeling of the data done (e.g., discretization or bucketing, tokenization, part-of-speech tagging, SIFT feature extraction, removal of instances, processing of missing values)?
+
+We mainly filtered out image pairs with too many changes: We told workers to discard images with too many (or in rare cases too few changes). We automatically pre-filtered by "CLIP-score" (the cosine similarity between the visual embeddings of source and target image) for Action-Genome-Edit and Something-Something-Edit.
+
+### Was the “raw” data saved in addition to the preprocessed/cleaned/labeled data (e.g., to support unanticipated future uses)?
+
+It was not directly saved but can be accessed again by downloading the original sources we build upon such as Action-Genome videos (or frames from [EQBEN](https://github.com/Wangt-CN/EqBen), or the Something Something dataset.
+
+### Is the software used to preprocess/clean/label the instances available?
+
+We provide scripts on how to go from raw videos/frames to the cleaner ones on our repository.
+
+### Any other comments?
+
+None.
+
+## Uses
+
+_These questions are intended to encourage dataset creators to reflect on the tasks
+for which the dataset should and should not be used. By explicitly highlighting these tasks,
+dataset creators can help dataset consumers to make informed decisions, thereby avoiding
+potential risks or harms._
+
+### Has the dataset been used for any tasks already?
+
+We used it to train an image editing model. We expect similar applications, also to video generation models.
+MagicBrush has been used by several people.
+
+### Is there a repository that links to any or all papers or systems that use the dataset?
+
+Our code repository, or [MagicBrush](https://github.com/OSU-NLP-Group/MagicBrush).
+
+### What (other) tasks could the dataset be used for?
+
+Training models for video generation, change descriptions (i.e. Vision-and-Language LLMs) or discrimination of two similar images.
+A possible negative application further down the road is surveillance systems that need to detect minor changes.
+
+### Is there anything about the composition of the dataset or the way it was collected and preprocessed/cleaned/labeled that might impact future uses?
+
+Not that I can think of.
+
+### Are there tasks for which the dataset should not be used?
+
+Unsure.
+
+### Any other comments?
+
+None.
+
+## Distribution
+
+### Will the dataset be distributed to third parties outside of the entity (e.g., company, institution, organization) on behalf of which the dataset was created? 
+
+We will fully open-source it and provide access via Zenodo/json files as well as Huggingface Datasets.
+
+### How will the dataset will be distributed (e.g., tarball on website, API, GitHub)?
+
+Both Zenodo and Huggingface datasets.
+
+### When will the dataset be distributed?
+
+The weeks after submission to NeurIPS Dataset & Benchmark track, so in June 2024.
+
+### Will the dataset be distributed under a copyright or other intellectual property (IP) license, and/or under applicable terms of use (ToU)?
+
+We stick with the standard open-source license: MIT License
+
+### Have any third parties imposed IP-based or other restrictions on the data associated with the instances?
+
+Something Something is the only dataset with a restricted license (it seems, I don't speak legalese: [License Terms](https://developer.qualcomm.com/software/ai-datasets/something-something)).
+So we are planning to link to their website and provide scripts to get to our final data.
+
+### Do any export controls or other regulatory restrictions apply to the dataset or to individual instances?
+
+[Official access and licensing](https://developer.qualcomm.com/software/ai-datasets/something-something) of Something Something dataset.
+
+### Any other comments?
+
+None.
+
+## Maintenance
+
+_These questions are intended to encourage dataset creators to plan for dataset maintenance
+and communicate this plan with dataset consumers._
+
+### Who is supporting/hosting/maintaining the dataset?
+
+The main author is responsible for ensuring long-term accessibility, which relies on Zenodo and Huggingface.
+
+### How can the owner/curator/manager of the dataset be contacted (e.g., email address)?
+
+[email protected] (or after I finish my PhD [email protected])
+
+### Is there an erratum?
+
+Not yet!
+
+### Will the dataset be updated (e.g., to correct labeling errors, add new instances, delete instances)?
+
+Not sure yet. If we find that people are interested in the data or trained model, we will continue our efforts.
+
+### If the dataset relates to people, are there applicable limits on the retention of the data associated with the instances (e.g., were individuals in question told that their data would be retained for a fixed period of time and then deleted)?
+
+No.
+
+### Will older versions of the dataset continue to be supported/hosted/maintained?
+
+If there ever was an update, yes.
+
+### If others want to extend/augment/build on/contribute to the dataset, is there a mechanism for them to do so?
+
+Since we use a non-restricting license (MIT license), anyone can build on top or include in their training data mixture.
+
+### Any other comments?
+
+No. We hope the data is useful to people!

disc_edit.py

@@ -0,0 +1,251 @@
+from __future__ import annotations
+
+import math
+import random
+import sys
+from argparse import ArgumentParser
+
+import einops
+import k_diffusion as K
+import numpy as np
+import torch
+import torch.nn as nn
+from einops import rearrange
+from omegaconf import OmegaConf
+from PIL import Image, ImageOps
+from torch import autocast
+from PIL import Image, ImageDraw, ImageFont
+import textwrap
+import json
+import os
+from dataset_loading import get_dataset
+from edit_dataset import EditITMDataset
+from torch.utils.data import DataLoader
+from tqdm import tqdm
+import clip
+from collections import defaultdict
+
+sys.path.append("./stable_diffusion")
+from stable_diffusion.ldm.util import instantiate_from_config
+
+# Assuming CFGDenoiser and other dependencies are correctly set up,
+# no changes needed there for image aspect ratio handling.
+
+
+def calculate_clip_similarity(generated_images, original_image, clip_model, preprocess, device):
+    original_image_processed = preprocess(original_image).unsqueeze(0).to(device)
+    
+    with torch.no_grad():
+        original_features = clip_model.encode_image(original_image_processed)
+
+    similarities = []
+    for img in generated_images:
+        img_processed = preprocess(img).unsqueeze(0).to(device)
+        with torch.no_grad():
+            generated_features = clip_model.encode_image(img_processed)
+        similarity = torch.nn.functional.cosine_similarity(generated_features, original_features, dim=-1)
+        similarities.append(similarity.item())
+
+        #concat both img and original_image for visualization
+        # original_image_np = np.array(original_image)
+        # img_np = np.array(img)
+        # both = np.concatenate((original_image_np, img_np), axis=1)
+        # both = Image.fromarray(both)
+        # if not os.path.exists('eval_output/edit_itm/flickr_edit_clip_sim/'):
+        #     os.makedirs('eval_output/edit_itm/flickr_edit_clip_sim/')
+        # random_id = random.randint(0, 100000)
+        # both.save(f'eval_output/edit_itm/flickr_edit_clip_sim/{similarity.item()}_{random_id}.png')
+
+    # average_similarity = sum(similarities) / len(similarities)
+    # dist = 1 - average_similarity
+    dists = [1 - sim for sim in similarities]
+    return dists
+
+
+class CFGDenoiser(nn.Module):
+    def __init__(self, model):
+        super().__init__()
+        self.inner_model = model
+
+    def forward(self, z, sigma, cond, uncond, text_cfg_scale, image_cfg_scale, conditional_only=False):
+        # cfg_z = einops.repeat(z, "1 ... -> n ...", n=3)
+        cfg_z = z.repeat(3, 1, 1, 1)
+        # cfg_sigma = einops.repeat(sigma, "1 ... -> n ...", n=3)
+        cfg_sigma = sigma.repeat(3)
+        cfg_cond = {
+            "c_crossattn": [torch.cat([cond["c_crossattn"][0], uncond["c_crossattn"][0], uncond["c_crossattn"][0]])],
+            "c_concat": [torch.cat([cond["c_concat"][0], cond["c_concat"][0], uncond["c_concat"][0]])],
+        }
+        out_cond, out_img_cond, out_uncond = self.inner_model(cfg_z, cfg_sigma, cond=cfg_cond).chunk(3)
+        if conditional_only:
+            return out_cond
+        else:
+            return out_uncond + text_cfg_scale * (out_cond - out_img_cond) + image_cfg_scale * (out_img_cond - out_uncond)
+
+def load_model_from_config(config, ckpt, vae_ckpt=None, verbose=False):
+    print(f"Loading model from {ckpt}")
+    pl_sd = torch.load(ckpt, map_location="cpu")
+    if "global_step" in pl_sd:
+        print(f"Global Step: {pl_sd['global_step']}")
+    sd = pl_sd["state_dict"]
+    if vae_ckpt is not None:
+        print(f"Loading VAE from {vae_ckpt}")
+        vae_sd = torch.load(vae_ckpt, map_location="cpu")["state_dict"]
+        sd = {
+            k: vae_sd[k[len("first_stage_model.") :]] if k.startswith("first_stage_model.") else v
+            for k, v in sd.items()
+        }
+    model = instantiate_from_config(config.model)
+    m, u = model.load_state_dict(sd, strict=False)
+    if len(m) > 0 and verbose:
+        print("missing keys:")
+        print(m)
+    if len(u) > 0 and verbose:
+        print("unexpected keys:")
+        print(u)
+    return model
+
+def calculate_accuracy(losses):
+    correct_count = 0
+    for loss in losses:
+        if loss[0] < min(loss[1:]):
+            correct_count += 1
+    return correct_count, len(losses)  # Return counts for aggregation
+
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument("--config", default="configs/generate.yaml", type=str)
+    parser.add_argument("--ckpt", default="aurora-mixratio-15-15-1-1-42k-steps.ckpt", type=str)
+    parser.add_argument("--vae-ckpt", default=None, type=str)
+    parser.add_argument("--task", default='flickr_edit', type=str)
+    parser.add_argument("--batchsize", default=1, type=int)
+    parser.add_argument("--samples", default=4, type=int)
+    parser.add_argument("--size", default=512, type=int)
+    parser.add_argument("--steps", default=20, type=int)
+    parser.add_argument("--cfg-text", default=7.5, type=float)
+    parser.add_argument("--cfg-image", default=1.5, type=float)
+    parser.add_argument('--targets', type=str, nargs='*', help="which target groups for mmbias",default='')
+    parser.add_argument("--device", default=0, type=int, help="GPU device index")
+    parser.add_argument("--log_imgs", action="store_true")
+    parser.add_argument("--conditional_only", action="store_true")
+    parser.add_argument("--metric", default="latent", type=str)
+    parser.add_argument("--split", default='test', type=str)
+    parser.add_argument("--skip", default=1, type=int)
+    args = parser.parse_args()
+    device = torch.device(f"cuda:{args.device}" if torch.cuda.is_available() else "cpu")
+
+    config = OmegaConf.load(args.config)
+    model = load_model_from_config(config, args.ckpt, args.vae_ckpt)
+    model.eval()
+    model.to(dtype=torch.float)
+    model = model.to(device)
+    model_wrap = K.external.CompVisDenoiser(model)
+    model_wrap_cfg = CFGDenoiser(model_wrap)
+    null_token = model.get_learned_conditioning([""])
+
+    clip_model, preprocess = clip.load("ViT-B/32", device=device)
+
+    dataset = EditITMDataset(split=args.split, task=args.task, min_resize_res=args.size, max_resize_res=args.size, crop_res=args.size)
+    dataloader= DataLoader(dataset,batch_size=args.batchsize,num_workers=1,worker_init_fn=None,shuffle=False, persistent_workers=True)
+
+    if os.path.exists(f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}_results.json'):
+        with open(f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}_results.json', 'r') as f:
+            results = json.load(f)
+            results = defaultdict(dict, results)
+    else:
+        results = defaultdict(dict)
+
+    for i, batch in tqdm(enumerate(dataloader), total=len(dataloader)):
+        if len(batch['input'][0].shape) < 3:
+            continue
+        for j, prompt in enumerate(batch['texts']):
+            # check if we already have results for this image
+            img_id = batch['path'][0] + f'_{i}'
+            # if img_id in results and ('pos' in results[img_id] and 'neg' in results[img_id]):
+            #     continue
+
+            with torch.no_grad(), autocast("cuda"), model.ema_scope():
+                prompt = prompt[0]
+                cond = {}
+                cond["c_crossattn"] = [model.get_learned_conditioning([prompt])]
+                input_image = batch['input'][0].to(device)
+                cond["c_concat"] = [model.encode_first_stage(input_image.unsqueeze(0)).mode()]
+                scaled_input = model.scale_factor * input_image
+
+                uncond = {}
+                uncond["c_crossattn"] = [null_token]
+                uncond["c_concat"] = [torch.zeros_like(cond["c_concat"][0])]
+
+                sigmas = model_wrap.get_sigmas(args.steps)
+                # move everything to the device
+                cond = {k: [v.to(device) for v in vs] for k, vs in cond.items()}
+                uncond = {k: [v.to(device) for v in vs] for k, vs in uncond.items()}
+
+                cond["c_concat"][0] = cond["c_concat"][0].repeat(args.samples, 1, 1, 1)
+                cond["c_crossattn"][0] = cond["c_crossattn"][0].repeat(args.samples, 1, 1)
+                uncond["c_concat"][0] = uncond["c_concat"][0].repeat(args.samples, 1, 1, 1)
+                uncond["c_crossattn"][0] = uncond["c_crossattn"][0].repeat(args.samples, 1, 1)
+
+                extra_args = {
+                    "cond": cond,
+                    "uncond": uncond,
+                    "text_cfg_scale": args.cfg_text,
+                    "image_cfg_scale": args.cfg_image,
+                    "conditional_only": args.conditional_only,
+                }
+                # torch.manual_seed(i)
+                torch.manual_seed(42)
+                z = torch.randn_like(cond["c_concat"][0]) * sigmas[0]
+                z = K.sampling.sample_euler_ancestral(model_wrap_cfg, z, sigmas, extra_args=extra_args, disable=True)
+                x = model.decode_first_stage(z)
+                x = torch.clamp((x + 1.0) / 2.0, min=0.0, max=1.0)
+                
+            ######## LOG IMAGES ########
+                input_image_pil = ((input_image + 1) * 0.5).clamp(0, 1)
+                input_image_pil = input_image_pil.permute(1, 2, 0)  # Change from CxHxW to HxWxC for PIL
+                input_image_pil = (input_image_pil * 255).type(torch.uint8).cpu().numpy()
+
+                for k in range(2):
+                    x_ = 255.0 * rearrange(x[k], "c h w -> h w c")
+                    edited_image = x_.type(torch.uint8).cpu().numpy()
+                    both = np.concatenate((input_image_pil, edited_image), axis=1)
+                    both = Image.fromarray(both)
+                    out_base = f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}'
+                    if not os.path.exists(out_base):
+                        os.makedirs(out_base)
+                    prompt_str = prompt.replace(' ', '_')[0:100]
+                    both.save(f'{out_base}/{i}_{"correct" if j == 0 else "incorrect"}_sample{k}_{prompt}.png')
+                
+            ######## CLIP ########
+
+                edited_images = []
+                for k in range(args.samples):
+                    x_ = 255.0 * rearrange(x[k], "c h w -> h w c")
+                    edited_image = Image.fromarray(x_.type(torch.uint8).cpu().numpy())
+                    edited_images.append(edited_image)
+                input_image_pil = ((input_image + 1) * 0.5).clamp(0, 1)
+                input_image_pil = input_image_pil.permute(1, 2, 0)  # Change from CxHxW to HxWxC for PIL
+                input_image_pil = (input_image_pil * 255).type(torch.uint8).cpu().numpy()
+                input_image_pil = Image.fromarray(input_image_pil)
+                dists_clip = calculate_clip_similarity(edited_images, input_image_pil, clip_model, preprocess, device)
+
+            ######## LATENT ########
+                z = z.flatten(1)
+                original_latent = cond["c_concat"][0].flatten(1)
+                dists_latent = torch.norm(z - original_latent, dim=1, p=2).cpu().numpy().tolist()
+                cos_sim = torch.nn.functional.cosine_similarity(z, original_latent, dim=1).cpu().numpy().tolist()
+                cos_dists_latent = [1 - sim for sim in cos_sim]
+            ######## SAVE RESULTS ########
+                img_id = batch['path'][0] + f'_{i}'
+                results[img_id]['pos' if j == 0 else 'neg'] = {
+                    "prompt" : prompt,
+                    "clip": dists_clip,
+                    "latent_l2": dists_latent,
+                    "latent_cosine": cos_dists_latent
+                }
+                with open(f'itm_evaluation/{args.split}/{args.task}/{args.ckpt.replace("/", "_")}_results.json', 'w') as f:
+                    json.dump(results, f, indent=2)
+
+if __name__ == "__main__":
+    main()

edit_cli.py

@@ -0,0 +1,124 @@
+from __future__ import annotations
+
+import math
+import random
+import sys
+from argparse import ArgumentParser
+
+import einops
+import k_diffusion as K
+import numpy as np
+import torch
+import torch.nn as nn
+from einops import rearrange
+from omegaconf import OmegaConf
+from PIL import Image, ImageOps
+from torch import autocast
+
+sys.path.append("./stable_diffusion")
+
+from stable_diffusion.ldm.util import instantiate_from_config
+
+
+class CFGDenoiser(nn.Module):
+    def __init__(self, model):
+        super().__init__()
+        self.inner_model = model
+
+    def forward(self, z, sigma, cond, uncond, text_cfg_scale, image_cfg_scale):
+        cfg_z = einops.repeat(z, "1 ... -> n ...", n=3)
+        cfg_sigma = einops.repeat(sigma, "1 ... -> n ...", n=3)
+        cfg_cond = {
+            "c_crossattn": [torch.cat([cond["c_crossattn"][0], uncond["c_crossattn"][0], uncond["c_crossattn"][0]])],
+            "c_concat": [torch.cat([cond["c_concat"][0], cond["c_concat"][0], uncond["c_concat"][0]])],
+        }
+        out_cond, out_img_cond, out_uncond = self.inner_model(cfg_z, cfg_sigma, cond=cfg_cond).chunk(3)
+        return out_uncond + text_cfg_scale * (out_cond - out_img_cond) + image_cfg_scale * (out_img_cond - out_uncond)
+
+
+def load_model_from_config(config, ckpt, vae_ckpt=None, verbose=False):
+    print(f"Loading model from {ckpt}")
+    pl_sd = torch.load(ckpt, map_location="cpu")
+    if "global_step" in pl_sd:
+        print(f"Global Step: {pl_sd['global_step']}")
+    sd = pl_sd["state_dict"]
+    if vae_ckpt is not None:
+        print(f"Loading VAE from {vae_ckpt}")
+        vae_sd = torch.load(vae_ckpt, map_location="cpu")["state_dict"]
+        sd = {
+            k: vae_sd[k[len("first_stage_model.") :]] if k.startswith("first_stage_model.") else v
+            for k, v in sd.items()
+        }
+    model = instantiate_from_config(config.model)
+    m, u = model.load_state_dict(sd, strict=False)
+    if len(m) > 0 and verbose:
+        print("missing keys:")
+        print(m)
+    if len(u) > 0 and verbose:
+        print("unexpected keys:")
+        print(u)
+    return model
+
+
+def main():
+    parser = ArgumentParser()
+    parser.add_argument("--resolution", default=512, type=int)
+    parser.add_argument("--steps", default=50, type=int)
+    parser.add_argument("--config", default="configs/generate.yaml", type=str)
+    parser.add_argument("--ckpt", default="aurora-mixratio-15-15-1-1-42k-steps.ckpt", type=str)
+    parser.add_argument("--vae-ckpt", default=None, type=str)
+    parser.add_argument("--input", default='example.jpg', type=str)
+    parser.add_argument("--output", default='example_output.jpg', type=str)
+    parser.add_argument("--edit", default='move the lemon to the right of the table', type=str)
+    parser.add_argument("--cfg-text", default=7.5, type=float)
+    parser.add_argument("--cfg-image", default=1.5, type=float)
+    parser.add_argument("--seed", default=42, type=int)
+    args = parser.parse_args()
+
+    config = OmegaConf.load(args.config)
+    model = load_model_from_config(config, args.ckpt, args.vae_ckpt)
+    model.eval().to('cuda:7')
+    model_wrap = K.external.CompVisDenoiser(model)
+    model_wrap_cfg = CFGDenoiser(model_wrap)
+    null_token = model.get_learned_conditioning([""])
+
+    seed = random.randint(0, 100000) if args.seed is None else args.seed
+    input_image = Image.open(args.input).convert("RGB")
+    width, height = input_image.size
+    factor = args.resolution / max(width, height)
+    factor = math.ceil(min(width, height) * factor / 64) * 64 / min(width, height)
+    width = int((width * factor) // 64) * 64
+    height = int((height * factor) // 64) * 64
+    input_image = ImageOps.fit(input_image, (width, height), method=Image.Resampling.LANCZOS)
+
+    with torch.no_grad(), autocast("cuda"), model.ema_scope():
+        cond = {}
+        cond["c_crossattn"] = [model.get_learned_conditioning([args.edit])]
+        input_image = 2 * torch.tensor(np.array(input_image)).float() / 255 - 1
+        input_image = rearrange(input_image, "h w c -> 1 c h w").to(model.device)
+        cond["c_concat"] = [model.encode_first_stage(input_image).mode()]
+
+        uncond = {}
+        uncond["c_crossattn"] = [null_token]
+        uncond["c_concat"] = [torch.zeros_like(cond["c_concat"][0])]
+
+        sigmas = model_wrap.get_sigmas(args.steps)
+
+        extra_args = {
+            "cond": cond,
+            "uncond": uncond,
+            "text_cfg_scale": args.cfg_text,
+            "image_cfg_scale": args.cfg_image,
+        }
+        torch.manual_seed(seed)
+        z = torch.randn_like(cond["c_concat"][0]) * sigmas[0]
+        z = K.sampling.sample_euler_ancestral(model_wrap_cfg, z, sigmas, extra_args=extra_args)
+        x = model.decode_first_stage(z)
+        x = torch.clamp((x + 1.0) / 2.0, min=0.0, max=1.0)
+        x = 255.0 * rearrange(x, "1 c h w -> h w c")
+        edited_image = Image.fromarray(x.type(torch.uint8).cpu().numpy())
+    edited_image.save(args.output)
+
+
+if __name__ == "__main__":
+    main()

edit_dataset.py

@@ -0,0 +1,603 @@
+from __future__ import annotations
+
+import json
+import math
+from pathlib import Path
+from typing import Any
+
+import numpy as np
+import torch
+import torchvision
+from einops import rearrange
+from PIL import Image
+from torch.utils.data import Dataset
+import os
+from datasets import load_dataset, DownloadConfig
+from tqdm import tqdm
+
+from PIL import ImageFile
+ImageFile.LOAD_TRUNCATED_IMAGES = True
+
+class FinetuneDataset(Dataset):
+    def __init__(
+        self,
+        path: str = '',
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.5,
+        msr_vtt_cc_full: bool = False,
+        mix: list[str] = ['magicbrush', 'something', 'hq'],
+        mix_factors: list[float] = [40, 1, 1],
+        copy_prob: float = 0.0,
+        kubric_100k: bool = False,
+    ):
+        self.split = split
+        assert split in ("train", "val", "test")
+        assert sum(splits) == 1
+        self.path = path
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+        self.mix_factors = mix_factors
+        self.msr_vtt_cc_full = msr_vtt_cc_full
+        self.copy_prob = copy_prob
+
+        self.data = []
+        for dataset in mix:
+            if dataset != 'hq':
+                for _ in range(mix_factors[mix.index(dataset)]):
+                    if kubric_100k and dataset == 'kubric':
+                        self.data.extend(json.load(open(f'data/{dataset}/train_100k.json', 'r')))
+                        print("LODADED KUBRIC 100K")
+                    else:
+                        self.data.extend(json.load(open(f'data/{dataset}/train.json', 'r')))
+                    # if dataset == 'msr-vtt-cc':
+                    #     self.data.extend(json.load(open(f'data/{dataset}/train_gpt.json', 'r')))
+
+        if split == 'val':
+            self.data = self.data[:2]
+ 
+    def __len__(self) -> int:
+        return len(self.data)
+    
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        # if i < len(self.data):
+        ex = self.data[i]
+        img_path0 = ex['input']
+        img_path1 = ex['output']
+        prompt = ex['instruction']
+        dataset = img_path0.split('/')[1]
+        if dataset == 'kubric':
+            subtask = img_path0.split('/')[2]
+        else:
+            subtask = '___'
+        
+        if type(prompt) == list:
+            prompt = prompt[0]
+        spatial = 'left' in prompt.lower() or 'right' in prompt.lower()
+        image_1 = Image.open(img_path1).convert('RGB') if i < len(self.data) else img_path1
+
+        if subtask not in ['closer', 'counting', 'further_location', 'rotate']:
+            if self.copy_prob > 0 and torch.rand(1) < self.copy_prob:
+                image_0 = Image.open(img_path1).convert('RGB') if i < len(self.data) else img_path1
+            else:
+                image_0 = Image.open(img_path0).convert('RGB') if i < len(self.data) else img_path0
+        else:
+            image_0 = Image.open(img_path0).convert('RGB') if i < len(self.data) else img_path0
+
+        reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+        image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+        crop = torchvision.transforms.RandomCrop(self.crop_res)
+        flip_prob = 0.0 if spatial else self.flip_prob
+        flip = torchvision.transforms.RandomHorizontalFlip(float(flip_prob))
+        image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+        return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class MagicEditDataset(Dataset):
+    def __init__(
+        self,
+        path: str = '../../change_descriptions/something-something',
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.0,
+        debug: bool = False,
+    ):
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+
+        print("Dataset params")
+        print(self.min_resize_res, self.max_resize_res, self.crop_res, self.flip_prob)
+
+        #clean json (if first and last are not both present, remove)
+        split = "train" if split == "train" else "dev"
+        self.dataset = load_dataset("osunlp/MagicBrush")[split]
+
+        # if split == 'dev':
+        #     eval_data = json.load(open('eval_data/video_edit.json', 'r'))
+        #     dummy_image = Image.new('RGB', (1, 1), (0, 0, 0))
+        #     eval_data = {
+        #         'source_img': [Image.open(x['img0']) for x in eval_data],
+        #         'target_img': [Image.open(x['img1']) for x in eval_data],
+        #         'instruction': [x['edit'] if type(x['edit']) == str else x['edit'][0] for x in eval_data],
+        #         'img_id': ['' for _ in eval_data],
+        #         'turn_index': np.array([1 for _ in eval_data], dtype=np.int32),
+        #         'mask_img': [dummy_image for _ in eval_data]  # Replace each entry with the dummy image
+        #     }
+        #     eval_dataset = HuggingFaceDataset.from_dict(eval_data)
+        #     self.dataset = concatenate_datasets([self.dataset, eval_dataset])
+
+        if debug:
+            self.dataset = self.dataset.shuffle(seed=42).select(range(50))
+
+    def __len__(self) -> int:
+        return len(self.dataset)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        
+        prompt = self.dataset[i]['instruction']
+        if type(prompt) == list:
+            prompt = prompt[0]
+        image_0 = self.dataset[i]['source_img']
+        image_1 = self.dataset[i]['target_img']
+        if image_0.mode == 'RGBA':
+            image_0 = image_0.convert('RGB')
+        if image_1.mode == 'RGBA':
+            image_1 = image_1.convert('RGB')
+        reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+        image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+        crop = torchvision.transforms.RandomCrop(self.crop_res)
+        flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+        image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+        return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class FrameEditDataset(Dataset):
+    def __init__(
+        self,
+        path: str = '../../change_descriptions/something-something',
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        task: str = 'flickr30k_text',
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.0,
+        debug: bool = False,
+    ):
+        self.split = split
+        self.task = task
+        if split == "train":
+            path = os.path.join(path, 'train.json')
+            self.json = json.load(open(path, 'r'))
+            np.random.shuffle(self.json)
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+
+        #clean json (if first and last are not both present, remove)
+        if split == 'train':
+            new_json = []
+            for i in range(len(self.json)):
+                video_id = self.json[i]['id']
+                img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+                img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+                if os.path.exists(img_path0) and os.path.exists(img_path1):
+                    new_json.append(self.json[i])
+            self.json = new_json
+        if debug:
+            self.json = self.json[:50]
+
+    def __len__(self) -> int:
+        return len(self.json)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        if self.split == 'train':
+            video_id = self.json[i]['id']
+            img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+            img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+            prompt = self.json[i]['label']
+        
+        image_0 = Image.open(img_path0).convert('RGB')
+        image_1 = Image.open(img_path1).convert('RGB')
+
+        reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+        # image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        # image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        image_0 = image_0.resize((self.crop_res, self.crop_res))
+        image_1 = image_1.resize((self.crop_res, self.crop_res))
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+        crop = torchvision.transforms.RandomCrop(self.crop_res)
+        flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+        image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+    
+        # if i ever wanna reverse time
+        # if torch.rand(1) > 0.5:
+        #     image_0, image_1 = image_1, image_0
+        #     prompt = caption0
+        if self.split == 'train':
+            return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+        else:
+            return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=texts))
+
+class EditITMDataset(Dataset):
+    def __init__(
+        self,
+        path: str = '../../change_descriptions/something-something',
+        split: str = "test",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        task: str = 'flickr30k_text',
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.0,
+        debug: bool = False,
+    ):
+        self.split = split
+        self.task = task
+        # if task == 'flickr_edit':
+        #     path = 'data/flickr_edit/valid.json' if split == 'val' else 'data/flickr_edit/test.json'
+        #     self.json = json.load(open(path, 'r'))
+        #     #clean json, if "pos" key is empty string, remove
+        #     self.json = [x for x in self.json if x['pos'] != '']
+        if task == 'whatsup':
+            path = 'data/whatsup/itm_test.json' if split == 'test' else 'data/whatsup/itm_valid.json'
+            self.json = json.load(open(path, 'r'))
+        elif task == 'svo':
+            path = 'data/svo/itm_test.json' if split == 'test' else 'data/svo/itm_valid.json'
+            self.json = json.load(open(path, 'r'))
+        else:
+            path = f'data/{task}/valid.json'
+            self.json = json.load(open(path, 'r'))
+            self.json = [x for x in self.json if x.get('pos', '') != '']
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+
+        if debug:
+            self.json = self.json[:50]
+
+    def __len__(self) -> int:
+        return len(self.json)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        ex = self.json[i]
+        pos = ex.get('pos', '')
+        if pos == '':
+            pos = ex['prompt']
+        neg = ex.get('neg', '')
+        if neg == '':
+            neg = ex['prompt']
+        img_path0 = ex['input']
+        texts = [pos, neg]
+        # if self.task == 'whatsup' or self.task == 'svo':
+        #     img_path0 = f"data/{self.task}/images/{ex['image']}" if self.task == 'flickr_edit' else ex['image']
+        #     texts = [ex['pos'], ex['neg']]
+        # else:
+        #     img_path0 = ex['input']
+        #     texts = ex['pos'], ex['prompt']
+        # subtasks = ex['type'] if self.task == 'flickr_edit' else ''
+        try:
+            image_0 = Image.open(img_path0).convert('RGB')
+            reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+            image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+            image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        except:
+            image_0 = 0
+
+        return dict(input=image_0, texts=texts, path=img_path0)
+
+class OldFrameEditDataset(Dataset):
+    def __init__(
+        self,
+        path: str = '../../change_descriptions/something-something',
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        task: str = 'flickr30k_text',
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.0,
+        debug: bool = False,
+    ):
+        if split == "train":
+            path = os.path.join(path, 'train.json')
+        elif split == "val":
+            path = os.path.join(path, 'validation.json')
+        self.json = json.load(open(path, 'r'))
+        np.random.shuffle(self.json)
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+
+        #clean json (if first and last are not both present, remove)
+        new_json = []
+        for i in range(len(self.json)):
+            video_id = self.json[i]['id']
+            img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+            img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+            if os.path.exists(img_path0) and os.path.exists(img_path1):
+                new_json.append(self.json[i])
+        self.json = new_json
+        if debug:
+            self.json = self.json[:50]
+
+    def __len__(self) -> int:
+        return len(self.json)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        video_id = self.json[i]['id']
+        img_path0 = f'../../change_descriptions/something-something/frames/{video_id}/first.jpg'
+        img_path1 = f'../../change_descriptions/something-something/frames/{video_id}/last.jpg'
+        prompt = self.json[i]['label']
+        image_0 = Image.open(img_path0)
+        image_1 = Image.open(img_path1)
+
+        reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+        image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+        crop = torchvision.transforms.RandomCrop(self.crop_res)
+        flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+        image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+        # if i ever wanna reverse time
+        # if torch.rand(1) > 0.5:
+        #     image_0, image_1 = image_1, image_0
+        #     prompt = caption0
+            
+        return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class EditDataset(Dataset):
+    def __init__(
+        self,
+        path: str = 'data/clip-filtered-dataset',
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.0,
+    ):
+        self.split = split
+        assert split in ("train", "val", "test")
+        assert sum(splits) == 1
+        self.path = path
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+
+        self.genhowto = open('data/genhowto/genhowto_train_clip0.7_filtered.txt', 'r').readlines()
+        # self.genhowto = open('data/genhowto/genhowto_train.txt', 'r').readlines()
+        self.genhowto = [x.strip() for x in self.genhowto]
+
+        new_genhowto = []
+        for i in range(len(self.genhowto)):
+            img_path, prompt, prompt2 = self.genhowto[i].split(':')
+            new_genhowto.append((img_path, prompt, 'action'))
+            new_genhowto.append((img_path, prompt2, 'state'))
+        self.genhowto = new_genhowto
+
+        with open(Path(self.path, "seeds.json")) as f:
+            self.seeds = json.load(f)
+
+        split_0, split_1 = {
+            "train": (0.0, splits[0]),
+            "val": (splits[0], splits[0] + splits[1]),
+            "test": (splits[0] + splits[1], 1.0),
+        }[split]
+
+        idx_0 = math.floor(split_0 * len(self.seeds))
+        idx_1 = math.floor(split_1 * len(self.seeds))
+        self.seeds = self.seeds[idx_0:idx_1]
+        # shuffle seeds and genhowto
+        # np.random.seed(42)
+        # np.random.shuffle(self.seeds)
+        # np.random.shuffle(self.genhowto)
+
+    def __len__(self) -> int:
+        return len(self.seeds) + len(self.genhowto)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        if i < len(self.seeds):
+            name, seeds = self.seeds[i]
+            propt_dir = Path(self.path, name)
+            seed = seeds[torch.randint(0, len(seeds), ()).item()]
+            with open(propt_dir.joinpath("prompt.json")) as fp:
+                prompt = json.load(fp)["edit"]
+            image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
+            image_1 = Image.open(propt_dir.joinpath(f"{seed}_1.jpg"))
+        else:
+            ex = self.genhowto[i - len(self.seeds)]
+            # img_path, prompt, prompt2 = ex.split(':')
+            # img_path = img_path.replace('changeit_detected_without_test', 'changeit_detected')
+            # img_path = 'data/genhowto/' + img_path
+            # full_img = Image.open(img_path).convert('RGB')
+            # image_0 = full_img.crop((0, 0, full_img.width // 3, full_img.height))
+            # image_1 = full_img.crop((full_img.width * 2 // 3, 0, full_img.width, full_img.height))
+            # image_2 = full_img.crop((full_img.width // 3, 0, full_img.width * 2 // 3, full_img.height))
+            # if torch.rand(1) > 0.5:
+            #     image_1 = image_2
+            #     prompt = prompt2
+            img_path, prompt, type = ex
+            img_path = img_path.replace('changeit_detected_without_test', 'changeit_detected')
+            img_path = 'data/genhowto/' + img_path
+            full_img = Image.open(img_path).convert('RGB')
+            image_0 = full_img.crop((0, 0, full_img.width // 3, full_img.height))
+            if type == 'action':
+                image_1 = full_img.crop((full_img.width // 3, 0, full_img.width * 2 // 3, full_img.height))
+            else:
+                image_1 = full_img.crop((full_img.width * 2 // 3, 0, full_img.width, full_img.height))
+            
+
+        reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+        image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+        crop = torchvision.transforms.RandomCrop(self.crop_res)
+        flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+        image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+        return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class GenHowToDataset(Dataset):
+    def __init__(
+        self,
+        path: str = 'data/clip-filtered-dataset',
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        min_resize_res: int = 256,
+        max_resize_res: int = 256,
+        crop_res: int = 256,
+        flip_prob: float = 0.0,
+    ):
+        self.split = split
+        assert split in ("train", "val", "test")
+        assert sum(splits) == 1
+        self.path = path
+        self.min_resize_res = min_resize_res
+        self.max_resize_res = max_resize_res
+        self.crop_res = crop_res
+        self.flip_prob = flip_prob
+
+        self.genhowto = open('data/genhowto/genhowto_train.txt', 'r').readlines()
+        self.genhowto = [x.strip() for x in self.genhowto]
+
+        new_genhowto = []
+        for i in range(len(self.genhowto)):
+            img_path, prompt, prompt2 = self.genhowto[i].split(':')
+            new_genhowto.append((img_path, prompt, 'action'))
+            new_genhowto.append((img_path, prompt2, 'state'))
+        self.genhowto = new_genhowto
+        np.random.shuffle(self.genhowto)
+
+        # with open(Path(self.path, "seeds.json")) as f:
+        #     self.seeds = json.load(f)
+
+        # split_0, split_1 = {
+        #     "train": (0.0, splits[0]),
+        #     "val": (splits[0], splits[0] + splits[1]),
+        #     "test": (splits[0] + splits[1], 1.0),
+        # }[split]
+
+        # idx_0 = math.floor(split_0 * len(self.seeds))
+        # idx_1 = math.floor(split_1 * len(self.seeds))
+        # self.seeds = self.seeds[idx_0:idx_1]
+        # shuffle seeds and genhowto
+        # np.random.seed(42)
+        # np.random.shuffle(self.seeds)
+        # np.random.shuffle(self.genhowto)
+
+    def __len__(self) -> int:
+        return len(self.genhowto)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        ex = self.genhowto[i]
+        img_path, prompt, type = ex
+        img_path = img_path.replace('changeit_detected_without_test', 'changeit_detected')
+        img_path = 'data/genhowto/' + img_path
+        full_img = Image.open(img_path).convert('RGB')
+        image_0 = full_img.crop((0, 0, full_img.width // 3, full_img.height))
+        if type == 'action':
+            image_1 = full_img.crop((full_img.width // 3, 0, full_img.width * 2 // 3, full_img.height))
+        else:
+            image_1 = full_img.crop((full_img.width * 2 // 3, 0, full_img.width, full_img.height))
+        
+
+        reize_res = torch.randint(self.min_resize_res, self.max_resize_res + 1, ()).item()
+        image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+        image_1 = image_1.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+        image_1 = rearrange(2 * torch.tensor(np.array(image_1)).float() / 255 - 1, "h w c -> c h w")
+
+        crop = torchvision.transforms.RandomCrop(self.crop_res)
+        flip = torchvision.transforms.RandomHorizontalFlip(float(self.flip_prob))
+        image_0, image_1 = flip(crop(torch.cat((image_0, image_1)))).chunk(2)
+
+        return dict(edited=image_1, edit=dict(c_concat=image_0, c_crossattn=prompt))
+
+
+class EditDatasetEval(Dataset):
+    def __init__(
+        self,
+        path: str,
+        split: str = "train",
+        splits: tuple[float, float, float] = (0.9, 0.05, 0.05),
+        res: int = 256,
+    ):
+        assert split in ("train", "val", "test")
+        assert sum(splits) == 1
+        self.path = path
+        self.res = res
+
+        with open(Path(self.path, "seeds.json")) as f:
+            self.seeds = json.load(f)
+
+        split_0, split_1 = {
+            "train": (0.0, splits[0]),
+            "val": (splits[0], splits[0] + splits[1]),
+            "test": (splits[0] + splits[1], 1.0),
+        }[split]
+
+        idx_0 = math.floor(split_0 * len(self.seeds))
+        idx_1 = math.floor(split_1 * len(self.seeds))
+        self.seeds = self.seeds[idx_0:idx_1]
+
+    def __len__(self) -> int:
+        return len(self.seeds)
+
+    def __getitem__(self, i: int) -> dict[str, Any]:
+        name, seeds = self.seeds[i]
+        propt_dir = Path(self.path, name)
+        seed = seeds[torch.randint(0, len(seeds), ()).item()]
+        with open(propt_dir.joinpath("prompt.json")) as fp:
+            prompt = json.load(fp)
+            edit = prompt["edit"]
+            input_prompt = prompt["input"]
+            output_prompt = prompt["output"]
+
+        image_0 = Image.open(propt_dir.joinpath(f"{seed}_0.jpg"))
+
+        reize_res = torch.randint(self.res, self.res + 1, ()).item()
+        image_0 = image_0.resize((reize_res, reize_res), Image.Resampling.LANCZOS)
+
+        image_0 = rearrange(2 * torch.tensor(np.array(image_0)).float() / 255 - 1, "h w c -> c h w")
+
+        return dict(image_0=image_0, input_prompt=input_prompt, edit=edit, output_prompt=output_prompt)

eq-kubric/3d_data/GSO_dict_all.json

@@ -0,0 +1,1035 @@
+{
+    "11pro_SL_TRX_FG": "11pro_SL_TRX_FG",
+    "2_of_Jenga_Classic_Game": "2_of_Jenga_Classic_Game",
+    "30_CONSTRUCTION_SET": "30_CONSTRUCTION_SET",
+    "3D_Dollhouse_Happy_Brother": "3D_Dollhouse_Happy_Brother",
+    "3D_Dollhouse_Lamp": "3D_Dollhouse_Lamp",
+    "3D_Dollhouse_Refrigerator": "green doll house wooden refrigerator",
+    "3D_Dollhouse_Sink": "3D_Dollhouse_Sink",
+    "3D_Dollhouse_Sofa": "purple doll house wooden sofa",
+    "3D_Dollhouse_Swing": "3D_Dollhouse_Swing",
+    "3D_Dollhouse_TablePurple": "3D_Dollhouse_TablePurple",
+    "3M_Antislip_Surfacing_Light_Duty_White": "3M_Antislip_Surfacing_Light_Duty_White",
+    "3M_Vinyl_Tape_Green_1_x_36_yd": "3M_Vinyl_Tape_Green_1_x_36_yd",
+    "45oz_RAMEKIN_ASST_DEEP_COLORS": "45oz_RAMEKIN_ASST_DEEP_COLORS",
+    "50_BLOCKS": "50_BLOCKS",
+    "5_HTP": "5_HTP",
+    "60_CONSTRUCTION_SET": "60_CONSTRUCTION_SET",
+    "ACE_Coffee_Mug_Kristen_16_oz_cup": "red coffee mug",
+    "ALPHABET_AZ_GRADIENT": "ALPHABET_AZ_GRADIENT",
+    "ALPHABET_AZ_GRADIENT_WQb1ufEycSj": "ALPHABET_AZ_GRADIENT_WQb1ufEycSj",
+    "AMBERLIGHT_UP_W": "AMBERLIGHT_UP_W",
+    "ASICS_GEL1140V_WhiteBlackSilver": "ASICS_GEL1140V_WhiteBlackSilver",
+    "ASICS_GEL1140V_WhiteRoyalSilver": "ASICS_GEL1140V_WhiteRoyalSilver",
+    "ASICS_GELAce_Pro_Pearl_WhitePink": "ASICS_GELAce_Pro_Pearl_WhitePink",
+    "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange": "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange",
+    "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver": "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver",
+    "ASICS_GELChallenger_9_Royal_BlueWhiteBlack": "ASICS_GELChallenger_9_Royal_BlueWhiteBlack",
+    "ASICS_GELDirt_Dog_4_SunFlameBlack": "ASICS_GELDirt_Dog_4_SunFlameBlack",
+    "ASICS_GELLinksmaster_WhiteCoffeeSand": "ASICS_GELLinksmaster_WhiteCoffeeSand",
+    "ASICS_GELLinksmaster_WhiteRasberryGunmetal": "ASICS_GELLinksmaster_WhiteRasberryGunmetal",
+    "ASICS_GELLinksmaster_WhiteSilverCarolina_Blue": "ASICS_GELLinksmaster_WhiteSilverCarolina_Blue",
+    "ASICS_GELResolution_5_Flash_YellowBlackSilver": "ASICS_GELResolution_5_Flash_YellowBlackSilver",
+    "ASICS_GELTour_Lyte_WhiteOrchidSilver": "ASICS_GELTour_Lyte_WhiteOrchidSilver",
+    "ASICS_HyperRocketgirl_SP_5_WhiteMalibu_BlueBlack": "ASICS_HyperRocketgirl_SP_5_WhiteMalibu_BlueBlack",
+    "ASSORTED_VEGETABLE_SET": "ASSORTED_VEGETABLE_SET",
+    "Adrenaline_GTS_13_Color_DrkDenimWhtBachlorBttnSlvr_Size_50_yfK40TNjq0V": "Adrenaline_GTS_13_Color_DrkDenimWhtBachlorBttnSlvr_Size_50_yfK40TNjq0V",
+    "Adrenaline_GTS_13_Color_WhtObsdianBlckOlmpcSlvr_Size_70": "Adrenaline_GTS_13_Color_WhtObsdianBlckOlmpcSlvr_Size_70",
+    "Air_Hogs_Wind_Flyers_Set_Airplane_Red": "Air_Hogs_Wind_Flyers_Set_Airplane_Red",
+    "AllergenFree_JarroDophilus": "AllergenFree_JarroDophilus",
+    "Android_Figure_Chrome": "Android_Figure_Chrome",
+    "Android_Figure_Orange": "Android_Figure_Orange",
+    "Android_Figure_Panda": "Android_Figure_Panda",
+    "Android_Lego": "Android_Lego",
+    "Animal_Crossing_New_Leaf_Nintendo_3DS_Game": "Animal_Crossing_New_Leaf_Nintendo_3DS_Game",
+    "Animal_Planet_Foam_2Headed_Dragon": "Animal_Planet_Foam_2Headed_Dragon",
+    "Apples_to_Apples_Kids_Edition": "Apples_to_Apples_Kids_Edition",
+    "Arm_Hammer_Diaper_Pail_Refills_12_Pack_MFWkmoweejt": "Arm_Hammer_Diaper_Pail_Refills_12_Pack_MFWkmoweejt",
+    "Aroma_Stainless_Steel_Milk_Frother_2_Cup": "stainless steel milk frother",
+    "Asus_80211ac_DualBand_Gigabit_Wireless_Router_RTAC68R": "Asus_80211ac_DualBand_Gigabit_Wireless_Router_RTAC68R",
+    "Asus_M5A78LMUSB3_Motherboard_Micro_ATX_Socket_AM3": "Asus_M5A78LMUSB3_Motherboard_Micro_ATX_Socket_AM3",
+    "Asus_M5A99FX_PRO_R20_Motherboard_ATX_Socket_AM3": "Asus_M5A99FX_PRO_R20_Motherboard_ATX_Socket_AM3",
+    "Asus_Sabertooth_990FX_20_Motherboard_ATX_Socket_AM3": "Asus_Sabertooth_990FX_20_Motherboard_ATX_Socket_AM3",
+    "Asus_Sabertooth_Z97_MARK_1_Motherboard_ATX_LGA1150_Socket": "Asus_Sabertooth_Z97_MARK_1_Motherboard_ATX_LGA1150_Socket",
+    "Asus_X99Deluxe_Motherboard_ATX_LGA2011v3_Socket": "Asus_X99Deluxe_Motherboard_ATX_LGA2011v3_Socket",
+    "Asus_Z87PRO_Motherboard_ATX_LGA1150_Socket": "Asus_Z87PRO_Motherboard_ATX_LGA1150_Socket",
+    "Asus_Z97AR_LGA_1150_Intel_ATX_Motherboard": "Asus_Z97AR_LGA_1150_Intel_ATX_Motherboard",
+    "Asus_Z97IPLUS_Motherboard_Mini_ITX_LGA1150_Socket": "Asus_Z97IPLUS_Motherboard_Mini_ITX_LGA1150_Socket",
+    "Avengers_Gamma_Green_Smash_Fists": "Avengers_Gamma_Green_Smash_Fists",
+    "Avengers_Thor_PLlrpYniaeB": "Avengers_Thor_PLlrpYniaeB",
+    "Azure_Snake_Tieks_Leather_Snake_Print_Ballet_Flats": "Azure_Snake_Tieks_Leather_Snake_Print_Ballet_Flats",
+    "BABY_CAR": "BABY_CAR",
+    "BAGEL_WITH_CHEESE": "BAGEL_WITH_CHEESE",
+    "BAKING_UTENSILS": "BAKING_UTENSILS",
+    "BALANCING_CACTUS": "BALANCING_CACTUS",
+    "BATHROOM_CLASSIC": "BATHROOM_CLASSIC",
+    "BATHROOM_FURNITURE_SET_1": "BATHROOM_FURNITURE_SET_1",
+    "BEDROOM_CLASSIC": "BEDROOM_CLASSIC",
+    "BEDROOM_CLASSIC_Gi22DjScTVS": "BEDROOM_CLASSIC_Gi22DjScTVS",
+    "BEDROOM_NEO": "BEDROOM_NEO",
+    "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028": "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028",
+    "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup": "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup",
+    "BIRD_RATTLE": "BIRD_RATTLE",
+    "BRAILLE_ALPHABET_AZ": "BRAILLE_ALPHABET_AZ",
+    "BREAKFAST_MENU": "BREAKFAST_MENU",
+    "BUILD_A_ROBOT": "BUILD_A_ROBOT",
+    "BUILD_A_ZOO": "BUILD_A_ZOO",
+    "BUNNY_RACER": "BUNNY_RACER",
+    "BUNNY_RATTLE": "BUNNY_RATTLE",
+    "Baby_Elements_Stacking_Cups": "Baby_Elements_Stacking_Cups",
+    "Balderdash_Game": "Balderdash_Game",
+    "Beetle_Adventure_Racing_Nintendo_64": "Beetle_Adventure_Racing_Nintendo_64",
+    "Beta_Glucan": "Beta_Glucan",
+    "Beyonc_Life_is_But_a_Dream_DVD": "Beyonc_Life_is_But_a_Dream_DVD",
+    "Bifidus_Balance_FOS": "Bifidus_Balance_FOS",
+    "Big_Dot_Aqua_Pencil_Case": "Big_Dot_Aqua_Pencil_Case",
+    "Big_Dot_Pink_Pencil_Case": "Big_Dot_Pink_Pencil_Case",
+    "Big_O_Sponges_Assorted_Cellulose_12_pack": "Big_O_Sponges_Assorted_Cellulose_12_pack",
+    "BlackBlack_Nintendo_3DSXL": "BlackBlack_Nintendo_3DSXL",
+    "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker": "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker",
+    "Black_Decker_Stainless_Steel_Toaster_4_Slice": "stainless steel toaster",
+    "Black_Elderberry_Syrup_54_oz_Gaia_Herbs": "Black_Elderberry_Syrup_54_oz_Gaia_Herbs",
+    "Black_Forest_Fruit_Snacks_28_Pack_Grape": "Black_Forest_Fruit_Snacks_28_Pack_Grape",
+    "Black_Forest_Fruit_Snacks_Juicy_Filled_Centers_10_pouches_9_oz_total": "Black_Forest_Fruit_Snacks_Juicy_Filled_Centers_10_pouches_9_oz_total",
+    "Black_and_Decker_PBJ2000_FusionBlade_Blender_Jars": "Black_and_Decker_PBJ2000_FusionBlade_Blender_Jars",
+    "Black_and_Decker_TR3500SD_2Slice_Toaster": "Black_and_Decker_TR3500SD_2Slice_Toaster",
+    "Blackcurrant_Lutein": "Blackcurrant_Lutein",
+    "BlueBlack_Nintendo_3DSXL": "BlueBlack_Nintendo_3DSXL",
+    "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD": "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD",
+    "Borage_GLA240Gamma_Tocopherol": "Borage_GLA240Gamma_Tocopherol",
+    "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl": "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl",
+    "Breyer_Horse_Of_The_Year_2015": "Breyer_Horse_Of_The_Year_2015",
+    "Brisk_Iced_Tea_Lemon_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Brisk_Iced_Tea_Lemon_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+    "Brother_Ink_Cartridge_Magenta_LC75M": "Brother_Ink_Cartridge_Magenta_LC75M",
+    "Brother_LC_1053PKS_Ink_Cartridge_CyanMagentaYellow_1pack": "Brother_LC_1053PKS_Ink_Cartridge_CyanMagentaYellow_1pack",
+    "Brother_Printing_Cartridge_PC501": "Brother_Printing_Cartridge_PC501",
+    "CARSII": "CARSII",
+    "CAR_CARRIER_TRAIN": "CAR_CARRIER_TRAIN",
+    "CASTLE_BLOCKS": "CASTLE_BLOCKS",
+    "CHICKEN_NESTING": "CHICKEN_NESTING",
+    "CHICKEN_RACER": "CHICKEN_RACER",
+    "CHILDRENS_ROOM_NEO": "CHILDRENS_ROOM_NEO",
+    "CHILDREN_BEDROOM_CLASSIC": "CHILDREN_BEDROOM_CLASSIC",
+    "CITY_TAXI_POLICE_CAR": "CITY_TAXI_POLICE_CAR",
+    "CLIMACOOL_BOAT_BREEZE_IE6CyqSaDwN": "CLIMACOOL_BOAT_BREEZE_IE6CyqSaDwN",
+    "COAST_GUARD_BOAT": "COAST_GUARD_BOAT",
+    "CONE_SORTING": "CONE_SORTING",
+    "CONE_SORTING_kg5fbARBwts": "CONE_SORTING_kg5fbARBwts",
+    "CREATIVE_BLOCKS_35_MM": "CREATIVE_BLOCKS_35_MM",
+    "California_Navy_Tieks_Italian_Leather_Ballet_Flats": "California_Navy_Tieks_Italian_Leather_Ballet_Flats",
+    "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black": "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black",
+    "Canon_225226_Ink_Cartridges_BlackColor_Cyan_Magenta_Yellow_6_count": "Canon_225226_Ink_Cartridges_BlackColor_Cyan_Magenta_Yellow_6_count",
+    "Canon_Ink_Cartridge_Green_6": "Canon_Ink_Cartridge_Green_6",
+    "Canon_Pixma_Chromalife_100_Magenta_8": "Canon_Pixma_Chromalife_100_Magenta_8",
+    "Canon_Pixma_Ink_Cartridge_251_M": "Canon_Pixma_Ink_Cartridge_251_M",
+    "Canon_Pixma_Ink_Cartridge_8": "Canon_Pixma_Ink_Cartridge_8",
+    "Canon_Pixma_Ink_Cartridge_8_Green": "Canon_Pixma_Ink_Cartridge_8_Green",
+    "Canon_Pixma_Ink_Cartridge_8_Red": "Canon_Pixma_Ink_Cartridge_8_Red",
+    "Canon_Pixma_Ink_Cartridge_Cyan_251": "Canon_Pixma_Ink_Cartridge_Cyan_251",
+    "Cascadia_8_Color_AquariusHibscsBearingSeaBlk_Size_50": "Cascadia_8_Color_AquariusHibscsBearingSeaBlk_Size_50",
+    "Central_Garden_Flower_Pot_Goo_425": "Central_Garden_Flower_Pot_Goo_425",
+    "Chef_Style_Round_Cake_Pan_9_inch_pan": "Chef_Style_Round_Cake_Pan_9_inch_pan",
+    "Chefmate_8_Frypan": "black frypan",
+    "Chelsea_BlkHeelPMP_DwxLtZNxLZZ": "Chelsea_BlkHeelPMP_DwxLtZNxLZZ",
+    "Chelsea_lo_fl_rdheel_nQ0LPNF1oMw": "red high heel",
+    "Chelsea_lo_fl_rdheel_zAQrnhlEfw8": "Chelsea_lo_fl_rdheel_zAQrnhlEfw8",
+    "Circo_Fish_Toothbrush_Holder_14995988": "Circo_Fish_Toothbrush_Holder_14995988",
+    "ClimaCool_Aerate_2_W_Wide": "ClimaCool_Aerate_2_W_Wide",
+    "Clorox_Premium_Choice_Gloves_SM_1_pair": "Clorox_Premium_Choice_Gloves_SM_1_pair",
+    "Closetmaid_Premium_Fabric_Cube_Red": "Closetmaid_Premium_Fabric_Cube_Red",
+    "Clue_Board_Game_Classic_Edition": "Clue_Board_Game_Classic_Edition",
+    "CoQ10": "white drug bottle",
+    "CoQ10_BjTLbuRVt1t": "CoQ10_BjTLbuRVt1t",
+    "CoQ10_wSSVoxVppVD": "CoQ10_wSSVoxVppVD",
+    "Cole_Hardware_Antislip_Surfacing_Material_White": "Cole_Hardware_Antislip_Surfacing_Material_White",
+    "Cole_Hardware_Antislip_Surfacing_White_2_x_60": "Cole_Hardware_Antislip_Surfacing_White_2_x_60",
+    "Cole_Hardware_Bowl_Scirocco_YellowBlue": "Cole_Hardware_Bowl_Scirocco_YellowBlue",
+    "Cole_Hardware_Butter_Dish_Square_Red": "Cole_Hardware_Butter_Dish_Square_Red",
+    "Cole_Hardware_Deep_Bowl_Good_Earth_1075": "Cole_Hardware_Deep_Bowl_Good_Earth_1075",
+    "Cole_Hardware_Dishtowel_Blue": "Cole_Hardware_Dishtowel_Blue",
+    "Cole_Hardware_Dishtowel_BlueWhite": "Cole_Hardware_Dishtowel_BlueWhite",
+    "Cole_Hardware_Dishtowel_Multicolors": "Cole_Hardware_Dishtowel_Multicolors",
+    "Cole_Hardware_Dishtowel_Red": "Cole_Hardware_Dishtowel_Red",
+    "Cole_Hardware_Dishtowel_Stripe": "Cole_Hardware_Dishtowel_Stripe",
+    "Cole_Hardware_Electric_Pot_Assortment_55": "Cole_Hardware_Electric_Pot_Assortment_55",
+    "Cole_Hardware_Electric_Pot_Cabana_55": "Cole_Hardware_Electric_Pot_Cabana_55",
+    "Cole_Hardware_Flower_Pot_1025": "Cole_Hardware_Flower_Pot_1025",
+    "Cole_Hardware_Hammer_Black": "black and yellow hammer",
+    "Cole_Hardware_Mini_Honey_Dipper": "Cole_Hardware_Mini_Honey_Dipper",
+    "Cole_Hardware_Mug_Classic_Blue": "Cole_Hardware_Mug_Classic_Blue",
+    "Cole_Hardware_Orchid_Pot_85": "Cole_Hardware_Orchid_Pot_85",
+    "Cole_Hardware_Plant_Saucer_Brown_125": "Cole_Hardware_Plant_Saucer_Brown_125",
+    "Cole_Hardware_Plant_Saucer_Glazed_9": "Cole_Hardware_Plant_Saucer_Glazed_9",
+    "Cole_Hardware_Saucer_Electric": "Cole_Hardware_Saucer_Electric",
+    "Cole_Hardware_Saucer_Glazed_6": "Cole_Hardware_Saucer_Glazed_6",
+    "Cole_Hardware_School_Bell_Solid_Brass_38": "Cole_Hardware_School_Bell_Solid_Brass_38",
+    "Colton_Wntr_Chukka_y4jO0I8JQFW": "Colton_Wntr_Chukka_y4jO0I8JQFW",
+    "Connect_4_Launchers": "Connect_4_Launchers",
+    "Cootie_Game": "Cootie_Game",
+    "Cootie_Game_tDhURNbfU5J": "Cootie_Game_tDhURNbfU5J",
+    "Copperhead_Snake_Tieks_Brown_Snake_Print_Ballet_Flats": "Copperhead_Snake_Tieks_Brown_Snake_Print_Ballet_Flats",
+    "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue": "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue",
+    "Court_Attitude": "Court_Attitude",
+    "Craftsman_Grip_Screwdriver_Phillips_Cushion": "Craftsman_Grip_Screwdriver_Phillips_Cushion",
+    "Crayola_Bonus_64_Crayons": "Crayola_Bonus_64_Crayons",
+    "Crayola_Crayons_120_crayons": "Crayola_Crayons_120_crayons",
+    "Crayola_Crayons_24_count": "Crayola_Crayons_24_count",
+    "Crayola_Crayons_Washable_24_crayons": "Crayola_Crayons_Washable_24_crayons",
+    "Crayola_Model_Magic_Modeling_Material_Single_Packs_6_pack_05_oz_packs": "Crayola_Model_Magic_Modeling_Material_Single_Packs_6_pack_05_oz_packs",
+    "Crayola_Model_Magic_Modeling_Material_White_3_oz": "Crayola_Model_Magic_Modeling_Material_White_3_oz",
+    "Crayola_Washable_Fingerpaint_Red_Blue_Yellow_3_count_8_fl_oz_bottes_each": "Crayola_Washable_Fingerpaint_Red_Blue_Yellow_3_count_8_fl_oz_bottes_each",
+    "Crayola_Washable_Sidewalk_Chalk_16_pack": "Crayola_Washable_Sidewalk_Chalk_16_pack",
+    "Crayola_Washable_Sidewalk_Chalk_16_pack_wDZECiw7J6s": "Crayola_Washable_Sidewalk_Chalk_16_pack_wDZECiw7J6s",
+    "Crazy_8": "Crazy_8",
+    "Crazy_Shadow_2": "Crazy_Shadow_2",
+    "Crazy_Shadow_2_oW4Jd10HFFr": "Crazy_Shadow_2_oW4Jd10HFFr",
+    "Cream_Tieks_Italian_Leather_Ballet_Flats": "Cream_Tieks_Italian_Leather_Ballet_Flats",
+    "Creatine_Monohydrate": "Creatine_Monohydrate",
+    "Crosley_Alarm_Clock_Vintage_Metal": "vintage metal alarm clock",
+    "Crunch_Girl_Scouts_Candy_Bars_Peanut_Butter_Creme_78_oz_box": "Crunch_Girl_Scouts_Candy_Bars_Peanut_Butter_Creme_78_oz_box",
+    "Curver_Storage_Bin_Black_Small": "Curver_Storage_Bin_Black_Small",
+    "DANCING_ALLIGATOR": "DANCING_ALLIGATOR",
+    "DANCING_ALLIGATOR_zoWBjc0jbTs": "DANCING_ALLIGATOR_zoWBjc0jbTs",
+    "DIM_CDG": "DIM_CDG",
+    "DINING_ROOM_CLASSIC": "DINING_ROOM_CLASSIC",
+    "DINING_ROOM_CLASSIC_UJuxQ0hv5XU": "DINING_ROOM_CLASSIC_UJuxQ0hv5XU",
+    "DINNING_ROOM_FURNITURE_SET_1": "DINNING_ROOM_FURNITURE_SET_1",
+    "DOLL_FAMILY": "DOLL_FAMILY",
+    "DPC_Handmade_Hat_Brown": "DPC_Handmade_Hat_Brown",
+    "DPC_Thinsulate_Isolate_Gloves_Brown": "DPC_Thinsulate_Isolate_Gloves_Brown",
+    "DPC_tropical_Trends_Hat": "DPC_tropical_Trends_Hat",
+    "DRAGON_W": "DRAGON_W",
+    "D_ROSE_45": "D_ROSE_45",
+    "D_ROSE_773_II_Kqclsph05pE": "D_ROSE_773_II_Kqclsph05pE",
+    "D_ROSE_773_II_hvInJwJ5HUD": "D_ROSE_773_II_hvInJwJ5HUD",
+    "D_ROSE_ENGLEWOOD_II": "D_ROSE_ENGLEWOOD_II",
+    "Dell_Ink_Cartridge": "Dell_Ink_Cartridge",
+    "Dell_Ink_Cartridge_Yellow_31": "Dell_Ink_Cartridge_Yellow_31",
+    "Dell_Series_9_Color_Ink_Cartridge_MK993_High_Yield": "Dell_Series_9_Color_Ink_Cartridge_MK993_High_Yield",
+    "Design_Ideas_Drawer_Store_Organizer": "Design_Ideas_Drawer_Store_Organizer",
+    "Deskstar_Desk_Top_Hard_Drive_1_TB": "Deskstar_Desk_Top_Hard_Drive_1_TB",
+    "Diamond_Visions_Scissors_Red": "red scissors",
+    "Diet_Pepsi_Soda_Cola12_Pack_12_oz_Cans": "Diet_Pepsi_Soda_Cola12_Pack_12_oz_Cans",
+    "Digital_Camo_Double_Decker_Lunch_Bag": "Digital_Camo_Double_Decker_Lunch_Bag",
+    "Dino_3": "Dino_3",
+    "Dino_4": "Dino_4",
+    "Dino_5": "Dino_5",
+    "Dixie_10_ounce_Bowls_35_ct": "Dixie_10_ounce_Bowls_35_ct",
+    "Dog": "Dog",
+    "Don_Franciscos_Gourmet_Coffee_Medium_Decaf_100_Colombian_12_oz_340_g": "Don_Franciscos_Gourmet_Coffee_Medium_Decaf_100_Colombian_12_oz_340_g",
+    "Down_To_Earth_Ceramic_Orchid_Pot_Asst_Blue": "Down_To_Earth_Ceramic_Orchid_Pot_Asst_Blue",
+    "Down_To_Earth_Orchid_Pot_Ceramic_Lime": "Down_To_Earth_Orchid_Pot_Ceramic_Lime",
+    "Down_To_Earth_Orchid_Pot_Ceramic_Red": "Down_To_Earth_Orchid_Pot_Ceramic_Red",
+    "ENFR_MID_ENFORCER": "ENFR_MID_ENFORCER",
+    "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book": "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book",
+    "Ecoforms_Cup_B4_SAN": "Ecoforms_Cup_B4_SAN",
+    "Ecoforms_Garden_Pot_GP16ATurquois": "Ecoforms_Garden_Pot_GP16ATurquois",
+    "Ecoforms_Plant_Bowl_Atlas_Low": "Ecoforms_Plant_Bowl_Atlas_Low",
+    "Ecoforms_Plant_Bowl_Turquoise_7": "Ecoforms_Plant_Bowl_Turquoise_7",
+    "Ecoforms_Plant_Container_12_Pot_Nova": "Ecoforms_Plant_Container_12_Pot_Nova",
+    "Ecoforms_Plant_Container_B4_Har": "Ecoforms_Plant_Container_B4_Har",
+    "Ecoforms_Plant_Container_FB6_Tur": "Ecoforms_Plant_Container_FB6_Tur",
+    "Ecoforms_Plant_Container_GP16AMOCHA": "Ecoforms_Plant_Container_GP16AMOCHA",
+    "Ecoforms_Plant_Container_GP16A_Coral": "Ecoforms_Plant_Container_GP16A_Coral",
+    "Ecoforms_Plant_Container_QP6CORAL": "Ecoforms_Plant_Container_QP6CORAL",
+    "Ecoforms_Plant_Container_QP6HARVEST": "Ecoforms_Plant_Container_QP6HARVEST",
+    "Ecoforms_Plant_Container_QP_Harvest": "Ecoforms_Plant_Container_QP_Harvest",
+    "Ecoforms_Plant_Container_QP_Turquoise": "Ecoforms_Plant_Container_QP_Turquoise",
+    "Ecoforms_Plant_Container_Quadra_Sand_QP6": "Ecoforms_Plant_Container_Quadra_Sand_QP6",
+    "Ecoforms_Plant_Container_Quadra_Turquoise_QP12": "Ecoforms_Plant_Container_Quadra_Turquoise_QP12",
+    "Ecoforms_Plant_Container_S14Turquoise": "Ecoforms_Plant_Container_S14Turquoise",
+    "Ecoforms_Plant_Container_S24NATURAL": "Ecoforms_Plant_Container_S24NATURAL",
+    "Ecoforms_Plant_Container_S24Turquoise": "Ecoforms_Plant_Container_S24Turquoise",
+    "Ecoforms_Plant_Container_SB9Turquoise": "Ecoforms_Plant_Container_SB9Turquoise",
+    "Ecoforms_Plant_Container_URN_NAT": "Ecoforms_Plant_Container_URN_NAT",
+    "Ecoforms_Plant_Container_URN_SAN": "Ecoforms_Plant_Container_URN_SAN",
+    "Ecoforms_Plant_Container_Urn_55_Avocado": "Ecoforms_Plant_Container_Urn_55_Avocado",
+    "Ecoforms_Plant_Container_Urn_55_Mocha": "Ecoforms_Plant_Container_Urn_55_Mocha",
+    "Ecoforms_Plant_Plate_S11Turquoise": "Ecoforms_Plant_Plate_S11Turquoise",
+    "Ecoforms_Plant_Pot_GP9AAvocado": "Ecoforms_Plant_Pot_GP9AAvocado",
+    "Ecoforms_Plant_Pot_GP9_SAND": "Ecoforms_Plant_Pot_GP9_SAND",
+    "Ecoforms_Plant_Saucer_S14MOCHA": "Ecoforms_Plant_Saucer_S14MOCHA",
+    "Ecoforms_Plant_Saucer_S14NATURAL": "Ecoforms_Plant_Saucer_S14NATURAL",
+    "Ecoforms_Plant_Saucer_S17MOCHA": "Ecoforms_Plant_Saucer_S17MOCHA",
+    "Ecoforms_Plant_Saucer_S20MOCHA": "Ecoforms_Plant_Saucer_S20MOCHA",
+    "Ecoforms_Plant_Saucer_SQ1HARVEST": "Ecoforms_Plant_Saucer_SQ1HARVEST",
+    "Ecoforms_Plant_Saucer_SQ8COR": "Ecoforms_Plant_Saucer_SQ8COR",
+    "Ecoforms_Planter_Bowl_Cole_Hardware": "Ecoforms_Planter_Bowl_Cole_Hardware",
+    "Ecoforms_Planter_Pot_GP12AAvocado": "Ecoforms_Planter_Pot_GP12AAvocado",
+    "Ecoforms_Planter_Pot_QP6Ebony": "Ecoforms_Planter_Pot_QP6Ebony",
+    "Ecoforms_Plate_S20Avocado": "Ecoforms_Plate_S20Avocado",
+    "Ecoforms_Pot_Nova_6_Turquoise": "Ecoforms_Pot_Nova_6_Turquoise",
+    "Ecoforms_Quadra_Saucer_SQ1_Avocado": "Ecoforms_Quadra_Saucer_SQ1_Avocado",
+    "Ecoforms_Saucer_SQ3_Turquoise": "Ecoforms_Saucer_SQ3_Turquoise",
+    "Elephant": "Elephant",
+    "Embark_Lunch_Cooler_Blue": "Embark_Lunch_Cooler_Blue",
+    "Envision_Home_Dish_Drying_Mat_Red_6_x_18": "Envision_Home_Dish_Drying_Mat_Red_6_x_18",
+    "Epson_273XL_Ink_Cartridge_Magenta": "Epson_273XL_Ink_Cartridge_Magenta",
+    "Epson_DURABrite_Ultra_786_Black_Ink_Cartridge_T786120S": "Epson_DURABrite_Ultra_786_Black_Ink_Cartridge_T786120S",
+    "Epson_Ink_Cartridge_126_Yellow": "Epson_Ink_Cartridge_126_Yellow",
+    "Epson_Ink_Cartridge_Black_200": "Epson_Ink_Cartridge_Black_200",
+    "Epson_LabelWorks_LC4WBN9_Tape_reel_labels_047_x_295_Roll_Black_on_White": "Epson_LabelWorks_LC4WBN9_Tape_reel_labels_047_x_295_Roll_Black_on_White",
+    "Epson_LabelWorks_LC5WBN9_Tape_reel_labels_071_x_295_Roll_Black_on_White": "Epson_LabelWorks_LC5WBN9_Tape_reel_labels_071_x_295_Roll_Black_on_White",
+    "Epson_T5803_Ink_Cartridge_Magenta_1pack": "Epson_T5803_Ink_Cartridge_Magenta_1pack",
+    "Epson_UltraChrome_T0543_Ink_Cartridge_Magenta_1pack": "Epson_UltraChrome_T0543_Ink_Cartridge_Magenta_1pack",
+    "Epson_UltraChrome_T0548_Ink_Cartridge_Matte_Black_1pack": "Epson_UltraChrome_T0548_Ink_Cartridge_Matte_Black_1pack",
+    "F10_TRX_FG_ssscuo9tGxb": "F10_TRX_FG_ssscuo9tGxb",
+    "F10_TRX_TF_rH7tmKCdUJq": "F10_TRX_TF_rH7tmKCdUJq",
+    "F5_TRX_FG": "F5_TRX_FG",
+    "FAIRY_TALE_BLOCKS": "FAIRY_TALE_BLOCKS",
+    "FARM_ANIMAL": "FARM_ANIMAL",
+    "FARM_ANIMAL_9GyfdcPyESK": "FARM_ANIMAL_9GyfdcPyESK",
+    "FIRE_ENGINE": "FIRE_ENGINE",
+    "FIRE_TRUCK": "FIRE_TRUCK",
+    "FISHING_GAME": "FISHING_GAME",
+    "FOOD_BEVERAGE_SET": "FOOD_BEVERAGE_SET",
+    "FRACTION_FUN_n4h4qte23QR": "FRACTION_FUN_n4h4qte23QR",
+    "FRUIT_VEGGIE_DOMINO_GRADIENT": "FRUIT_VEGGIE_DOMINO_GRADIENT",
+    "FRUIT_VEGGIE_MEMO_GRADIENT": "FRUIT_VEGGIE_MEMO_GRADIENT",
+    "FYW_ALTERNATION": "FYW_ALTERNATION",
+    "FYW_DIVISION": "FYW_DIVISION",
+    "FemDophilus": "FemDophilus",
+    "Final_Fantasy_XIV_A_Realm_Reborn_60Day_Subscription": "Final_Fantasy_XIV_A_Realm_Reborn_60Day_Subscription",
+    "Firefly_Clue_Board_Game": "Firefly_Clue_Board_Game",
+    "FisherPrice_Make_A_Match_Game_Thomas_Friends": "FisherPrice_Make_A_Match_Game_Thomas_Friends",
+    "Fisher_price_Classic_Toys_Buzzy_Bee": "Fisher_price_Classic_Toys_Buzzy_Bee",
+    "Focus_8643_Lime_Squeezer_10x35x188_Enamelled_Aluminum_Light": "Focus_8643_Lime_Squeezer_10x35x188_Enamelled_Aluminum_Light",
+    "Folic_Acid": "Folic_Acid",
+    "Footed_Bowl_Sand": "Footed_Bowl_Sand",
+    "Fresca_Peach_Citrus_Sparkling_Flavored_Soda_12_PK": "Fresca_Peach_Citrus_Sparkling_Flavored_Soda_12_PK",
+    "Frozen_Olafs_In_Trouble_PopOMatic_Game": "Frozen_Olafs_In_Trouble_PopOMatic_Game",
+    "Frozen_Olafs_In_Trouble_PopOMatic_Game_OEu83W9T8pD": "Frozen_Olafs_In_Trouble_PopOMatic_Game_OEu83W9T8pD",
+    "Frozen_Scrabble_Jr": "Frozen_Scrabble_Jr",
+    "Fruity_Friends": "Fruity_Friends",
+    "Fujifilm_instax_SHARE_SP1_10_photos": "Fujifilm_instax_SHARE_SP1_10_photos",
+    "Full_Circle_Happy_Scraps_Out_Collector_Gray": "Full_Circle_Happy_Scraps_Out_Collector_Gray",
+    "GARDEN_SWING": "GARDEN_SWING",
+    "GEARS_PUZZLES_STANDARD_gcYxhNHhKlI": "GEARS_PUZZLES_STANDARD_gcYxhNHhKlI",
+    "GEOMETRIC_PEG_BOARD": "GEOMETRIC_PEG_BOARD",
+    "GEOMETRIC_SORTING_BOARD": "GEOMETRIC_SORTING_BOARD",
+    "GEOMETRIC_SORTING_BOARD_MNi4Rbuz9vj": "GEOMETRIC_SORTING_BOARD_MNi4Rbuz9vj",
+    "GIRLS_DECKHAND": "GIRLS_DECKHAND",
+    "GRANDFATHER_DOLL": "GRANDFATHER_DOLL",
+    "GRANDMOTHER": "GRANDMOTHER",
+    "Germanium_GE132": "Germanium_GE132",
+    "Ghost_6_Color_BlckWhtLavaSlvrCitrus_Size_80": "Ghost_6_Color_BlckWhtLavaSlvrCitrus_Size_80",
+    "Ghost_6_Color_MdngtDenmPomBrtePnkSlvBlk_Size_50": "Ghost_6_Color_MdngtDenmPomBrtePnkSlvBlk_Size_50",
+    "Ghost_6_GTX_Color_AnthBlckSlvrFernSulphSprng_Size_80": "Ghost_6_GTX_Color_AnthBlckSlvrFernSulphSprng_Size_80",
+    "Gigabyte_GA78LMTUSB3_50_Motherboard_Micro_ATX_Socket_AM3": "Gigabyte_GA78LMTUSB3_50_Motherboard_Micro_ATX_Socket_AM3",
+    "Gigabyte_GA970AUD3P_10_Motherboard_ATX_Socket_AM3": "Gigabyte_GA970AUD3P_10_Motherboard_ATX_Socket_AM3",
+    "Gigabyte_GAZ97XSLI_10_motherboard_ATX_LGA1150_Socket_Z97": "Gigabyte_GAZ97XSLI_10_motherboard_ATX_LGA1150_Socket_Z97",
+    "Glycerin_11_Color_AqrsDrsdnBluBlkSlvShckOrng_Size_50": "Glycerin_11_Color_AqrsDrsdnBluBlkSlvShckOrng_Size_50",
+    "Glycerin_11_Color_BrllntBluSkydvrSlvrBlckWht_Size_80": "Glycerin_11_Color_BrllntBluSkydvrSlvrBlckWht_Size_80",
+    "GoPro_HERO3_Composite_Cable": "GoPro_HERO3_Composite_Cable",
+    "Google_Cardboard_Original_package": "Google_Cardboard_Original_package",
+    "Grand_Prix": "Grand_Prix",
+    "Granimals_20_Wooden_ABC_Blocks_Wagon": "Granimals_20_Wooden_ABC_Blocks_Wagon",
+    "Granimals_20_Wooden_ABC_Blocks_Wagon_85VdSftGsLi": "Granimals_20_Wooden_ABC_Blocks_Wagon_85VdSftGsLi",
+    "Granimals_20_Wooden_ABC_Blocks_Wagon_g2TinmUGGHI": "Granimals_20_Wooden_ABC_Blocks_Wagon_g2TinmUGGHI",
+    "Great_Dinos_Triceratops_Toy": "Great_Dinos_Triceratops_Toy",
+    "Great_Jones_Wingtip": "Great_Jones_Wingtip",
+    "Great_Jones_Wingtip_j5NV8GRnitM": "Great_Jones_Wingtip_j5NV8GRnitM",
+    "Great_Jones_Wingtip_kAqSg6EgG0I": "Great_Jones_Wingtip_kAqSg6EgG0I",
+    "Great_Jones_Wingtip_wxH3dbtlvBC": "Great_Jones_Wingtip_wxH3dbtlvBC",
+    "Grreat_Choice_Dog_Double_Dish_Plastic_Blue": "Grreat_Choice_Dog_Double_Dish_Plastic_Blue",
+    "Grreatv_Choice_Dog_Bowl_Gray_Bones_Plastic_20_fl_oz_total": "Grreatv_Choice_Dog_Bowl_Gray_Bones_Plastic_20_fl_oz_total",
+    "Guardians_of_the_Galaxy_Galactic_Battlers_Rocket_Raccoon_Figure": "Guardians_of_the_Galaxy_Galactic_Battlers_Rocket_Raccoon_Figure",
+    "HAMMER_BALL": "HAMMER_BALL",
+    "HAMMER_PEG": "HAMMER_PEG",
+    "HAPPY_ENGINE": "HAPPY_ENGINE",
+    "HELICOPTER": "HELICOPTER",
+    "HP_1800_Tablet_8GB_7": "HP_1800_Tablet_8GB_7",
+    "HP_Card_Invitation_Kit": "HP_Card_Invitation_Kit",
+    "Hasbro_Cranium_Performance_and_Acting_Game": "Hasbro_Cranium_Performance_and_Acting_Game",
+    "Hasbro_Dont_Wake_Daddy_Board_Game": "Hasbro_Dont_Wake_Daddy_Board_Game",
+    "Hasbro_Dont_Wake_Daddy_Board_Game_NJnjGna4u1a": "Hasbro_Dont_Wake_Daddy_Board_Game_NJnjGna4u1a",
+    "Hasbro_Life_Board_Game": "Hasbro_Life_Board_Game",
+    "Hasbro_Monopoly_Hotels_Game": "Hasbro_Monopoly_Hotels_Game",
+    "Hasbro_Trivial_Pursuit_Family_Edition_Game": "Hasbro_Trivial_Pursuit_Family_Edition_Game",
+    "HeavyDuty_Flashlight": "HeavyDuty_Flashlight",
+    "Hefty_Waste_Basket_Decorative_Bronze_85_liter": "Hefty_Waste_Basket_Decorative_Bronze_85_liter",
+    "Hey_You_Pikachu_Nintendo_64": "Hey_You_Pikachu_Nintendo_64",
+    "Hilary": "Hilary",
+    "Home_Fashions_Washcloth_Linen": "Home_Fashions_Washcloth_Linen",
+    "Home_Fashions_Washcloth_Olive_Green": "Home_Fashions_Washcloth_Olive_Green",
+    "Horse_Dreams_Pencil_Case": "Horse_Dreams_Pencil_Case",
+    "Horses_in_Pink_Pencil_Case": "Horses_in_Pink_Pencil_Case",
+    "House_of_Cards_The_Complete_First_Season_4_Discs_DVD": "House_of_Cards_The_Complete_First_Season_4_Discs_DVD",
+    "Hyaluronic_Acid": "Hyaluronic_Acid",
+    "HyperX_Cloud_II_Headset_Gun_Metal": "HyperX_Cloud_II_Headset_Gun_Metal",
+    "HyperX_Cloud_II_Headset_Red": "HyperX_Cloud_II_Headset_Red",
+    "INTERNATIONAL_PAPER_Willamette_4_Brown_Bag_500Count": "INTERNATIONAL_PAPER_Willamette_4_Brown_Bag_500Count",
+    "Imaginext_Castle_Ogre": "Imaginext_Castle_Ogre",
+    "In_Green_Company_Surface_Saver_Ring_10_Terra_Cotta": "In_Green_Company_Surface_Saver_Ring_10_Terra_Cotta",
+    "Inositol": "Inositol",
+    "InterDesign_Over_Door": "InterDesign_Over_Door",
+    "IsoRich_Soy": "IsoRich_Soy",
+    "JA_Henckels_International_Premio_Cutlery_Block_Set_14Piece": "JA_Henckels_International_Premio_Cutlery_Block_Set_14Piece",
+    "JBL_Charge_Speaker_portable_wireless_wired_Green": "JBL_Charge_Speaker_portable_wireless_wired_Green",
+    "JS_WINGS_20_BLACK_FLAG": "JS_WINGS_20_BLACK_FLAG",
+    "JUICER_SET": "JUICER_SET",
+    "JUNGLE_HEIGHT": "JUNGLE_HEIGHT",
+    "Jansport_School_Backpack_Blue_Streak": "blue and black backpack",
+    "JarroDophilusFOS_Value_Size": "JarroDophilusFOS_Value_Size",
+    "JarroSil_Activated_Silicon": "JarroSil_Activated_Silicon",
+    "JarroSil_Activated_Silicon_5exdZHIeLAp": "JarroSil_Activated_Silicon_5exdZHIeLAp",
+    "Jarrow_Formulas_Glucosamine_Hci_Mega_1000_100_ct": "Jarrow_Formulas_Glucosamine_Hci_Mega_1000_100_ct",
+    "Jarrow_Glucosamine_Chondroitin_Combination_120_Caps": "Jarrow_Glucosamine_Chondroitin_Combination_120_Caps",
+    "Jawbone_UP24_Wireless_Activity_Tracker_Pink_Coral_L": "Jawbone_UP24_Wireless_Activity_Tracker_Pink_Coral_L",
+    "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_Kit_Jet_Black_M60": "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_Kit_Jet_Black_M60",
+    "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_MediumDark_Brown_M40": "Just_For_Men_Mustache_Beard_Brushin_Hair_Color_Gel_MediumDark_Brown_M40",
+    "Just_For_Men_ShampooIn_Haircolor_Jet_Black_60": "Just_For_Men_ShampooIn_Haircolor_Jet_Black_60",
+    "Just_For_Men_ShampooIn_Haircolor_Light_Brown_25": "Just_For_Men_ShampooIn_Haircolor_Light_Brown_25",
+    "Just_For_Men_Shampoo_In_Haircolor_Darkest_Brown_50": "Just_For_Men_Shampoo_In_Haircolor_Darkest_Brown_50",
+    "Justified_The_Complete_Fourth_Season_3_Discs_DVD": "Justified_The_Complete_Fourth_Season_3_Discs_DVD",
+    "KID_ROOM_FURNITURE_SET_1": "KID_ROOM_FURNITURE_SET_1",
+    "KITCHEN_FURNITURE_SET_1": "KITCHEN_FURNITURE_SET_1",
+    "KITCHEN_SET_CLASSIC_40HwCHfeG0H": "KITCHEN_SET_CLASSIC_40HwCHfeG0H",
+    "KS_Chocolate_Cube_Box_Assortment_By_Neuhaus_2010_Ounces": "white gift box with red straps",
+    "Kanex_MultiSync_Wireless_Keyboard": "Kanex_MultiSync_Wireless_Keyboard",
+    "Kid_Icarus_Uprising_Nintendo_3DS_Game": "Kid_Icarus_Uprising_Nintendo_3DS_Game",
+    "Kingston_DT4000MR_G2_Management_Ready_USB_64GB": "Kingston_DT4000MR_G2_Management_Ready_USB_64GB",
+    "Kong_Puppy_Teething_Rubber_Small_Pink": "Kong_Puppy_Teething_Rubber_Small_Pink",
+    "Kotex_U_Barely_There_Liners_Thin_60_count": "Kotex_U_Barely_There_Liners_Thin_60_count",
+    "Kotex_U_Tween_Pads_16_pads": "Kotex_U_Tween_Pads_16_pads",
+    "Kotobuki_Saucer_Dragon_Fly": "Kotobuki_Saucer_Dragon_Fly",
+    "Krill_Oil": "Krill_Oil",
+    "LACING_SHEEP": "LACING_SHEEP",
+    "LADYBUG_BEAD": "LADYBUG_BEAD",
+    "LEGO_5887_Dino_Defense_HQ": "LEGO_5887_Dino_Defense_HQ",
+    "LEGO_Bricks_More_Creative_Suitcase": "LEGO_Bricks_More_Creative_Suitcase",
+    "LEGO_City_Advent_Calendar": "LEGO_City_Advent_Calendar",
+    "LEGO_Creationary_Game": "LEGO_Creationary_Game",
+    "LEGO_Creationary_Game_ZJa163wlWp2": "LEGO_Creationary_Game_ZJa163wlWp2",
+    "LEGO_Duplo_Build_and_Play_Box_4629": "LEGO_Duplo_Build_and_Play_Box_4629",
+    "LEGO_Duplo_Creative_Animals_10573": "LEGO_Duplo_Creative_Animals_10573",
+    "LEGO_Fusion_Set_Town_Master": "LEGO_Fusion_Set_Town_Master",
+    "LEGO_Star_Wars_Advent_Calendar": "LEGO_Star_Wars_Advent_Calendar",
+    "LEUCIPPUS_ADIPURE": "LEUCIPPUS_ADIPURE",
+    "LTyrosine": "LTyrosine",
+    "Lactoferrin": "Lactoferrin",
+    "Lalaloopsy_Peanut_Big_Top_Tricycle": "Lalaloopsy_Peanut_Big_Top_Tricycle",
+    "Lavender_Snake_Tieks_Snake_Print_Ballet_Flats": "Lavender_Snake_Tieks_Snake_Print_Ballet_Flats",
+    "Leap_Frog_Paint_Dabber_Dot_Art_5_paint_bottles": "Leap_Frog_Paint_Dabber_Dot_Art_5_paint_bottles",
+    "Lego_Friends_Advent_Calendar": "Lego_Friends_Advent_Calendar",
+    "Lego_Friends_Mia": "Lego_Friends_Mia",
+    "Lenovo_Yoga_2_11": "Lenovo_Yoga_2_11",
+    "Little_Big_Planet_3_Plush_Edition": "Little_Big_Planet_3_Plush_Edition",
+    "Little_Debbie_Chocolate_Cupcakes_8_ct": "Little_Debbie_Chocolate_Cupcakes_8_ct",
+    "Little_Debbie_Cloud_Cakes_10_ct": "Little_Debbie_Cloud_Cakes_10_ct",
+    "Little_Debbie_Donut_Sticks_6_cake_donuts_10_oz_total": "Little_Debbie_Donut_Sticks_6_cake_donuts_10_oz_total",
+    "Little_House_on_the_Prairie_Season_Two_5_Discs_Includes_Digital": "Little_House_on_the_Prairie_Season_Two_5_Discs_Includes_Digital",
+    "Logitech_Ultimate_Ears_Boom_Wireless_Speaker_Night_Black": "Logitech_Ultimate_Ears_Boom_Wireless_Speaker_Night_Black",
+    "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige": "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige",
+    "Lovestruck_Tieks_Glittery_Rose_Gold_Italian_Leather_Ballet_Flats": "Lovestruck_Tieks_Glittery_Rose_Gold_Italian_Leather_Ballet_Flats",
+    "Luigis_Mansion_Dark_Moon_Nintendo_3DS_Game": "Luigis_Mansion_Dark_Moon_Nintendo_3DS_Game",
+    "Lutein": "Lutein",
+    "MARTIN_WEDGE_LACE_BOOT": "MARTIN_WEDGE_LACE_BOOT",
+    "MEAT_SET": "MEAT_SET",
+    "MINI_EXCAVATOR": "MINI_EXCAVATOR",
+    "MINI_FIRE_ENGINE": "MINI_FIRE_ENGINE",
+    "MINI_ROLLER": "MINI_ROLLER",
+    "MIRACLE_POUNDING": "MIRACLE_POUNDING",
+    "MK7": "MK7",
+    "MODERN_DOLL_FAMILY": "MODERN_DOLL_FAMILY",
+    "MONKEY_BOWLING": "MONKEY_BOWLING",
+    "MOSAIC": "MOSAIC",
+    "MOVING_MOUSE_PW_6PCSSET": "MOVING_MOUSE_PW_6PCSSET",
+    "MY_MOOD_MEMO": "MY_MOOD_MEMO",
+    "Mad_Gab_Refresh_Card_Game": "Mad_Gab_Refresh_Card_Game",
+    "Magnifying_Glassassrt": "Magnifying_Glassassrt",
+    "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil": "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil",
+    "Marc_Anthony_Strictly_Curls_Curl_Envy_Perfect_Curl_Cream_6_fl_oz_bottle": "Marc_Anthony_Strictly_Curls_Curl_Envy_Perfect_Curl_Cream_6_fl_oz_bottle",
+    "Marc_Anthony_True_Professional_Oil_of_Morocco_Argan_Oil_Treatment": "Marc_Anthony_True_Professional_Oil_of_Morocco_Argan_Oil_Treatment",
+    "Marc_Anthony_True_Professional_Strictly_Curls_Curl_Defining_Lotion": "Marc_Anthony_True_Professional_Strictly_Curls_Curl_Defining_Lotion",
+    "Mario_Luigi_Dream_Team_Nintendo_3DS_Game": "Mario_Luigi_Dream_Team_Nintendo_3DS_Game",
+    "Mario_Party_9_Wii_Game": "Mario_Party_9_Wii_Game",
+    "Markings_Desk_Caddy": "Markings_Desk_Caddy",
+    "Markings_Letter_Holder": "Markings_Letter_Holder",
+    "Marvel_Avengers_Titan_Hero_Series_Doctor_Doom": "Marvel_Avengers_Titan_Hero_Series_Doctor_Doom",
+    "Mastic_Gum": "Mastic_Gum",
+    "Matte_Black_Tieks_Italian_Leather_Ballet_Flats": "Matte_Black_Tieks_Italian_Leather_Ballet_Flats",
+    "Mattel_SKIP_BO_Card_Game": "Mattel_SKIP_BO_Card_Game",
+    "Melissa_Doug_Cart_Turtle_Block": "Melissa_Doug_Cart_Turtle_Block",
+    "Melissa_Doug_Chunky_Puzzle_Vehicles": "Melissa_Doug_Chunky_Puzzle_Vehicles",
+    "Melissa_Doug_Felt_Food_Pizza_Set": "Melissa_Doug_Felt_Food_Pizza_Set",
+    "Melissa_Doug_Jumbo_Knob_Puzzles_Barnyard_Animals": "Melissa_Doug_Jumbo_Knob_Puzzles_Barnyard_Animals",
+    "Melissa_Doug_Pattern_Blocks_and_Boards": "Melissa_Doug_Pattern_Blocks_and_Boards",
+    "Melissa_Doug_Pound_and_Roll": "Melissa_Doug_Pound_and_Roll",
+    "Melissa_Doug_See_Spell": "Melissa_Doug_See_Spell",
+    "Melissa_Doug_Shape_Sorting_Clock": "Melissa_Doug_Shape_Sorting_Clock",
+    "Melissa_Doug_Traffic_Signs_and_Vehicles": "Melissa_Doug_Traffic_Signs_and_Vehicles",
+    "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w": "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w",
+    "Mens_ASV_Billfish_Boat_Shoe_in_Tan_Leather_wmUJ5PbwANc": "Mens_ASV_Billfish_Boat_Shoe_in_Tan_Leather_wmUJ5PbwANc",
+    "Mens_ASV_Shock_Light_Bungee_in_Light_Grey_xGCOvtLDnQJ": "Mens_ASV_Shock_Light_Bungee_in_Light_Grey_xGCOvtLDnQJ",
+    "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_NHHQddDLQys": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_NHHQddDLQys",
+    "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_RpT4GvUXRRP": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_RpT4GvUXRRP",
+    "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_xgoEcZtRNmH": "Mens_Authentic_Original_Boat_Shoe_in_Navy_Leather_xgoEcZtRNmH",
+    "Mens_Bahama_in_Black_b4ADzYywRHl": "Mens_Bahama_in_Black_b4ADzYywRHl",
+    "Mens_Bahama_in_Khaki_Oyster_xU2jeqYwhQJ": "Mens_Bahama_in_Khaki_Oyster_xU2jeqYwhQJ",
+    "Mens_Bahama_in_White_vSwvGMCo32f": "Mens_Bahama_in_White_vSwvGMCo32f",
+    "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH": "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH",
+    "Mens_Billfish_Slip_On_in_Coffee_e8bPKE9Lfgo": "Mens_Billfish_Slip_On_in_Coffee_e8bPKE9Lfgo",
+    "Mens_Billfish_Slip_On_in_Coffee_nK6AJJAHOae": "Mens_Billfish_Slip_On_in_Coffee_nK6AJJAHOae",
+    "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8": "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8",
+    "Mens_Billfish_Ultra_Lite_Boat_Shoe_in_Dark_Brown_Blue_c6zDZTtRJr6": "Mens_Billfish_Ultra_Lite_Boat_Shoe_in_Dark_Brown_Blue_c6zDZTtRJr6",
+    "Mens_Gold_Cup_ASV_2Eye_Boat_Shoe_in_Cognac_Leather": "Mens_Gold_Cup_ASV_2Eye_Boat_Shoe_in_Cognac_Leather",
+    "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_EjPnk3E8fCs": "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_EjPnk3E8fCs",
+    "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_GkQBKqABeQN": "Mens_Gold_Cup_ASV_Capetown_Penny_Loafer_in_Black_GkQBKqABeQN",
+    "Mens_Gold_Cup_ASV_Dress_Casual_Venetian_in_Dark_Brown_Leather": "Mens_Gold_Cup_ASV_Dress_Casual_Venetian_in_Dark_Brown_Leather",
+    "Mens_Largo_Slip_On_in_Taupe_gooyS417q4R": "Mens_Largo_Slip_On_in_Taupe_gooyS417q4R",
+    "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_9d05GG33QQQ": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_9d05GG33QQQ",
+    "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_K9e8FoV73uZ": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_Coffee_K9e8FoV73uZ",
+    "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_OysterTaupe_otyRrfvPMiA": "Mens_Mako_Canoe_Moc_2Eye_Boat_Shoe_in_OysterTaupe_otyRrfvPMiA",
+    "Mens_RR_Moc_in_Navy_Suede_vmFfijhBzL3": "Mens_RR_Moc_in_Navy_Suede_vmFfijhBzL3",
+    "Mens_Santa_Cruz_Thong_in_Chocolate_La1fo2mAovE": "Mens_Santa_Cruz_Thong_in_Chocolate_La1fo2mAovE",
+    "Mens_Santa_Cruz_Thong_in_Chocolate_lvxYW7lek6B": "Mens_Santa_Cruz_Thong_in_Chocolate_lvxYW7lek6B",
+    "Mens_Santa_Cruz_Thong_in_Tan_r59C69daRPh": "Mens_Santa_Cruz_Thong_in_Tan_r59C69daRPh",
+    "Mens_Striper_Sneaker_in_White_rnp8HUli59Y": "Mens_Striper_Sneaker_in_White_rnp8HUli59Y",
+    "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto",
+    "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_FT0I9OjSA6O": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_FT0I9OjSA6O",
+    "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_rCdzRZqgCnI": "Mens_Tremont_Kiltie_Tassel_Loafer_in_Black_Amaretto_rCdzRZqgCnI",
+    "Mens_Wave_Driver_Kiltie_Moc_in_Tan_Leather": "Mens_Wave_Driver_Kiltie_Moc_in_Tan_Leather",
+    "Metallic_Gold_Tieks_Italian_Leather_Ballet_Flats": "Metallic_Gold_Tieks_Italian_Leather_Ballet_Flats",
+    "Metallic_Pewter_Tieks_Italian_Leather_Ballet_Flats": "Metallic_Pewter_Tieks_Italian_Leather_Ballet_Flats",
+    "Mist_Wipe_Warmer": "Mist_Wipe_Warmer",
+    "My_First_Animal_Tower": "My_First_Animal_Tower",
+    "My_First_Rolling_Lion": "My_First_Rolling_Lion",
+    "My_First_Wiggle_Crocodile": "My_First_Wiggle_Crocodile",
+    "My_Little_Pony_Princess_Celestia": "My_Little_Pony_Princess_Celestia",
+    "My_Monopoly_Board_Game": "My_Monopoly_Board_Game",
+    "NAPA_VALLEY_NAVAJO_SANDAL": "NAPA_VALLEY_NAVAJO_SANDAL",
+    "NESCAFE_NESCAFE_TC_STKS_DECAF_6_CT": "NESCAFE_NESCAFE_TC_STKS_DECAF_6_CT",
+    "NUTS_BOLTS": "NUTS_BOLTS",
+    "NattoMax": "NattoMax",
+    "Neat_Solutions_Character_Bib_2_pack": "Neat_Solutions_Character_Bib_2_pack",
+    "Nescafe_16Count_Dolce_Gusto_Cappuccino_Capsules": "Nescafe_16Count_Dolce_Gusto_Cappuccino_Capsules",
+    "Nescafe_Memento_Latte_Caramel_8_08_oz_23_g_packets_64_oz_184_g": "Nescafe_Memento_Latte_Caramel_8_08_oz_23_g_packets_64_oz_184_g",
+    "Nescafe_Momento_Mocha_Specialty_Coffee_Mix_8_ct": "Nescafe_Momento_Mocha_Specialty_Coffee_Mix_8_ct",
+    "Nescafe_Tasters_Choice_Instant_Coffee_Decaf_House_Blend_Light_7_oz": "Nescafe_Tasters_Choice_Instant_Coffee_Decaf_House_Blend_Light_7_oz",
+    "Nestl_Crunch_Girl_Scouts_Cookie_Flavors_Caramel_Coconut_78_oz_box": "Nestl_Crunch_Girl_Scouts_Cookie_Flavors_Caramel_Coconut_78_oz_box",
+    "Nestl_Skinny_Cow_Heavenly_Crisp_Candy_Bar_Chocolate_Raspberry_6_pack_462_oz_total": "Nestl_Skinny_Cow_Heavenly_Crisp_Candy_Bar_Chocolate_Raspberry_6_pack_462_oz_total",
+    "Nestle_Candy_19_oz_Butterfinger_Singles_116567": "Nestle_Candy_19_oz_Butterfinger_Singles_116567",
+    "Nestle_Carnation_Cinnamon_Coffeecake_Kit_1913OZ": "Nestle_Carnation_Cinnamon_Coffeecake_Kit_1913OZ",
+    "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister": "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister",
+    "Nestle_Nips_Hard_Candy_Peanut_Butter": "Nestle_Nips_Hard_Candy_Peanut_Butter",
+    "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can": "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can",
+    "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can_aX0ygjh3bxi": "Nestle_Pure_Life_Exotics_Sparkling_Water_Strawberry_Dragon_Fruit_8_count_12_fl_oz_can_aX0ygjh3bxi",
+    "Nestle_Raisinets_Milk_Chocolate_35_oz_992_g": "Nestle_Raisinets_Milk_Chocolate_35_oz_992_g",
+    "Nestle_Skinny_Cow_Dreamy_Clusters_Candy_Dark_Chocolate_6_pack_1_oz_pouches": "Nestle_Skinny_Cow_Dreamy_Clusters_Candy_Dark_Chocolate_6_pack_1_oz_pouches",
+    "Netgear_Ac1750_Router_Wireless_Dual_Band_Gigabit_Router": "Netgear_Ac1750_Router_Wireless_Dual_Band_Gigabit_Router",
+    "Netgear_N750_Wireless_Dual_Band_Gigabit_Router": "Netgear_N750_Wireless_Dual_Band_Gigabit_Router",
+    "Netgear_Nighthawk_X6_AC3200_TriBand_Gigabit_Wireless_Router": "Netgear_Nighthawk_X6_AC3200_TriBand_Gigabit_Wireless_Router",
+    "New_Super_Mario_BrosWii_Wii_Game": "New_Super_Mario_BrosWii_Wii_Game",
+    "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo",
+    "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo",
+    "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael": "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael",
+    "Nickelodeon_The_Spongebob_Movie_PopAPart_Spongebob": "Nickelodeon_The_Spongebob_Movie_PopAPart_Spongebob",
+    "Nightmare_Before_Christmas_Collectors_Edition_Operation": "Nightmare_Before_Christmas_Collectors_Edition_Operation",
+    "Nikon_1_AW1_w11275mm_Lens_Silver": "Nikon_1_AW1_w11275mm_Lens_Silver",
+    "Nintendo_2DS_Crimson_Red": "Nintendo_2DS_Crimson_Red",
+    "Nintendo_Mario_Action_Figure": "Nintendo_Mario_Action_Figure",
+    "Nintendo_Wii_Party_U_with_Controller_Wii_U_Game": "Nintendo_Wii_Party_U_with_Controller_Wii_U_Game",
+    "Nintendo_Yoshi_Action_Figure": "Nintendo_Yoshi_Action_Figure",
+    "Nips_Hard_Candy_Rich_Creamy_Butter_Rum_4_oz_1133_g": "Nips_Hard_Candy_Rich_Creamy_Butter_Rum_4_oz_1133_g",
+    "Nordic_Ware_Original_Bundt_Pan": "Nordic_Ware_Original_Bundt_Pan",
+    "Now_Designs_Bowl_Akita_Black": "Now_Designs_Bowl_Akita_Black",
+    "Now_Designs_Dish_Towel_Mojave_18_x_28": "Now_Designs_Dish_Towel_Mojave_18_x_28",
+    "Now_Designs_Snack_Bags_Bicycle_2_count": "Now_Designs_Snack_Bags_Bicycle_2_count",
+    "OVAL_XYLOPHONE": "OVAL_XYLOPHONE",
+    "OWL_SORTER": "OWL_SORTER",
+    "OXO_Cookie_Spatula": "OXO_Cookie_Spatula",
+    "OXO_Soft_Works_Can_Opener_SnapLock": "OXO_Soft_Works_Can_Opener_SnapLock",
+    "Object": "Object",
+    "Object_REmvBDJStub": "Object_REmvBDJStub",
+    "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct": "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct",
+    "Office_Depot_Canon_CL211XL_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Canon_CL211XL_Remanufactured_Ink_Cartridge_TriColor",
+    "Office_Depot_Canon_CLI36_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Canon_CLI36_Remanufactured_Ink_Cartridge_TriColor",
+    "Office_Depot_Canon_CLI_221BK_Ink_Cartridge_Black_2946B001": "Office_Depot_Canon_CLI_221BK_Ink_Cartridge_Black_2946B001",
+    "Office_Depot_Canon_CLI_8CMY_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": "Office_Depot_Canon_CLI_8CMY_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+    "Office_Depot_Canon_CLI_8Y_Ink_Cartridge_Yellow_0623B002": "Office_Depot_Canon_CLI_8Y_Ink_Cartridge_Yellow_0623B002",
+    "Office_Depot_Canon_CL_41_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Canon_CL_41_Remanufactured_Ink_Cartridge_TriColor",
+    "Office_Depot_Canon_PG21XL_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PG21XL_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Canon_PGI22_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PGI22_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Canon_PGI35_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PGI35_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Canon_PGI5BK_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Canon_PGI5BK_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Canon_PG_240XL_Ink_Cartridge_Black_5206B001": "Office_Depot_Canon_PG_240XL_Ink_Cartridge_Black_5206B001",
+    "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Dell_Series_11_Remanufactured_Ink_Cartridge_TriColor",
+    "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_Dell_Series_1_Remanufactured_Ink_Cartridge_TriColor",
+    "Office_Depot_Dell_Series_5_Remanufactured_Ink_Cartridge_Black": "Office_Depot_Dell_Series_5_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_Dell_Series_9_Color_Ink_Ink_Cartridge_MK991_MK993": "Office_Depot_Dell_Series_9_Color_Ink_Ink_Cartridge_MK991_MK993",
+    "Office_Depot_Dell_Series_9_Ink_Cartridge_Black_MK992": "Office_Depot_Dell_Series_9_Ink_Cartridge_Black_MK992",
+    "Office_Depot_HP_2_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": "Office_Depot_HP_2_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+    "Office_Depot_HP_564XL_Ink_Cartridge_Black_CN684WN": "Office_Depot_HP_564XL_Ink_Cartridge_Black_CN684WN",
+    "Office_Depot_HP_564XL_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count": "Office_Depot_HP_564XL_Remanufactured_Ink_Cartridges_Color_Cyan_Magenta_Yellow_3_count",
+    "Office_Depot_HP_61Tricolor_Ink_Cartridge": "Office_Depot_HP_61Tricolor_Ink_Cartridge",
+    "Office_Depot_HP_71_Remanufactured_Ink_Cartridge_Black": "Office_Depot_HP_71_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_HP_74XL75_Remanufactured_Ink_Cartridges_BlackTriColor_2_count": "Office_Depot_HP_74XL75_Remanufactured_Ink_Cartridges_BlackTriColor_2_count",
+    "Office_Depot_HP_75_Remanufactured_Ink_Cartridge_TriColor": "Office_Depot_HP_75_Remanufactured_Ink_Cartridge_TriColor",
+    "Office_Depot_HP_920XL_920_High_Yield_Black_and_Standard_CMY_Color_Ink_Cartridges": "Office_Depot_HP_920XL_920_High_Yield_Black_and_Standard_CMY_Color_Ink_Cartridges",
+    "Office_Depot_HP_932XL_Ink_Cartridge_Black_CN053A": "Office_Depot_HP_932XL_Ink_Cartridge_Black_CN053A",
+    "Office_Depot_HP_950XL_Ink_Cartridge_Black_CN045AN": "Office_Depot_HP_950XL_Ink_Cartridge_Black_CN045AN",
+    "Office_Depot_HP_96_Remanufactured_Ink_Cartridge_Black": "Office_Depot_HP_96_Remanufactured_Ink_Cartridge_Black",
+    "Office_Depot_HP_98_Remanufactured_Ink_Cartridge_Black": "Office_Depot_HP_98_Remanufactured_Ink_Cartridge_Black",
+    "Olive_Kids_Birdie_Lunch_Box": "Olive_Kids_Birdie_Lunch_Box",
+    "Olive_Kids_Birdie_Munch_n_Lunch": "Olive_Kids_Birdie_Munch_n_Lunch",
+    "Olive_Kids_Birdie_Pack_n_Snack": "Olive_Kids_Birdie_Pack_n_Snack",
+    "Olive_Kids_Birdie_Sidekick_Backpack": "Olive_Kids_Birdie_Sidekick_Backpack",
+    "Olive_Kids_Butterfly_Garden_Munch_n_Lunch_Bag": "Olive_Kids_Butterfly_Garden_Munch_n_Lunch_Bag",
+    "Olive_Kids_Butterfly_Garden_Pencil_Case": "Olive_Kids_Butterfly_Garden_Pencil_Case",
+    "Olive_Kids_Dinosaur_Land_Lunch_Box": "Olive_Kids_Dinosaur_Land_Lunch_Box",
+    "Olive_Kids_Dinosaur_Land_Munch_n_Lunch": "Olive_Kids_Dinosaur_Land_Munch_n_Lunch",
+    "Olive_Kids_Dinosaur_Land_Pack_n_Snack": "Olive_Kids_Dinosaur_Land_Pack_n_Snack",
+    "Olive_Kids_Dinosaur_Land_Sidekick_Backpack": "Olive_Kids_Dinosaur_Land_Sidekick_Backpack",
+    "Olive_Kids_Game_On_Lunch_Box": "Olive_Kids_Game_On_Lunch_Box",
+    "Olive_Kids_Game_On_Munch_n_Lunch": "Olive_Kids_Game_On_Munch_n_Lunch",
+    "Olive_Kids_Game_On_Pack_n_Snack": "Olive_Kids_Game_On_Pack_n_Snack",
+    "Olive_Kids_Mermaids_Pack_n_Snack_Backpack": "Olive_Kids_Mermaids_Pack_n_Snack_Backpack",
+    "Olive_Kids_Paisley_Pencil_Case": "Olive_Kids_Paisley_Pencil_Case",
+    "Olive_Kids_Robots_Pencil_Case": "Olive_Kids_Robots_Pencil_Case",
+    "Olive_Kids_Trains_Planes_Trucks_Bogo_Backpack": "Olive_Kids_Trains_Planes_Trucks_Bogo_Backpack",
+    "Olive_Kids_Trains_Planes_Trucks_Munch_n_Lunch_Bag": "Olive_Kids_Trains_Planes_Trucks_Munch_n_Lunch_Bag",
+    "Orbit_Bubblemint_Mini_Bottle_6_ct": "Orbit_Bubblemint_Mini_Bottle_6_ct",
+    "Organic_Whey_Protein_Unflavored": "Organic_Whey_Protein_Unflavored",
+    "Organic_Whey_Protein_Vanilla": "Organic_Whey_Protein_Vanilla",
+    "Ortho_Forward_Facing": "Ortho_Forward_Facing",
+    "Ortho_Forward_Facing_3Q6J2oKJD92": "Ortho_Forward_Facing_3Q6J2oKJD92",
+    "Ortho_Forward_Facing_CkAW6rL25xH": "Ortho_Forward_Facing_CkAW6rL25xH",
+    "Ortho_Forward_Facing_QCaor9ImJ2G": "Ortho_Forward_Facing_QCaor9ImJ2G",
+    "PARENT_ROOM_FURNITURE_SET_1": "PARENT_ROOM_FURNITURE_SET_1",
+    "PARENT_ROOM_FURNITURE_SET_1_DLKEy8H4mwK": "PARENT_ROOM_FURNITURE_SET_1_DLKEy8H4mwK",
+    "PEEKABOO_ROLLER": "PEEKABOO_ROLLER",
+    "PEPSI_NEXT_CACRV": "PEPSI_NEXT_CACRV",
+    "PETS_ACCESSORIES": "PETS_ACCESSORIES",
+    "PHEEHAN_RUN": "PHEEHAN_RUN",
+    "PINEAPPLE_MARACA_6_PCSSET": "PINEAPPLE_MARACA_6_PCSSET",
+    "POUNDING_MUSHROOMS": "POUNDING_MUSHROOMS",
+    "PUNCH_DROP": "PUNCH_DROP",
+    "PUNCH_DROP_TjicLPMqLvz": "PUNCH_DROP_TjicLPMqLvz",
+    "Paint_Maker": "Paint_Maker",
+    "Paper_Mario_Sticker_Star_Nintendo_3DS_Game": "Paper_Mario_Sticker_Star_Nintendo_3DS_Game",
+    "Pass_The_Popcorn_Movie_Guessing_Game": "Pass_The_Popcorn_Movie_Guessing_Game",
+    "Paul_Frank_Dot_Lunch_Box": "Paul_Frank_Dot_Lunch_Box",
+    "Pennington_Electric_Pot_Cabana_4": "Pennington_Electric_Pot_Cabana_4",
+    "Pepsi_Caffeine_Free_Diet_12_CT": "Pepsi_Caffeine_Free_Diet_12_CT",
+    "Pepsi_Cola_Caffeine_Free_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Pepsi_Cola_Caffeine_Free_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+    "Pepsi_Cola_Wild_Cherry_Diet_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Pepsi_Cola_Wild_Cherry_Diet_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+    "Pepsi_Max_Cola_Zero_Calorie_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt": "Pepsi_Max_Cola_Zero_Calorie_12_12_fl_oz_355_ml_cans_144_fl_oz_426_lt",
+    "Perricoen_MD_No_Concealer_Concealer": "Perricoen_MD_No_Concealer_Concealer",
+    "Perricone_MD_AcylGlutathione_Deep_Crease_Serum": "Perricone_MD_AcylGlutathione_Deep_Crease_Serum",
+    "Perricone_MD_AcylGlutathione_Eye_Lid_Serum": "Perricone_MD_AcylGlutathione_Eye_Lid_Serum",
+    "Perricone_MD_Best_of_Perricone_7Piece_Collection_MEGsO6GIsyL": "Perricone_MD_Best_of_Perricone_7Piece_Collection_MEGsO6GIsyL",
+    "Perricone_MD_Blue_Plasma_Orbital": "Perricone_MD_Blue_Plasma_Orbital",
+    "Perricone_MD_Chia_Serum": "Perricone_MD_Chia_Serum",
+    "Perricone_MD_Cold_Plasma": "Perricone_MD_Cold_Plasma",
+    "Perricone_MD_Cold_Plasma_Body": "Perricone_MD_Cold_Plasma_Body",
+    "Perricone_MD_Face_Finishing_Moisturizer": "Perricone_MD_Face_Finishing_Moisturizer",
+    "Perricone_MD_Face_Finishing_Moisturizer_4_oz": "Perricone_MD_Face_Finishing_Moisturizer_4_oz",
+    "Perricone_MD_Firming_Neck_Therapy_Treatment": "Perricone_MD_Firming_Neck_Therapy_Treatment",
+    "Perricone_MD_Health_Weight_Management_Supplements": "Perricone_MD_Health_Weight_Management_Supplements",
+    "Perricone_MD_High_Potency_Evening_Repair": "Perricone_MD_High_Potency_Evening_Repair",
+    "Perricone_MD_Hypoallergenic_Firming_Eye_Cream_05_oz": "Perricone_MD_Hypoallergenic_Firming_Eye_Cream_05_oz",
+    "Perricone_MD_Hypoallergenic_Gentle_Cleanser": "Perricone_MD_Hypoallergenic_Gentle_Cleanser",
+    "Perricone_MD_Neuropeptide_Facial_Conformer": "Perricone_MD_Neuropeptide_Facial_Conformer",
+    "Perricone_MD_Neuropeptide_Firming_Moisturizer": "Perricone_MD_Neuropeptide_Firming_Moisturizer",
+    "Perricone_MD_No_Bronzer_Bronzer": "Perricone_MD_No_Bronzer_Bronzer",
+    "Perricone_MD_No_Foundation_Foundation_No_1": "Perricone_MD_No_Foundation_Foundation_No_1",
+    "Perricone_MD_No_Foundation_Serum": "Perricone_MD_No_Foundation_Serum",
+    "Perricone_MD_No_Lipstick_Lipstick": "Perricone_MD_No_Lipstick_Lipstick",
+    "Perricone_MD_No_Mascara_Mascara": "Perricone_MD_No_Mascara_Mascara",
+    "Perricone_MD_Nutritive_Cleanser": "Perricone_MD_Nutritive_Cleanser",
+    "Perricone_MD_OVM": "Perricone_MD_OVM",
+    "Perricone_MD_Omega_3_Supplements": "Perricone_MD_Omega_3_Supplements",
+    "Perricone_MD_Photo_Plasma": "Perricone_MD_Photo_Plasma",
+    "Perricone_MD_Skin_Clear_Supplements": "Perricone_MD_Skin_Clear_Supplements",
+    "Perricone_MD_Skin_Total_Body_Supplements": "Perricone_MD_Skin_Total_Body_Supplements",
+    "Perricone_MD_Super_Berry_Powder_with_Acai_Supplements": "Perricone_MD_Super_Berry_Powder_with_Acai_Supplements",
+    "Perricone_MD_The_Cold_Plasma_Face_Eyes_Duo": "Perricone_MD_The_Cold_Plasma_Face_Eyes_Duo",
+    "Perricone_MD_The_Crease_Cure_Duo": "Perricone_MD_The_Crease_Cure_Duo",
+    "Perricone_MD_The_Metabolic_Formula_Supplements": "Perricone_MD_The_Metabolic_Formula_Supplements",
+    "Perricone_MD_The_Power_Treatments": "Perricone_MD_The_Power_Treatments",
+    "Perricone_MD_Vitamin_C_Ester_15": "Perricone_MD_Vitamin_C_Ester_15",
+    "Perricone_MD_Vitamin_C_Ester_Serum": "Perricone_MD_Vitamin_C_Ester_Serum",
+    "Persona_Q_Shadow_of_the_Labyrinth_Nintendo_3DS": "Persona_Q_Shadow_of_the_Labyrinth_Nintendo_3DS",
+    "Pet_Dophilus_powder": "Pet_Dophilus_powder",
+    "Philips_60ct_Warm_White_LED_Smooth_Mini_String_Lights": "Philips_60ct_Warm_White_LED_Smooth_Mini_String_Lights",
+    "Philips_EcoVantage_43_W_Light_Bulbs_Natural_Light_2_pack": "Philips_EcoVantage_43_W_Light_Bulbs_Natural_Light_2_pack",
+    "Philips_Sonicare_Tooth_Brush_2_count": "Philips_Sonicare_Tooth_Brush_2_count",
+    "Phillips_Caplets_Size_24": "Phillips_Caplets_Size_24",
+    "Phillips_Colon_Health_Probiotic_Capsule": "Phillips_Colon_Health_Probiotic_Capsule",
+    "Phillips_Milk_of_Magnesia_Saline_Laxative_Liquid_Original": "Phillips_Milk_of_Magnesia_Saline_Laxative_Liquid_Original",
+    "Phillips_Stool_Softener_Liquid_Gels_30_liquid_gels": "Phillips_Stool_Softener_Liquid_Gels_30_liquid_gels",
+    "PhosphOmega": "PhosphOmega",
+    "Pinwheel_Pencil_Case": "Pinwheel_Pencil_Case",
+    "Playmates_Industrial_CoSplinter_Teenage_Mutant_Ninja_Turtle_Action_Figure": "Playmates_Industrial_CoSplinter_Teenage_Mutant_Ninja_Turtle_Action_Figure",
+    "Playmates_nickelodeon_teenage_mutant_ninja_turtles_shredder": "Playmates_nickelodeon_teenage_mutant_ninja_turtles_shredder",
+    "Poise_Ultimate_Pads_Long": "Poise_Ultimate_Pads_Long",
+    "Pokmon_Conquest_Nintendo_DS_Game": "Pokmon_Conquest_Nintendo_DS_Game",
+    "Pokmon_X_Nintendo_3DS_Game": "Pokmon_X_Nintendo_3DS_Game",
+    "Pokmon_Y_Nintendo_3DS_Game": "Pokmon_Y_Nintendo_3DS_Game",
+    "Pok\u00e9mon_Omega_Ruby_Alpha_Sapphire_Dual_Pack_Nintendo_3DS": "Pok\u00e9mon_Omega_Ruby_Alpha_Sapphire_Dual_Pack_Nintendo_3DS",
+    "Pok\u00e9mon_Yellow_Special_Pikachu_Edition_Nintendo_Game_Boy_Color": "Pok\u00e9mon_Yellow_Special_Pikachu_Edition_Nintendo_Game_Boy_Color",
+    "Polar_Herring_Fillets_Smoked_Peppered_705_oz_total": "Polar_Herring_Fillets_Smoked_Peppered_705_oz_total",
+    "Pony_C_Clamp_1440": "Pony_C_Clamp_1440",
+    "Poppin_File_Sorter_Blue": "Poppin_File_Sorter_Blue",
+    "Poppin_File_Sorter_Pink": "Poppin_File_Sorter_Pink",
+    "Poppin_File_Sorter_White": "Poppin_File_Sorter_White",
+    "Predator_LZ_TRX_FG": "Predator_LZ_TRX_FG",
+    "Predito_LZ_TRX_FG_W": "Predito_LZ_TRX_FG_W",
+    "ProSport_Harness_to_Booster_Seat": "ProSport_Harness_to_Booster_Seat",
+    "Progressive_Rubber_Spatulas_3_count": "Progressive_Rubber_Spatulas_3_count",
+    "Prostate_Optimizer": "Prostate_Optimizer",
+    "Provence_Bath_Towel_Royal_Blue": "Provence_Bath_Towel_Royal_Blue",
+    "PureCadence_2_Color_HiRskRedNghtlfeSlvrBlckWht_Size_70": "PureCadence_2_Color_HiRskRedNghtlfeSlvrBlckWht_Size_70",
+    "PureCadence_2_Color_TleBluLmePnchSlvMoodIndgWh_Size_50_EEzAfcBfHHO": "PureCadence_2_Color_TleBluLmePnchSlvMoodIndgWh_Size_50_EEzAfcBfHHO",
+    "PureConnect_2_Color_AnthrcteKnckoutPnkGrnGecko_Size_50": "PureConnect_2_Color_AnthrcteKnckoutPnkGrnGecko_Size_50",
+    "PureConnect_2_Color_BlckBrllntBluNghtlfeAnthrct_Size_70": "PureConnect_2_Color_BlckBrllntBluNghtlfeAnthrct_Size_70",
+    "PureConnect_2_Color_FernNightlifeSilverBlack_Size_70_5w0BYsiogeV": "PureConnect_2_Color_FernNightlifeSilverBlack_Size_70_5w0BYsiogeV",
+    "PureFlow_2_Color_RylPurHibiscusBlkSlvrWht_Size_50": "PureFlow_2_Color_RylPurHibiscusBlkSlvrWht_Size_50",
+    "QAbsorb_CoQ10": "QAbsorb_CoQ10",
+    "QAbsorb_CoQ10_53iUqjWjW3O": "QAbsorb_CoQ10_53iUqjWjW3O",
+    "QHPomegranate": "QHPomegranate",
+    "Quercetin_500": "Quercetin_500",
+    "REEF_BANTU": "black boot",
+    "REEF_BRAIDED_CUSHION": "REEF_BRAIDED_CUSHION",
+    "REEF_ZENFUN": "REEF_ZENFUN",
+    "RESCUE_CREW": "RESCUE_CREW",
+    "RJ_Rabbit_Easter_Basket_Blue": "RJ_Rabbit_Easter_Basket_Blue",
+    "ROAD_CONSTRUCTION_SET": "ROAD_CONSTRUCTION_SET",
+    "Racoon": "Racoon",
+    "Ravenna_4_Color_WhtOlyBluBlkShkOrngSlvRdO_Size_70": "Ravenna_4_Color_WhtOlyBluBlkShkOrngSlvRdO_Size_70",
+    "Rayna_BootieWP": "Rayna_BootieWP",
+    "Razer_Abyssus_Ambidextrous_Gaming_Mouse": "Razer_Abyssus_Ambidextrous_Gaming_Mouse",
+    "Razer_BlackWidow_Stealth_2014_Keyboard_07VFzIVabgh": "black keyboard",
+    "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard": "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard",
+    "Razer_Blackwidow_Tournament_Edition_Keyboard": "Razer_Blackwidow_Tournament_Edition_Keyboard",
+    "Razer_Goliathus_Control_Edition_Small_Soft_Gaming_Mouse_Mat": "Razer_Goliathus_Control_Edition_Small_Soft_Gaming_Mouse_Mat",
+    "Razer_Kraken_71_Chroma_headset_Full_size_Black": "Razer_Kraken_71_Chroma_headset_Full_size_Black",
+    "Razer_Kraken_Pro_headset_Full_size_Black": "Razer_Kraken_Pro_headset_Full_size_Black",
+    "Razer_Naga_MMO_Gaming_Mouse": "Razer_Naga_MMO_Gaming_Mouse",
+    "Razer_Taipan_Black_Ambidextrous_Gaming_Mouse": "black gaming mouse",
+    "Razer_Taipan_White_Ambidextrous_Gaming_Mouse": "white gaming mouse",
+    "ReadytoUse_Rolled_Fondant_Pure_White_24_oz_box": "ReadytoUse_Rolled_Fondant_Pure_White_24_oz_box",
+    "Real_Deal_1nIwCHX1MTh": "Real_Deal_1nIwCHX1MTh",
+    "RedBlack_Nintendo_3DSXL": "black and red gameboy",
+    "Reebok_ALLYLYNN": "Reebok_ALLYLYNN",
+    "Reebok_BREAKPOINT_LO_2V": "Reebok_BREAKPOINT_LO_2V",
+    "Reebok_BREAKPOINT_MID": "Reebok_BREAKPOINT_MID",
+    "Reebok_CLASSIC_JOGGER": "Reebok_CLASSIC_JOGGER",
+    "Reebok_CLASSIC_LEGACY_II": "Reebok_CLASSIC_LEGACY_II",
+    "Reebok_CL_DIBELLO_II": "Reebok_CL_DIBELLO_II",
+    "Reebok_CL_LTHR_R12": "Reebok_CL_LTHR_R12",
+    "Reebok_CL_RAYEN": "Reebok_CL_RAYEN",
+    "Reebok_COMFORT_REEFRESH_FLIP": "Reebok_COMFORT_REEFRESH_FLIP",
+    "Reebok_DMX_MAX_MANIA_WD_D": "Reebok_DMX_MAX_MANIA_WD_D",
+    "Reebok_DMX_MAX_PLUS_ATHLETIC": "Reebok_DMX_MAX_PLUS_ATHLETIC",
+    "Reebok_DMX_MAX_PLUS_RAINWALKER": "Reebok_DMX_MAX_PLUS_RAINWALKER",
+    "Reebok_EASYTONE_CL_LEATHER": "Reebok_EASYTONE_CL_LEATHER",
+    "Reebok_FS_HI_INT_R12": "Reebok_FS_HI_INT_R12",
+    "Reebok_FS_HI_MINI": "Reebok_FS_HI_MINI",
+    "Reebok_FUELTRAIN": "Reebok_FUELTRAIN",
+    "Reebok_GL_6000": "Reebok_GL_6000",
+    "Reebok_HIMARA_LTR": "Reebok_HIMARA_LTR",
+    "Reebok_JR_ZIG_COOPERSTOWN_MR": "Reebok_JR_ZIG_COOPERSTOWN_MR",
+    "Reebok_KAMIKAZE_II_MID": "Reebok_KAMIKAZE_II_MID",
+    "Reebok_PUMP_OMNI_LITE_HLS": "Reebok_PUMP_OMNI_LITE_HLS",
+    "Reebok_REALFLEX_SELECT": "Reebok_REALFLEX_SELECT",
+    "Reebok_REESCULPT_TRAINER_II": "Reebok_REESCULPT_TRAINER_II",
+    "Reebok_RETRO_RUSH_2V": "Reebok_RETRO_RUSH_2V",
+    "Reebok_R_CROSSFIT_OLY_UFORM": "Reebok_R_CROSSFIT_OLY_UFORM",
+    "Reebok_R_DANCE_FLASH": "Reebok_R_DANCE_FLASH",
+    "Reebok_SH_COURT_MID_II": "Reebok_SH_COURT_MID_II",
+    "Reebok_SH_NEWPORT_LOW": "Reebok_SH_NEWPORT_LOW",
+    "Reebok_SH_PRIME_COURT_LOW": "Reebok_SH_PRIME_COURT_LOW",
+    "Reebok_SH_PRIME_COURT_MID": "Reebok_SH_PRIME_COURT_MID",
+    "Reebok_SL_FLIP_UPDATE": "Reebok_SL_FLIP_UPDATE",
+    "Reebok_SMOOTHFLEX_CUSHRUN_20": "Reebok_SMOOTHFLEX_CUSHRUN_20",
+    "Reebok_SOMERSET_RUN": "Reebok_SOMERSET_RUN",
+    "Reebok_STUDIO_BEAT_LOW_V": "Reebok_STUDIO_BEAT_LOW_V",
+    "Reebok_TRIPLE_BREAK_LITE": "Reebok_TRIPLE_BREAK_LITE",
+    "Reebok_TURBO_RC": "Reebok_TURBO_RC",
+    "Reebok_ULTIMATIC_2V": "Reebok_ULTIMATIC_2V",
+    "Reebok_VERSA_TRAIN": "Reebok_VERSA_TRAIN",
+    "Reebok_ZIGCOOPERSTOWN_QUAG": "Reebok_ZIGCOOPERSTOWN_QUAG",
+    "Reebok_ZIGLITE_RUSH": "Reebok_ZIGLITE_RUSH",
+    "Reebok_ZIGLITE_RUSH_AC": "Reebok_ZIGLITE_RUSH_AC",
+    "Reebok_ZIGSTORM": "Reebok_ZIGSTORM",
+    "Reebok_ZIGTECH_SHARK_MAYHEM360": "Reebok_ZIGTECH_SHARK_MAYHEM360",
+    "Reef_Star_Cushion_Flipflops_Size_8_Black": "Reef_Star_Cushion_Flipflops_Size_8_Black",
+    "Remington_1_12_inch_Hair_Straightener": "Remington_1_12_inch_Hair_Straightener",
+    "Remington_TStudio_Hair_Dryer": "Remington_TStudio_Hair_Dryer",
+    "Remington_TStudio_Silk_Ceramic_Hair_Straightener_2_Inch_Floating_Plates": "Remington_TStudio_Silk_Ceramic_Hair_Straightener_2_Inch_Floating_Plates",
+    "Retail_Leadership_Summit": "brown hat",
+    "Retail_Leadership_Summit_eCT3zqHYIkX": "Retail_Leadership_Summit_eCT3zqHYIkX",
+    "Retail_Leadership_Summit_tQFCizMt6g0": "Retail_Leadership_Summit_tQFCizMt6g0",
+    "Rexy_Glove_Heavy_Duty_Gloves_Medium": "blue gloves",
+    "Rexy_Glove_Heavy_Duty_Large": "Rexy_Glove_Heavy_Duty_Large",
+    "Romantic_Blush_Tieks_Metallic_Italian_Leather_Ballet_Flats": "Romantic_Blush_Tieks_Metallic_Italian_Leather_Ballet_Flats",
+    "Room_Essentials_Bowl_Turquiose": "Room_Essentials_Bowl_Turquiose",
+    "Room_Essentials_Dish_Drainer_Collapsible_White": "Room_Essentials_Dish_Drainer_Collapsible_White",
+    "Room_Essentials_Fabric_Cube_Lavender": "Room_Essentials_Fabric_Cube_Lavender",
+    "Room_Essentials_Kitchen_Towels_16_x_26_2_count": "Room_Essentials_Kitchen_Towels_16_x_26_2_count",
+    "Room_Essentials_Mug_White_Yellow": "Room_Essentials_Mug_White_Yellow",
+    "Room_Essentials_Salad_Plate_Turquoise": "Room_Essentials_Salad_Plate_Turquoise",
+    "Rose_Garden_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes": "Rose_Garden_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes",
+    "Rubbermaid_Large_Drainer": "Rubbermaid_Large_Drainer",
+    "SAMBA_HEMP": "SAMBA_HEMP",
+    "SAMOA": "SAMOA",
+    "SAMe_200": "SAMe_200",
+    "SAMe_200_KX7ZmOw47co": "SAMe_200_KX7ZmOw47co",
+    "SANDWICH_MEAL": "SANDWICH_MEAL",
+    "SAPPHIRE_R7_260X_OC": "SAPPHIRE_R7_260X_OC",
+    "SCHOOL_BUS": "SCHOOL_BUS",
+    "SHAPE_MATCHING": "SHAPE_MATCHING",
+    "SHAPE_MATCHING_NxacpAY9jDt": "SHAPE_MATCHING_NxacpAY9jDt",
+    "SHAPE_SORTER": "SHAPE_SORTER",
+    "SIT_N_WALK_PUPPY": "SIT_N_WALK_PUPPY",
+    "SLACK_CRUISER": "SLACK_CRUISER",
+    "SNAIL_MEASURING_TAPE": "SNAIL_MEASURING_TAPE",
+    "SORTING_BUS": "SORTING_BUS",
+    "SORTING_TRAIN": "SORTING_TRAIN",
+    "SPEED_BOAT": "SPEED_BOAT",
+    "STACKING_BEAR": "STACKING_BEAR",
+    "STACKING_BEAR_V04KKgGBn2A": "STACKING_BEAR_V04KKgGBn2A",
+    "STACKING_RING": "STACKING_RING",
+    "STEAK_SET": "STEAK_SET",
+    "SUPERSTAR_CLR": "SUPERSTAR_CLR",
+    "Saccharomyces_Boulardii_MOS_Value_Size": "Saccharomyces_Boulardii_MOS_Value_Size",
+    "Samoa_onepiece": "Samoa_onepiece",
+    "Samsung_CLTC406S_Toner_Cartridge_Cyan_1pack": "Samsung_CLTC406S_Toner_Cartridge_Cyan_1pack",
+    "Santa_Cruz_Mens": "Santa_Cruz_Mens",
+    "Santa_Cruz_Mens_G7kQXK7cIky": "Santa_Cruz_Mens_G7kQXK7cIky",
+    "Santa_Cruz_Mens_YmsMDkFf11Z": "Santa_Cruz_Mens_YmsMDkFf11Z",
+    "Santa_Cruz_Mens_umxTczr1Ygg": "Santa_Cruz_Mens_umxTczr1Ygg",
+    "Santa_Cruz_Mens_vnbiTDDt5xH": "Santa_Cruz_Mens_vnbiTDDt5xH",
+    "Sapota_Threshold_4_Ceramic_Round_Planter_Red": "Sapota_Threshold_4_Ceramic_Round_Planter_Red",
+    "Schleich_African_Black_Rhino": "Schleich_African_Black_Rhino",
+    "Schleich_Allosaurus": "Schleich_Allosaurus",
+    "Schleich_Bald_Eagle": "bald eagle toy",
+    "Schleich_Hereford_Bull": "brown bull",
+    "Schleich_Lion_Action_Figure": "Schleich_Lion_Action_Figure",
+    "Schleich_S_Bayala_Unicorn_70432": "Schleich_S_Bayala_Unicorn_70432",
+    "Schleich_Spinosaurus_Action_Figure": "Schleich_Spinosaurus_Action_Figure",
+    "Schleich_Therizinosaurus_ln9cruulPqc": "Schleich_Therizinosaurus_ln9cruulPqc",
+    "Sea_to_Summit_Xl_Bowl": "Sea_to_Summit_Xl_Bowl",
+    "Seagate_1TB_Backup_Plus_portable_drive_Blue": "Seagate_1TB_Backup_Plus_portable_drive_Blue",
+    "Seagate_1TB_Backup_Plus_portable_drive_Silver": "Seagate_1TB_Backup_Plus_portable_drive_Silver",
+    "Seagate_1TB_Backup_Plus_portable_drive_for_Mac": "Seagate_1TB_Backup_Plus_portable_drive_for_Mac",
+    "Seagate_1TB_Wireless_Plus_mobile_device_storage": "Seagate_1TB_Wireless_Plus_mobile_device_storage",
+    "Seagate_3TB_Central_shared_storage": "Seagate_3TB_Central_shared_storage",
+    "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002": "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002",
+    "Shark": "Shark",
+    "Shaxon_100_Molded_Category_6_RJ45RJ45_Shielded_Patch_Cord_White": "Shaxon_100_Molded_Category_6_RJ45RJ45_Shielded_Patch_Cord_White",
+    "Shurtape_30_Day_Removal_UV_Delct_15": "Shurtape_30_Day_Removal_UV_Delct_15",
+    "Shurtape_Gaffers_Tape_Silver_2_x_60_yd": "Shurtape_Gaffers_Tape_Silver_2_x_60_yd",
+    "Shurtape_Tape_Purple_CP28": "Shurtape_Tape_Purple_CP28",
+    "Sienna_Brown_Croc_Tieks_Patent_Leather_Crocodile_Print_Ballet_Flats": "Sienna_Brown_Croc_Tieks_Patent_Leather_Crocodile_Print_Ballet_Flats",
+    "Simon_Swipe_Game": "Simon_Swipe_Game",
+    "Sleep_Optimizer": "Sleep_Optimizer",
+    "Smith_Hawken_Woven_BasketTray_Organizer_with_3_Compartments_95_x_9_x_13": "Smith_Hawken_Woven_BasketTray_Organizer_with_3_Compartments_95_x_9_x_13",
+    "Snack_Catcher_Snack_Dispenser": "Snack_Catcher_Snack_Dispenser",
+    "Sonicare_2_Series_Toothbrush_Plaque_Control": "Sonicare_2_Series_Toothbrush_Plaque_Control",
+    "Sonny_School_Bus": "school bus toy",
+    "Sony_Acid_Music_Studio": "Sony_Acid_Music_Studio",
+    "Sony_Downloadable_Loops": "Sony_Downloadable_Loops",
+    "Sootheze_Cold_Therapy_Elephant": "grey elephant toy",
+    "Sootheze_Toasty_Orca": "Sootheze_Toasty_Orca",
+    "Sorry_Sliders_Board_Game": "Sorry_Sliders_Board_Game",
+    "Spectrum_Wall_Mount": "Spectrum_Wall_Mount",
+    "Sperry_TopSider_pSUFPWQXPp3": "Sperry_TopSider_pSUFPWQXPp3",
+    "Sperry_TopSider_tNB9t6YBUf3": "Sperry_TopSider_tNB9t6YBUf3",
+    "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP": "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP",
+    "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW": "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW",
+    "Spritz_Easter_Basket_Plastic_Teal": "Spritz_Easter_Basket_Plastic_Teal",
+    "Squirrel": "Squirrel",
+    "Squirt_Strain_Fruit_Basket": "Squirt_Strain_Fruit_Basket",
+    "Squirtin_Barnyard_Friends_4pk": "Squirtin_Barnyard_Friends_4pk",
+    "Star_Wars_Rogue_Squadron_Nintendo_64": "Star_Wars_Rogue_Squadron_Nintendo_64",
+    "Starstruck_Tieks_Glittery_Gold_Italian_Leather_Ballet_Flats": "Starstruck_Tieks_Glittery_Gold_Italian_Leather_Ballet_Flats",
+    "Sterilite_Caddy_Blue_Sky_17_58_x_12_58_x_9_14": "Sterilite_Caddy_Blue_Sky_17_58_x_12_58_x_9_14",
+    "Super_Mario_3D_World_Deluxe_Set": "Super_Mario_3D_World_Deluxe_Set",
+    "Super_Mario_3D_World_Deluxe_Set_yThuvW9vZed": "Super_Mario_3D_World_Deluxe_Set_yThuvW9vZed",
+    "Super_Mario_3D_World_Wii_U_Game": "Super_Mario_3D_World_Wii_U_Game",
+    "Super_Mario_Kart_Super_Nintendo_Entertainment_System": "Super_Mario_Kart_Super_Nintendo_Entertainment_System",
+    "Superman_Battle_of_Smallville": "Superman_Battle_of_Smallville",
+    "Supernatural_Ouija_Board_Game": "Supernatural_Ouija_Board_Game",
+    "Sushi_Mat": "Sushi_Mat",
+    "Swiss_Miss_Hot_Cocoa_KCups_Milk_Chocolate_12_count": "Swiss_Miss_Hot_Cocoa_KCups_Milk_Chocolate_12_count",
+    "TABLEWARE_SET": "TABLEWARE_SET",
+    "TABLEWARE_SET_5CHkPjjxVpp": "TABLEWARE_SET_5CHkPjjxVpp",
+    "TABLEWARE_SET_5ww1UFLuCJG": "TABLEWARE_SET_5ww1UFLuCJG",
+    "TEA_SET": "TEA_SET",
+    "TERREX_FAST_R": "TERREX_FAST_R",
+    "TERREX_FAST_X_GTX": "TERREX_FAST_X_GTX",
+    "TOOL_BELT": "TOOL_BELT",
+    "TOP_TEN_HI": "TOP_TEN_HI",
+    "TOP_TEN_HI_60KlbRbdoJA": "TOP_TEN_HI_60KlbRbdoJA",
+    "TOWER_TUMBLING": "TOWER_TUMBLING",
+    "TROCHILUS_BOOST": "TROCHILUS_BOOST",
+    "TURBOPROP_AIRPLANE_WITH_PILOT": "TURBOPROP_AIRPLANE_WITH_PILOT",
+    "TWISTED_PUZZLE": "TWISTED_PUZZLE",
+    "TWISTED_PUZZLE_twb4AyFtu8Q": "TWISTED_PUZZLE_twb4AyFtu8Q",
+    "TWIST_SHAPE": "TWIST_SHAPE",
+    "TZX_Runner": "TZX_Runner",
+    "Tag_Dishtowel_18_x_26": "Tag_Dishtowel_18_x_26",
+    "Tag_Dishtowel_Basket_Weave_Red_18_x_26": "Tag_Dishtowel_Basket_Weave_Red_18_x_26",
+    "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26": "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26",
+    "Tag_Dishtowel_Green": "Tag_Dishtowel_Green",
+    "Tag_Dishtowel_Waffle_Gray_Checks_18_x_26": "Tag_Dishtowel_Waffle_Gray_Checks_18_x_26",
+    "Target_Basket_Medium": "Target_Basket_Medium",
+    "Teenage_Mutant_Ninja_Turtles_Rahzar_Action_Figure": "Teenage_Mutant_Ninja_Turtles_Rahzar_Action_Figure",
+    "Tena_Pads_Heavy_Long_42_pads": "Tena_Pads_Heavy_Long_42_pads",
+    "Tetris_Link_Game": "Tetris_Link_Game",
+    "The_Coffee_Bean_Tea_Leaf_KCup_Packs_Jasmine_Green_Tea_16_count": "The_Coffee_Bean_Tea_Leaf_KCup_Packs_Jasmine_Green_Tea_16_count",
+    "The_Scooper_Hooper": "The_Scooper_Hooper",
+    "Theanine": "Theanine",
+    "Thomas_Friends_Woodan_Railway_Henry": "Thomas_Friends_Woodan_Railway_Henry",
+    "Thomas_Friends_Wooden_Railway_Ascending_Track_Riser_Pack": "Thomas_Friends_Wooden_Railway_Ascending_Track_Riser_Pack",
+    "Thomas_Friends_Wooden_Railway_Deluxe_Track_Accessory_Pack": "Thomas_Friends_Wooden_Railway_Deluxe_Track_Accessory_Pack",
+    "Thomas_Friends_Wooden_Railway_Porter_5JzRhMm3a9o": "Thomas_Friends_Wooden_Railway_Porter_5JzRhMm3a9o",
+    "Thomas_Friends_Wooden_Railway_Talking_Thomas_z7yi7UFHJRj": "Thomas_Friends_Wooden_Railway_Talking_Thomas_z7yi7UFHJRj",
+    "Threshold_Bamboo_Ceramic_Soap_Dish": "Threshold_Bamboo_Ceramic_Soap_Dish",
+    "Threshold_Basket_Natural_Finish_Fabric_Liner_Small": "fabric basket",
+    "Threshold_Bead_Cereal_Bowl_White": "Threshold_Bead_Cereal_Bowl_White",
+    "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring": "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring",
+    "Threshold_Dinner_Plate_Square_Rim_White_Porcelain": "Threshold_Dinner_Plate_Square_Rim_White_Porcelain",
+    "Threshold_Hand_Towel_Blue_Medallion_16_x_27": "Threshold_Hand_Towel_Blue_Medallion_16_x_27",
+    "Threshold_Performance_Bath_Sheet_Sandoval_Blue_33_x_63": "Threshold_Performance_Bath_Sheet_Sandoval_Blue_33_x_63",
+    "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White": "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White",
+    "Threshold_Porcelain_Pitcher_White": "Threshold_Porcelain_Pitcher_White",
+    "Threshold_Porcelain_Serving_Bowl_Coupe_White": "Threshold_Porcelain_Serving_Bowl_Coupe_White",
+    "Threshold_Porcelain_Spoon_Rest_White": "Threshold_Porcelain_Spoon_Rest_White",
+    "Threshold_Porcelain_Teapot_White": "white porcelain teapot",
+    "Threshold_Ramekin_White_Porcelain": "Threshold_Ramekin_White_Porcelain",
+    "Threshold_Salad_Plate_Square_Rim_Porcelain": "Threshold_Salad_Plate_Square_Rim_Porcelain",
+    "Threshold_Textured_Damask_Bath_Towel_Pink": "pink damask bath towel",
+    "Threshold_Tray_Rectangle_Porcelain": "Threshold_Tray_Rectangle_Porcelain",
+    "Tiek_Blue_Patent_Tieks_Italian_Leather_Ballet_Flats": "Tiek_Blue_Patent_Tieks_Italian_Leather_Ballet_Flats",
+    "Tieks_Ballet_Flats_Diamond_White_Croc": "Tieks_Ballet_Flats_Diamond_White_Croc",
+    "Tieks_Ballet_Flats_Electric_Snake": "Tieks_Ballet_Flats_Electric_Snake",
+    "Timberland_Mens_Classic_2Eye_Boat_Shoe": "Timberland_Mens_Classic_2Eye_Boat_Shoe",
+    "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_Oxford": "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_Oxford",
+    "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_SlipOn": "Timberland_Mens_Earthkeepers_Casco_Bay_Canvas_SlipOn",
+    "Timberland_Mens_Earthkeepers_Casco_Bay_Suede_1Eye": "Timberland_Mens_Earthkeepers_Casco_Bay_Suede_1Eye",
+    "Timberland_Mens_Earthkeepers_Heritage_2Eye_Boat_Shoe": "Timberland_Mens_Earthkeepers_Heritage_2Eye_Boat_Shoe",
+    "Timberland_Mens_Earthkeepers_Newmarket_6Inch_Cupsole_Boot": "Timberland_Mens_Earthkeepers_Newmarket_6Inch_Cupsole_Boot",
+    "Timberland_Mens_Earthkeepers_Stormbuck_Chukka": "Timberland_Mens_Earthkeepers_Stormbuck_Chukka",
+    "Timberland_Mens_Earthkeepers_Stormbuck_Lite_Plain_Toe_Oxford": "Timberland_Mens_Earthkeepers_Stormbuck_Lite_Plain_Toe_Oxford",
+    "Timberland_Mens_Earthkeepers_Stormbuck_Plain_Toe_Oxford": "Timberland_Mens_Earthkeepers_Stormbuck_Plain_Toe_Oxford",
+    "Timberland_Womens_Classic_Amherst_2Eye_Boat_Shoe": "Timberland_Womens_Classic_Amherst_2Eye_Boat_Shoe",
+    "Timberland_Womens_Earthkeepers_Classic_Unlined_Boat_Shoe": "Timberland_Womens_Earthkeepers_Classic_Unlined_Boat_Shoe",
+    "Timberland_Womens_Waterproof_Nellie_Chukka_Double": "Timberland_Womens_Waterproof_Nellie_Chukka_Double",
+    "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total": "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total",
+    "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total": "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total",
+    "Tory_Burch_Kaitlin_Ballet_Mestico_in_BlackGold": "Tory_Burch_Kaitlin_Ballet_Mestico_in_BlackGold",
+    "Tory_Burch_Kiernan_Riding_Boot": "Tory_Burch_Kiernan_Riding_Boot",
+    "Tory_Burch_Reva_Metal_Logo_Litus_Snake_Print_in_dark_BranchGold": "Tory_Burch_Reva_Metal_Logo_Litus_Snake_Print_in_dark_BranchGold",
+    "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel": "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel",
+    "Toys_R_Us_Treat_Dispenser_Smart_Puzzle_Foobler": "Toys_R_Us_Treat_Dispenser_Smart_Puzzle_Foobler",
+    "Toysmith_Windem_Up_Flippin_Animals_Dog": "white animal dog toy",
+    "Transformers_Age_of_Extinction_Mega_1Step_Bumblebee_Figure": "Transformers_Age_of_Extinction_Mega_1Step_Bumblebee_Figure",
+    "Transformers_Age_of_Extinction_Stomp_and_Chomp_Grimlock_Figure": "Transformers_Age_of_Extinction_Stomp_and_Chomp_Grimlock_Figure",
+    "Travel_Mate_P_series_Notebook": "black laptop",
+    "Travel_Smart_Neck_Rest_Inflatable": "Travel_Smart_Neck_Rest_Inflatable",
+    "TriStar_Products_PPC_Power_Pressure_Cooker_XL_in_Black": "black power pressure cooker",
+    "Tune_Belt_Sport_Armband_For_Samsung_Galaxy_S3": "Tune_Belt_Sport_Armband_For_Samsung_Galaxy_S3",
+    "Twinlab_100_Whey_Protein_Fuel_Chocolate": "Twinlab_100_Whey_Protein_Fuel_Chocolate",
+    "Twinlab_100_Whey_Protein_Fuel_Cookies_and_Cream": "Twinlab_100_Whey_Protein_Fuel_Cookies_and_Cream",
+    "Twinlab_100_Whey_Protein_Fuel_Vanilla": "Twinlab_100_Whey_Protein_Fuel_Vanilla",
+    "Twinlab_Nitric_Fuel": "Twinlab_Nitric_Fuel",
+    "Twinlab_Premium_Creatine_Fuel_Powder": "Twinlab_Premium_Creatine_Fuel_Powder",
+    "UGG_Bailey_Bow_Womens_Clogs_Black_7": "UGG_Bailey_Bow_Womens_Clogs_Black_7",
+    "UGG_Bailey_Button_Triplet_Womens_Boots_Black_7": "UGG_Bailey_Button_Triplet_Womens_Boots_Black_7",
+    "UGG_Bailey_Button_Womens_Boots_Black_7": "UGG_Bailey_Button_Womens_Boots_Black_7",
+    "UGG_Cambridge_Womens_Black_7": "UGG_Cambridge_Womens_Black_7",
+    "UGG_Classic_Tall_Womens_Boots_Chestnut_7": "UGG_Classic_Tall_Womens_Boots_Chestnut_7",
+    "UGG_Classic_Tall_Womens_Boots_Grey_7": "UGG_Classic_Tall_Womens_Boots_Grey_7",
+    "UGG_Jena_Womens_Java_7": "UGG_Jena_Womens_Java_7",
+    "US_Army_Stash_Lunch_Bag": "US_Army_Stash_Lunch_Bag",
+    "U_By_Kotex_Cleanwear_Heavy_Flow_Pads_32_Ct": "U_By_Kotex_Cleanwear_Heavy_Flow_Pads_32_Ct",
+    "U_By_Kotex_Sleek_Regular_Unscented_Tampons_36_Ct_Box": "U_By_Kotex_Sleek_Regular_Unscented_Tampons_36_Ct_Box",
+    "Ubisoft_RockSmith_Real_Tone_Cable_Xbox_360": "Ubisoft_RockSmith_Real_Tone_Cable_Xbox_360",
+    "Ultra_JarroDophilus": "Ultra_JarroDophilus",
+    "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats": "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats",
+    "Utana_5_Porcelain_Ramekin_Large": "white ramekin porcelain",
+    "VANS_FIRE_ROASTED_VEGGIE_CRACKERS_GLUTEN_FREE": "VANS_FIRE_ROASTED_VEGGIE_CRACKERS_GLUTEN_FREE",
+    "VEGETABLE_GARDEN": "VEGETABLE_GARDEN",
+    "Vans_Cereal_Honey_Nut_Crunch_11_oz_box": "Vans_Cereal_Honey_Nut_Crunch_11_oz_box",
+    "Victor_Reversible_Bookend": "Victor_Reversible_Bookend",
+    "Vtech_Cruise_Learn_Car_25_Years": "Vtech_Cruise_Learn_Car_25_Years",
+    "Vtech_Roll_Learn_Turtle": "green turtle toy",
+    "Vtech_Stack_Sing_Rings_636_Months": "Vtech_Stack_Sing_Rings_636_Months",
+    "WATER_LANDING_NET": "WATER_LANDING_NET",
+    "WHALE_WHISTLE_6PCS_SET": "WHALE_WHISTLE_6PCS_SET",
+    "W_Lou_z0dkC78niiZ": "W_Lou_z0dkC78niiZ",
+    "Weisshai_Great_White_Shark": "great white shark model",
+    "Weston_No_22_Cajun_Jerky_Tonic_12_fl_oz_nLj64ZnGwDh": "Weston_No_22_Cajun_Jerky_Tonic_12_fl_oz_nLj64ZnGwDh",
+    "Weston_No_33_Signature_Sausage_Tonic_12_fl_oz": "Weston_No_33_Signature_Sausage_Tonic_12_fl_oz",
+    "Whey_Protein_3_Flavor_Variety_Pack_12_Packets": "Whey_Protein_3_Flavor_Variety_Pack_12_Packets",
+    "Whey_Protein_Chocolate_12_Packets": "Whey_Protein_Chocolate_12_Packets",
+    "Whey_Protein_Vanilla": "Whey_Protein_Vanilla",
+    "Whey_Protein_Vanilla_12_Packets": "Whey_Protein_Vanilla_12_Packets",
+    "White_Rose_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes": "White_Rose_Tieks_Leather_Ballet_Flats_with_Floral_Rosettes",
+    "Wild_Copper_Tieks_Metallic_Italian_Leather_Ballet_Flats": "Wild_Copper_Tieks_Metallic_Italian_Leather_Ballet_Flats",
+    "Wilton_Easy_Layers_Cake_Pan_Set": "Wilton_Easy_Layers_Cake_Pan_Set",
+    "Wilton_Pearlized_Sugar_Sprinkles_525_oz_Gold": "Wilton_Pearlized_Sugar_Sprinkles_525_oz_Gold",
+    "Wilton_PreCut_Parchment_Sheets_10_x_15_24_sheets": "Wilton_PreCut_Parchment_Sheets_10_x_15_24_sheets",
+    "Winning_Moves_1180_Aggravation_Board_Game": "Winning_Moves_1180_Aggravation_Board_Game",
+    "Wishbone_Pencil_Case": "Wishbone_Pencil_Case",
+    "Womens_Angelfish_Boat_Shoe_in_Linen_Leopard_Sequin_NJDwosWNeZz": "Womens_Angelfish_Boat_Shoe_in_Linen_Leopard_Sequin_NJDwosWNeZz",
+    "Womens_Angelfish_Boat_Shoe_in_Linen_Oat": "Womens_Angelfish_Boat_Shoe_in_Linen_Oat",
+    "Womens_Audrey_Slip_On_Boat_Shoe_in_Graphite_Nubuck_xWVkCJ5vxZe": "Womens_Audrey_Slip_On_Boat_Shoe_in_Graphite_Nubuck_xWVkCJ5vxZe",
+    "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather",
+    "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_48Nh7VuMwW6": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_48Nh7VuMwW6",
+    "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_cJSCWiH7QmB": "Womens_Authentic_Original_Boat_Shoe_in_Classic_Brown_Leather_cJSCWiH7QmB",
+    "Womens_Authentic_Original_Boat_Shoe_in_Navy_Deerskin_50lWJaLWG8R": "Womens_Authentic_Original_Boat_Shoe_in_Navy_Deerskin_50lWJaLWG8R",
+    "Womens_Betty_Chukka_Boot_in_Grey_Jersey_Sequin": "Womens_Betty_Chukka_Boot_in_Grey_Jersey_Sequin",
+    "Womens_Betty_Chukka_Boot_in_Navy_Jersey_Sequin_y0SsHk7dKUX": "Womens_Betty_Chukka_Boot_in_Navy_Jersey_Sequin_y0SsHk7dKUX",
+    "Womens_Betty_Chukka_Boot_in_Navy_aEE8OqvMII4": "Womens_Betty_Chukka_Boot_in_Navy_aEE8OqvMII4",
+    "Womens_Betty_Chukka_Boot_in_Salt_Washed_Red_AL2YrOt9CRy": "Womens_Betty_Chukka_Boot_in_Salt_Washed_Red_AL2YrOt9CRy",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_JJ2pfEHTZG7": "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_JJ2pfEHTZG7",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_i1TgjjO0AKY": "Womens_Bluefish_2Eye_Boat_Shoe_in_Brown_Deerskin_i1TgjjO0AKY",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_kqi81aojcOR": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_kqi81aojcOR",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_w34KNQ41csH": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Natural_Sparkle_Suede_w34KNQ41csH",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_IbrSyJdpT3h": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_IbrSyJdpT3h",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_niKJKeWsmxY": "Womens_Bluefish_2Eye_Boat_Shoe_in_Linen_Oat_niKJKeWsmxY",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_Tan": "Womens_Bluefish_2Eye_Boat_Shoe_in_Tan",
+    "Womens_Bluefish_2Eye_Boat_Shoe_in_White_Tumbled_YG44xIePRHw": "Womens_Bluefish_2Eye_Boat_Shoe_in_White_Tumbled_YG44xIePRHw",
+    "Womens_Canvas_Bahama_in_Black": "Womens_Canvas_Bahama_in_Black",
+    "Womens_Canvas_Bahama_in_Black_vnJULsDVyq5": "Womens_Canvas_Bahama_in_Black_vnJULsDVyq5",
+    "Womens_Canvas_Bahama_in_White_4UyOhP6rYGO": "white canvas shoe",
+    "Womens_Canvas_Bahama_in_White_UfZPHGQpvz0": "Womens_Canvas_Bahama_in_White_UfZPHGQpvz0",
+    "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_8LigQYwf4gr": "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_8LigQYwf4gr",
+    "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_cZR022qFI4k": "Womens_Cloud_Logo_Authentic_Original_Boat_Shoe_in_Black_Supersoft_cZR022qFI4k",
+    "Womens_Hikerfish_Boot_in_Black_Leopard_bVSNY1Le1sm": "Womens_Hikerfish_Boot_in_Black_Leopard_bVSNY1Le1sm",
+    "Womens_Hikerfish_Boot_in_Black_Leopard_ridcCWsv8rW": "Womens_Hikerfish_Boot_in_Black_Leopard_ridcCWsv8rW",
+    "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_QktIyAkonrU": "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_QktIyAkonrU",
+    "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_imlP8VkwqIH": "Womens_Hikerfish_Boot_in_Linen_Leather_Sparkle_Suede_imlP8VkwqIH",
+    "Womens_Multi_13": "Womens_Multi_13",
+    "Womens_Sequin_Bahama_in_White_Sequin_V9K1hf24Oxe": "Womens_Sequin_Bahama_in_White_Sequin_V9K1hf24Oxe",
+    "Womens_Sequin_Bahama_in_White_Sequin_XoR8xTlxj1g": "Womens_Sequin_Bahama_in_White_Sequin_XoR8xTlxj1g",
+    "Womens_Sequin_Bahama_in_White_Sequin_yGVsSA4tOwJ": "Womens_Sequin_Bahama_in_White_Sequin_yGVsSA4tOwJ",
+    "Womens_Sparkle_Suede_Angelfish_in_Grey_Sparkle_Suede_Silver": "Womens_Sparkle_Suede_Angelfish_in_Grey_Sparkle_Suede_Silver",
+    "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_tYrIBLMhSTN": "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_tYrIBLMhSTN",
+    "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_x9rclU7EJXx": "Womens_Sparkle_Suede_Bahama_in_Silver_Sparkle_Suede_Grey_Patent_x9rclU7EJXx",
+    "Womens_Suede_Bahama_in_Graphite_Suede_cUAjIMhWSO9": "Womens_Suede_Bahama_in_Graphite_Suede_cUAjIMhWSO9",
+    "Womens_Suede_Bahama_in_Graphite_Suede_p1KUwoWbw7R": "Womens_Suede_Bahama_in_Graphite_Suede_p1KUwoWbw7R",
+    "Womens_Suede_Bahama_in_Graphite_Suede_t22AJSRjBOX": "Womens_Suede_Bahama_in_Graphite_Suede_t22AJSRjBOX",
+    "Womens_Teva_Capistrano_Bootie": "Womens_Teva_Capistrano_Bootie",
+    "Womens_Teva_Capistrano_Bootie_ldjRT9yZ5Ht": "Womens_Teva_Capistrano_Bootie_ldjRT9yZ5Ht",
+    "Wooden_ABC_123_Blocks_50_pack": "Wooden_ABC_123_Blocks_50_pack",
+    "Wrigley_Orbit_Mint_Variety_18_Count": "Wrigley_Orbit_Mint_Variety_18_Count",
+    "Xyli_Pure_Xylitol": "Xyli_Pure_Xylitol",
+    "YumYum_D3_Liquid": "YumYum_D3_Liquid",
+    "ZX700_lYiwcTIekXk": "ZX700_lYiwcTIekXk",
+    "ZX700_mf9Pc06uL06": "ZX700_mf9Pc06uL06",
+    "ZX700_mzGbdP3u6JB": "ZX700_mzGbdP3u6JB",
+    "ZigKick_Hoops": "ZigKick_Hoops",
+    "adiZero_Slide_2_SC": "adiZero_Slide_2_SC",
+    "adistar_boost_m": "black sneaker",
+    "adizero_5Tool_25": "adizero_5Tool_25",
+    "adizero_F50_TRX_FG_LEA": "adizero_F50_TRX_FG_LEA"
+}

eq-kubric/3d_data/GSO_dict_filtered.json

@@ -0,0 +1,583 @@
+{
+  "purple-white lamp": [
+    "3D_Dollhouse_Lamp"
+  ],
+  "green wooden refrigerator": [
+    "3D_Dollhouse_Refrigerator"
+  ],
+  "purple wooden sofa": [
+    "3D_Dollhouse_Sofa"
+  ],
+  "purple wooden table": [
+    "3D_Dollhouse_TablePurple"
+  ],
+  "light-gray tape": [
+    "3M_Antislip_Surfacing_Light_Duty_White"
+  ],
+  "green tape": [
+    "3M_Vinyl_Tape_Green_1_x_36_yd"
+  ],
+  "green shiny bowl": [
+    "45oz_RAMEKIN_ASST_DEEP_COLORS"
+  ],
+  "blue medicine bottle": [
+    "5_HTP"
+  ],
+  "red coffee mug": [
+    "ACE_Coffee_Mug_Kristen_16_oz_cup"
+  ],
+  "blue sneakers": [
+    "AMBERLIGHT_UP_W"
+  ],
+  "white-black shoes": [
+    "ASICS_GEL1140V_WhiteBlackSilver",
+    "ASICS_GEL1140V_WhiteRoyalSilver"
+  ],
+  "white-pink shoes": [
+    "ASICS_GELAce_Pro_Pearl_WhitePink"
+  ],
+  "black-orange shoes": [
+    "ASICS_GELBlur33_20_GS_BlackWhiteSafety_Orange"
+  ],
+  "yellow-orange shoes": [
+    "ASICS_GELBlur33_20_GS_Flash_YellowHot_PunchSilver"
+  ],
+  "blue-white shoes": [
+    "ASICS_GELChallenger_9_Royal_BlueWhiteBlack"
+  ],
+  "red toy airplane": [
+    "Air_Hogs_Wind_Flyers_Set_Airplane_Red"
+  ],
+  "yellow medicine bottle": [
+    "AllergenFree_JarroDophilus"
+  ],
+  "silver android figure": [
+    "Android_Figure_Chrome"
+  ],
+  "orange android figure": [
+    "Android_Figure_Orange"
+  ],
+  "green-yellow boardgame": [
+    "Apples_to_Apples_Kids_Edition"
+  ],
+  "steel milk frother": [
+    "Aroma_Stainless_Steel_Milk_Frother_2_Cup"
+  ],
+  "green hulk toy fists": [
+    "Avengers_Gamma_Green_Smash_Fists"
+  ],
+  "white porcelain utensil holder": [
+    "BIA_Cordon_Bleu_White_Porcelain_Utensil_Holder_900028"
+  ],
+  "white porcelain ramekin": [
+    "BIA_Porcelain_Ramekin_With_Glazed_Rim_35_45_oz_cup",
+    "Threshold_Ramekin_White_Porcelain",
+    "Utana_5_Porcelain_Ramekin_Large"
+  ],
+  "stack of colorful cups": [
+    "Baby_Elements_Stacking_Cups"
+  ],
+  "black DVD": [
+    "Beyonc_Life_is_But_a_Dream_DVD"
+  ],
+  "purple medicine bottle": [
+    "Bifidus_Balance_FOS"
+  ],
+  "green-purple pencil case": [
+    "Big_Dot_Aqua_Pencil_Case"
+  ],
+  "pink-black pencil case": [
+    "Big_Dot_Pink_Pencil_Case"
+  ],
+  "purple sponge": [
+    "Big_O_Sponges_Assorted_Cellulose_12_pack"
+  ],
+  "black metal coffee maker": [
+    "Black_Decker_CM2035B_12Cup_Thermal_Coffeemaker"
+  ],
+  "stainless steel toaster": [
+    "Black_Decker_Stainless_Steel_Toaster_4_Slice"
+  ],
+  "Nintendo gaming console": [
+    "BlueBlack_Nintendo_3DSXL"
+  ],
+  "white DVD": [
+    "Blue_Jasmine_Includes_Digital_Copy_UltraViolet_DVD"
+  ],
+  "red bowl": [
+    "Bradshaw_International_11642_7_Qt_MP_Plastic_Bowl"
+  ],
+  "toy horse": [
+    "Breyer_Horse_Of_The_Year_2015"
+  ],
+  "CARSII": [
+    "CARSII"
+  ],
+  "black toy train loaded with cars": [
+    "CAR_CARRIER_TRAIN"
+  ],
+  "black ballet shoe": [
+    "California_Navy_Tieks_Italian_Leather_Ballet_Flats"
+  ],
+  "white bowl": [
+    "Calphalon_Kitchen_Essentials_12_Cast_Iron_Fry_Pan_Black",
+    "Threshold_Bead_Cereal_Bowl_White",
+    "Threshold_Porcelain_Serving_Bowl_Coupe_White"
+  ],
+  "round cake pan": [
+    "Chef_Style_Round_Cake_Pan_9_inch_pan"
+  ],
+  "black frypan": [
+    "Chefmate_8_Frypan"
+  ],
+  "golden-black high heel": [
+    "Chelsea_BlkHeelPMP_DwxLtZNxLZZ"
+  ],
+  "red high heel": [
+    "Chelsea_lo_fl_rdheel_nQ0LPNF1oMw"
+  ],
+  "pink high heel": [
+    "Chelsea_lo_fl_rdheel_zAQrnhlEfw8"
+  ],
+  "white drug bottle": [
+    "CoQ10"
+  ],
+  "toilet paper": [
+    "Cole_Hardware_Antislip_Surfacing_Material_White"
+  ],
+  "yellow round bowl": [
+    "Cole_Hardware_Bowl_Scirocco_YellowBlue"
+  ],
+  "brown bowl": [
+    "Cole_Hardware_Deep_Bowl_Good_Earth_1075"
+  ],
+  "blue-white dish towel": [
+    "Cole_Hardware_Dishtowel_BlueWhite"
+  ],
+  "red towel": [
+    "Cole_Hardware_Dishtowel_Red"
+  ],
+  "red-white striped towel": [
+    "Cole_Hardware_Dishtowel_Stripe",
+    "Tag_Dishtowel_Basket_Weave_Red_18_x_26"
+  ],
+  "red flower pot": [
+    "Cole_Hardware_Electric_Pot_Assortment_55",
+    "Sapota_Threshold_4_Ceramic_Round_Planter_Red"
+  ],
+  "orange flower pot": [
+    "Cole_Hardware_Electric_Pot_Cabana_55",
+    "Cole_Hardware_Orchid_Pot_85"
+  ],
+  "gray flower pot": [
+    "Cole_Hardware_Flower_Pot_1025"
+  ],
+  "black and yellow hammer": [
+    "Cole_Hardware_Hammer_Black"
+  ],
+  "brown round plate": [
+    "Cole_Hardware_Plant_Saucer_Brown_125",
+    "Cole_Hardware_Plant_Saucer_Glazed_9"
+  ],
+  "pink saucer": [
+    "Cole_Hardware_Saucer_Electric"
+  ],
+  "school bell": [
+    "Cole_Hardware_School_Bell_Solid_Brass_38"
+  ],
+  "leather boot": [
+    "Colton_Wntr_Chukka_y4jO0I8JQFW"
+  ],
+  "rectangular blue casserol dish": [
+    "Corningware_CW_by_Corningware_3qt_Oblong_Casserole_Dish_Blue"
+  ],
+  "screwdriver": [
+    "Craftsman_Grip_Screwdriver_Phillips_Cushion"
+  ],
+  "vintage metal alarm clock": [
+    "Crosley_Alarm_Clock_Vintage_Metal"
+  ],
+  "black net basket": [
+    "Curver_Storage_Bin_Black_Small"
+  ],
+  "black hat": [
+    "DPC_Handmade_Hat_Brown",
+    "Retail_Leadership_Summit_tQFCizMt6g0"
+  ],
+  "brown straw hat": [
+    "DPC_tropical_Trends_Hat"
+  ],
+  "red scissors": [
+    "Diamond_Visions_Scissors_Red"
+  ],
+  "toy T-Rex": [
+    "Dino_3"
+  ],
+  "toy triceratops": [
+    "Dino_4"
+  ],
+  "toy dicynodont dinosaur": [
+    "Dino_5"
+  ],
+  "white bowl with purple pattern": [
+    "Dixie_10_ounce_Bowls_35_ct"
+  ],
+  "Dog": [
+    "Dog"
+  ],
+  "white book": [
+    "Eat_to_Live_The_Amazing_NutrientRich_Program_for_Fast_and_Sustained_Weight_Loss_Revised_Edition_Book"
+  ],
+  "turquoise flower pot": [
+    "Ecoforms_Garden_Pot_GP16ATurquois"
+  ],
+  "green flower pot": [
+    "Ecoforms_Plant_Container_12_Pot_Nova"
+  ],
+  "red plant container": [
+    "Ecoforms_Plant_Container_QP6CORAL"
+  ],
+  "brown flower pot": [
+    "Ecoforms_Plant_Container_URN_NAT"
+  ],
+  "dark brown saucer": [
+    "Ecoforms_Plant_Saucer_S20MOCHA"
+  ],
+  "gray elephant toy": [
+    "Elephant"
+  ],
+  "blue cooler bag": [
+    "Embark_Lunch_Cooler_Blue"
+  ],
+  "blue-red soccer cleats": [
+    "F10_TRX_FG_ssscuo9tGxb"
+  ],
+  "yellow soccer cleats": [
+    "F5_TRX_FG"
+  ],
+  "FemDophilus": [
+    "FemDophilus"
+  ],
+  "garden swing": [
+    "GARDEN_SWING"
+  ],
+  "wooden doll": [
+    "GRANDFATHER_DOLL",
+    "GRANDMOTHER"
+  ],
+  "composite cable": [
+    "GoPro_HERO3_Composite_Cable"
+  ],
+  "green android mascot": [
+    "Great_Dinos_Triceratops_Toy"
+  ],
+  "blue dog dish": [
+    "Grreat_Choice_Dog_Double_Dish_Plastic_Blue"
+  ],
+  "red flashlight": [
+    "HeavyDuty_Flashlight"
+  ],
+  "black basket": [
+    "Hefty_Waste_Basket_Decorative_Bronze_85_liter"
+  ],
+  "brown leather boot": [
+    "Hilary",
+    "MARTIN_WEDGE_LACE_BOOT",
+    "Rayna_BootieWP",
+    "Sperry_TopSider_pSUFPWQXPp3",
+    "Sperry_TopSider_tNB9t6YBUf3",
+    "Tory_Burch_Sabe_65mm_Bootie_Split_Suede_in_Caramel",
+    "W_Lou_z0dkC78niiZ"
+  ],
+  "linen cloth": [
+    "Home_Fashions_Washcloth_Linen"
+  ],
+  "olive green cloth": [
+    "Home_Fashions_Washcloth_Olive_Green"
+  ],
+  "pink pencil case": [
+    "Horses_in_Pink_Pencil_Case"
+  ],
+  "green toy ogre": [
+    "Imaginext_Castle_Ogre"
+  ],
+  "Inositol": [
+    "Inositol"
+  ],
+  "green JBL portable speaker": [
+    "JBL_Charge_Speaker_portable_wireless_wired_Green"
+  ],
+  "blue and black backpack": [
+    "Jansport_School_Backpack_Blue_Streak"
+  ],
+  "white gift box with red straps": [
+    "KS_Chocolate_Cube_Box_Assortment_By_Neuhaus_2010_Ounces"
+  ],
+  "white keyboard": [
+    "Kanex_MultiSync_Wireless_Keyboard"
+  ],
+  "pale green saucer": [
+    "Kotobuki_Saucer_Dragon_Fly"
+  ],
+  "toy sheep": [
+    "LACING_SHEEP"
+  ],
+  "gray laptop": [
+    "Lenovo_Yoga_2_11"
+  ],
+  "brown teddy bear": [
+    "Lovable_Huggable_Cuddly_Boutique_Teddy_Bear_Beige"
+  ],
+  "green-orange magnifying glass": [
+    "Magnifying_Glassassrt"
+  ],
+  "blue conditioner bottle": [
+    "Marc_Anthony_Skip_Professional_Oil_of_Morocco_Conditioner_with_Argan_Oil"
+  ],
+  "brown leather shoe": [
+    "Mens_ASV_Billfish_Boat_Shoe_in_Dark_Brown_Leather_zdHVHXueI3w",
+    "Mens_Billfish_3Eye_Boat_Shoe_in_Dark_Tan_wyns9HRcEuH",
+    "Mens_Billfish_Slip_On_in_Tan_Beige_aaVUk0tNTv8"
+  ],
+  "sandal": [
+    "NAPA_VALLEY_NAVAJO_SANDAL"
+  ],
+  "white square bowl": [
+    "Neat_Solutions_Character_Bib_2_pack"
+  ],
+  "yellow nesquik chocolate powder canister": [
+    "Nestle_Nesquik_Chocolate_Powder_Flavored_Milk_Additive_109_Oz_Canister"
+  ],
+  "teenage mutant ninja turtle figure": [
+    "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Leonardo",
+    "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Michelangelo",
+    "Nickelodeon_Teenage_Mutant_Ninja_Turtles_Raphael"
+  ],
+  "nikon camera lens": [
+    "Nikon_1_AW1_w11275mm_Lens_Silver"
+  ],
+  "black-red nintendo 2ds console": [
+    "Nintendo_2DS_Crimson_Red"
+  ],
+  "mario action figure": [
+    "Nintendo_Mario_Action_Figure"
+  ],
+  "green yoshi action figure": [
+    "Nintendo_Yoshi_Action_Figure"
+  ],
+  "black-white bowl": [
+    "Now_Designs_Bowl_Akita_Black"
+  ],
+  "green towel": [
+    "Now_Designs_Dish_Towel_Mojave_18_x_28"
+  ],
+  "colorful xylophone": [
+    "OVAL_XYLOPHONE"
+  ],
+  "black-purple spatula": [
+    "OXO_Cookie_Spatula"
+  ],
+  "black can opener": [
+    "OXO_Soft_Works_Can_Opener_SnapLock"
+  ],
+  "green hat with feather": [
+    "Object_REmvBDJStub"
+  ],
+  "white dust pan with brush": [
+    "Ocedar_Snap_On_Dust_Pan_And_Brush_1_ct"
+  ],
+  "turquoise backpack": [
+    "Olive_Kids_Birdie_Sidekick_Backpack"
+  ],
+  "yellow tow giraffe": [
+    "Ortho_Forward_Facing"
+  ],
+  "black helmet": [
+    "Ortho_Forward_Facing_CkAW6rL25xH"
+  ],
+  "toy koala": [
+    "Ortho_Forward_Facing_QCaor9ImJ2G"
+  ],
+  "yellow flower pot": [
+    "Pennington_Electric_Pot_Cabana_4"
+  ],
+  "colorful pencil case": [
+    "Pinwheel_Pencil_Case"
+  ],
+  "white soccer cleats": [
+    "Predator_LZ_TRX_FG",
+    "Predito_LZ_TRX_FG_W"
+  ],
+  "white plate with salad": [
+    "ProSport_Harness_to_Booster_Seat"
+  ],
+  "dark blue towel": [
+    "Provence_Bath_Towel_Royal_Blue"
+  ],
+  "black boot": [
+    "REEF_BANTU"
+  ],
+  "black flip-flop sandal": [
+    "REEF_BRAIDED_CUSHION",
+    "Reef_Star_Cushion_Flipflops_Size_8_Black"
+  ],
+  "white-blue basket": [
+    "RJ_Rabbit_Easter_Basket_Blue"
+  ],
+  "plush racoon": [
+    "Racoon"
+  ],
+  "black gaming mouse": [
+    "Razer_Abyssus_Ambidextrous_Gaming_Mouse",
+    "Razer_Naga_MMO_Gaming_Mouse",
+    "Razer_Taipan_Black_Ambidextrous_Gaming_Mouse"
+  ],
+  "black keyboard": [
+    "Razer_BlackWidow_Stealth_2014_Keyboard_07VFzIVabgh",
+    "Razer_BlackWidow_Ultimate_2014_Mechanical_Gaming_Keyboard",
+    "Razer_Blackwidow_Tournament_Edition_Keyboard"
+  ],
+  "white gaming mouse": [
+    "Razer_Taipan_White_Ambidextrous_Gaming_Mouse"
+  ],
+  "black and red gameboy": [
+    "RedBlack_Nintendo_3DSXL"
+  ],
+  "red hair dryer": [
+    "Remington_TStudio_Hair_Dryer"
+  ],
+  "brown hat": [
+    "Retail_Leadership_Summit"
+  ],
+  "gray hat": [
+    "Retail_Leadership_Summit_eCT3zqHYIkX"
+  ],
+  "blue gloves": [
+    "Rexy_Glove_Heavy_Duty_Gloves_Medium"
+  ],
+  "turquoise bowl": [
+    "Room_Essentials_Bowl_Turquiose"
+  ],
+  "white-yellow mug": [
+    "Room_Essentials_Mug_White_Yellow"
+  ],
+  "turquoise plate": [
+    "Room_Essentials_Salad_Plate_Turquoise"
+  ],
+  "dish drainer": [
+    "Rubbermaid_Large_Drainer"
+  ],
+  "brown shoe": [
+    "SAMBA_HEMP"
+  ],
+  "sandwich on plate": [
+    "SANDWICH_MEAL"
+  ],
+  "yellow school bus": [
+    "SCHOOL_BUS"
+  ],
+  "wooden ring stacker toy": [
+    "STACKING_RING"
+  ],
+  "rhino": [
+    "Schleich_African_Black_Rhino"
+  ],
+  "bald eagle": [
+    "Schleich_Bald_Eagle"
+  ],
+  "brown bull": [
+    "Schleich_Hereford_Bull"
+  ],
+  "lion": [
+    "Schleich_Lion_Action_Figure"
+  ],
+  "unicorn": [
+    "Schleich_S_Bayala_Unicorn_70432"
+  ],
+  "metal hard drive storage": [
+    "Seagate_Archive_HDD_8_TB_Internal_hard_drive_SATA_6Gbs_35_ST8000AS0002"
+  ],
+  "shark": [
+    "Shark",
+    "Weisshai_Great_White_Shark"
+  ],
+  "purple tape": [
+    "Shurtape_30_Day_Removal_UV_Delct_15"
+  ],
+  "gray tape": [
+    "Shurtape_Gaffers_Tape_Silver_2_x_60_yd"
+  ],
+  "grey elephant toy": [
+    "Sootheze_Cold_Therapy_Elephant"
+  ],
+  "orca toy": [
+    "Sootheze_Toasty_Orca"
+  ],
+  "spider man action figure": [
+    "SpiderMan_Titan_Hero_12Inch_Action_Figure_5Hnn4mtkFsP",
+    "SpiderMan_Titan_Hero_12Inch_Action_Figure_oo1qph4wwiW"
+  ],
+  "toy squirrel": [
+    "Squirrel"
+  ],
+  "bamboo sushi mat": [
+    "Sushi_Mat"
+  ],
+  "blue-white striped towel": [
+    "Tag_Dishtowel_Dobby_Stripe_Blue_18_x_26"
+  ],
+  "green-white striped towel": [
+    "Tag_Dishtowel_Green"
+  ],
+  "green toy train": [
+    "Thomas_Friends_Woodan_Railway_Henry"
+  ],
+  "woven storage basket": [
+    "Threshold_Basket_Natural_Finish_Fabric_Liner_Small"
+  ],
+  "white-red plate": [
+    "Threshold_Bistro_Ceramic_Dinner_Plate_Ruby_Ring"
+  ],
+  "white mug": [
+    "Threshold_Porcelain_Coffee_Mug_All_Over_Bead_White"
+  ],
+  "white porcelain teapot": [
+    "Threshold_Porcelain_Teapot_White"
+  ],
+  "white square saucer": [
+    "Threshold_Salad_Plate_Square_Rim_Porcelain"
+  ],
+  "pink bath towel": [
+    "Threshold_Textured_Damask_Bath_Towel_Pink"
+  ],
+  "rectangular porcelain tray": [
+    "Threshold_Tray_Rectangle_Porcelain"
+  ],
+  "white-pink dog bowl": [
+    "Top_Paw_Dog_Bow_Bone_Ceramic_13_fl_oz_total"
+  ],
+  "blue dog bowl": [
+    "Top_Paw_Dog_Bowl_Blue_Paw_Bone_Ceramic_25_fl_oz_total"
+  ],
+  "white animal dog toy": [
+    "Toysmith_Windem_Up_Flippin_Animals_Dog"
+  ],
+  "black laptop": [
+    "Travel_Mate_P_series_Notebook"
+  ],
+  "black power pressure cooker": [
+    "TriStar_Products_PPC_Power_Pressure_Cooker_XL_in_Black"
+  ],
+  "yellow ballet shoe": [
+    "Unmellow_Yellow_Tieks_Neon_Patent_Leather_Ballet_Flats"
+  ],
+  "green turtle toy": [
+    "Vtech_Roll_Learn_Turtle"
+  ],
+  "white shoe": [
+    "Womens_Canvas_Bahama_in_White_4UyOhP6rYGO"
+  ],
+  "black sneaker": [
+    "adistar_boost_m"
+  ]
+}

eq-kubric/create_scene.py

@@ -0,0 +1,49 @@
+import subprocess
+
+def create_scene(index: int, dataset_type="location", max_num_objects=1, retries=10, log_file="logs/error_log.txt", verbose=False) -> int:
+    """
+    Attempts to create a data entry point in a dataset by running a Docker container that executes a Python script.
+
+    This function tries to execute a command to create a scene up to a specified number of retries. It logs the attempts and errors to a specified file. If successful, it returns 1; if it fails after all retries, it returns 0.
+
+    Args:
+        index (int): The index of the scene to generate, which affects the generate_idx parameter in the command.
+        dataset_type (str): The type of the dataset, which customizes the Python script to be executed.
+        max_num_objects (int): The maximum number of objects to include in the scene.
+        retries (int): The number of attempts to make in case of failure.
+        log_file (str): Path to the file where error logs are appended.
+
+    Returns:
+        int: 0 if the scene was successfully created, 1 otherwise.
+
+    Raises:
+        None directly by the function, but subprocess.run may raise an exception if the command execution fails critically.
+
+    Side Effects:
+        Writes to a log file at `log_file` path if any errors occur during the execution.
+        Tries to execute a Docker command which can affect system resources and Docker state.
+    """
+    command = f"""
+        sudo docker run --rm --interactive \
+                   --user $(id -u):$(id -g) \
+                   --volume "$(pwd):/kubric" kubricdockerhub/kubruntu \
+                   /usr/bin/python3 eq-kubric/my_kubric_twoframe_{dataset_type}.py \
+                   --sub_outputdir {dataset_type} \
+                   --generate_idx {index+1} \
+                   --max_num_objects {max_num_objects}
+        """
+
+    attempt = 0
+    while attempt < retries:
+        result = subprocess.run(command, shell=True, capture_output=True, text=True)
+        if result.returncode == 0 and ("INFO:root:Done!" in result.stderr or "INFO:root:Done!" in result.stdout):
+            return 0
+        attempt += 1
+        if verbose:
+            print(f"Attempt {attempt} failed with return code {result.returncode}.")
+            print(result.stderr)
+
+    error_message = f"Failed to create a scene after {attempt} attempts: Index: {index+1}, Dataset Type: '{dataset_type}'."
+    with open(log_file, "a") as file:
+        file.write(f"{error_message}\n")
+    return 1

eq-kubric/main.py

@@ -0,0 +1,16 @@
+import argparse
+from create_dataset import create_dataset
+
+def main():
+    parser = argparse.ArgumentParser(description='Create a dataset.')
+    parser.add_argument('dataset_length', type=int, help='The length of the dataset')
+    parser.add_argument('--dataset_type', type=str, default='location', help='Type of dataset to create (default: location)')
+    parser.add_argument('--max_num_objects', type=int, default=4, help='Maximum number of objects in the scene (default: 4)')
+    parser.add_argument('--n_jobs', type=int, default=1, help='Number of parallel jobs to run (default: 1)')
+    parser.add_argument('--verbose', action='store_true', help='Print verbose output')
+
+    args = parser.parse_args()
+    create_dataset(args.dataset_length, args.dataset_type, args.max_num_objects, args.n_jobs, args.verbose)
+
+if __name__ == '__main__':
+    main()

eq-kubric/my_kubric_twoframe_attribute.py

@@ -0,0 +1,587 @@
+# Copyright 2022 The Kubric Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Worker file for the Multi-Object Video (MOVi) C (and CC) datasets.
+  * The number of objects is randomly chosen between
+    --min_num_objects (3) and --max_num_objects (10)
+  * The objects are randomly chosen from the Google Scanned Objects dataset
+
+  * Background is an random HDRI from the HDRI Haven dataset,
+    projected onto a Dome (half-sphere).
+    The HDRI is also used for lighting the scene.
+"""
+
+import logging
+
+import bpy
+import copy
+import os
+import kubric as kb
+from kubric.simulator import PyBullet
+from kubric.renderer import Blender
+import numpy as np
+import random
+import shutil
+
+from GSO_transfer import GSO_dict, GSO_dict_attr
+from utils import save_scene_instruction, dataset_dir
+
+# --- Some configuration values
+DATASET_TYPE = "attribute"
+# the region in which to place objects [(min), (max)]
+SPAWN_REGION = [(-8, -8, 0), (8, 8, 5)]
+SPAWN_REGION_OBJ = [[-6, -6, 0.5], [6, 6, 0.5]]
+VELOCITY_RANGE = [(-4., -4., 0.), (4., 4., 0.)]
+
+# --- CLI arguments
+parser = kb.ArgumentParser()
+parser.add_argument("--objects_split", choices=["train", "test"],
+                    default="train")
+# Configuration for the objects of the scene
+parser.add_argument("--min_num_objects", type=int, default=1,
+                    help="minimum number of objects")
+parser.add_argument("--max_num_objects", type=int, default=4,
+                    help="maximum number of objects")
+# Configuration for the floor and background
+parser.add_argument("--floor_friction", type=float, default=0.3)
+parser.add_argument("--floor_restitution", type=float, default=0.5)
+parser.add_argument("--backgrounds_split", choices=["train", "test"],
+                    default="train")
+
+parser.add_argument("--camera", choices=["fixed_random", "linear_movement"],
+                    default="fixed_random")
+parser.add_argument("--max_camera_movement", type=float, default=4.0)
+parser.add_argument("--smallest_scale", type=float, default=1.5)
+parser.add_argument("--largest_scale", type=float, default=4.)
+
+# Configuration for the source of the assets
+parser.add_argument("--kubasic_assets", type=str,
+                    default="gs://kubric-public/assets/KuBasic/KuBasic.json")
+parser.add_argument("--hdri_assets", type=str,
+                    default="gs://kubric-public/assets/HDRI_haven/HDRI_haven.json")
+parser.add_argument("--gso_assets", type=str,
+                    default="gs://kubric-public/assets/GSO/GSO.json")
+parser.add_argument("--save_state", dest="save_state", action="store_true")
+parser.set_defaults(save_state=False, frame_end=24, frame_rate=12,
+                    resolution=512)
+parser.add_argument("--sub_outputdir", type=str, default="test sub output dir")
+parser.add_argument("--generate_idx", type=int, default=-1, help="generation idx")
+FLAGS = parser.parse_args()
+
+
+import pyquaternion as pyquat
+def default_rng():
+  return np.random.RandomState()
+
+
+# def random_rotation(axis=None, rng=default_rng()):
+#   """ Compute a random rotation as a quaternion.
+#   If axis is None the rotation is sampled uniformly over all possible orientations.
+#   Otherwise it corresponds to a random rotation around the given axis."""
+
+#   if axis is None:
+#     # uniform across rotation space
+#     # copied from pyquat.Quaternion.random to be able to use a custom rng
+#     r1, r2, r3 = rng.random(3)
+
+#     q1 = np.sqrt(1.0 - r1) * (np.sin(2 * np.pi * r2))
+#     q2 = np.sqrt(1.0 - r1) * (np.cos(2 * np.pi * r2))
+#     q3 = np.sqrt(r1) * (np.sin(2 * np.pi * r3))
+#     q4 = np.sqrt(r1) * (np.cos(2 * np.pi * r3))
+
+#     return q1, q2, q3, q4
+
+#   else:
+#     if isinstance(axis, str) and axis.upper() in ["X", "Y", "Z"]:
+#       axis = {"X": (1., 0., 0.),
+#               "Y": (0., 1., 0.),
+#               "Z": (0., 0., 1.)}[axis.upper()]
+
+#     # quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(0, 2*np.pi))
+#     quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(-0.5*np.pi, 0.5*np.pi)) # -0.5pi -- 0.5pi
+#     return tuple(quat)
+
+
+# from kubric.core import objects
+# def rotation_sampler(axis=None):
+#   def _sampler(obj: objects.PhysicalObject, rng):
+#     obj.quaternion = random_rotation(axis=axis, rng=rng)
+#   return _sampler
+
+
+def move_until_no_overlap(asset, simulator, spawn_region=((-1, -1, -1), (1, 1, 1)), max_trials=100,
+                          rng=default_rng()):
+  return kb.randomness.resample_while(asset,
+                        samplers=[kb.randomness.position_sampler(spawn_region)],
+                        condition=simulator.check_overlap,
+                        max_trials=max_trials,
+                        rng=rng)
+
+
+def check_ok(obj, pos, region):
+    # import pdb; pdb.set_trace()
+    x, y, z = pos
+    if pos[0]<region[0][0] or pos[0]>region[1][0] or pos[1]<region[0][1] or pos[1]>region[1][1]: #or pos[2]<region[0][2] or  pos[2]>region[1][2]:
+        return False
+
+    if simulator.check_overlap(obj):
+        return False
+
+    return True
+
+
+def get_obj_x_left(bound, scale):
+    return -bound[0][0] * scale[0]
+
+def get_obj_x_right(bound, scale):
+    return bound[1][0] * scale[0]
+
+def get_obj_y_front(bound, scale):
+    return -bound[0][1] * scale[1]
+
+def get_obj_y_behind(bound, scale):
+    return bound[1][1] * scale[1]
+
+def get_obj_z(bound, scale):
+    return bound[0][2] * scale[2]
+
+def get_obj_z_up(bound, scale):
+    return bound[1][2] * scale[2]
+
+
+def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object,  rng):
+
+    obj_z = - get_obj_z(bounds, scale)
+    # import pdb; pdb.set_trace()
+    ref_x_left, ref_x_right, ref_y_front, ref_y_behind = get_obj_x_left(ref_object.bounds, ref_object.scale), get_obj_x_right(ref_object.bounds, ref_object.scale), get_obj_y_front(ref_object.bounds, ref_object.scale), get_obj_y_behind(ref_object.bounds, ref_object.scale)
+    ref_x, ref_y, ref_z = ref_pos
+    if ref_location == 'front':
+        return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y-ref_y_front-6, ref_y-ref_y_front-2), obj_z+0.02]
+    elif ref_location == 'behind':
+        return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y+ref_y_behind+3, ref_y+ref_y_behind+7), obj_z+0.02]
+    elif ref_location == 'left':
+        return [rng.uniform(ref_x-ref_x_left-6, ref_x-ref_x_left-2), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+    elif ref_location == 'right':
+        return [rng.uniform(ref_x+ref_x_right+2, ref_x+ref_x_right+6), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+    elif ref_location == 'on':
+        return [ref_x, ref_y, ref_z+ref_z_up+obj_z+1]
+    
+def get_second_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+    obj_z = -get_obj_z(bounds, scale)
+    ref_x, ref_y, ref_z = ref_pos
+
+    if ref_location == 'on':
+        return [ref_x, ref_y, ref_z]
+    else:
+        return [ref_x, ref_y, obj_z + 0.02]
+
+
+def add_new_obj(scene, new_obj, ref_location, ref_object, rng, max_trails=50, second_obj=False):
+
+    ref_obj_pos = ref_object.position
+    # import pdb; pdb.set_trace()
+    ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+    if not second_obj:
+        new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+    else:
+        new_obj_pos = get_second_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+    new_obj.position = new_obj_pos
+    scene += new_obj
+
+    # import pdb; pdb.set_trace()
+    trails = 0
+    while not check_ok(new_obj, new_obj.position, SPAWN_REGION_OBJ):
+        trails += 1
+        # import pdb; pdb.set_trace()
+        # new_obj.position = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+        if not second_obj:
+            new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+        else:
+            new_obj_pos = get_second_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+        new_obj.position = new_obj_pos
+        # new_obj.quaternion = random_rotation(axis="Z", rng=rng)
+        if trails > max_trails:
+            print('cannot put the object, break')
+            # import pdb; pdb.set_trace()
+            return None
+    print('try {} times'.format(trails))
+    return scene
+
+def gen_caption(obj_name, obj_scale, ref_obj_name, ref_obj_scale, use_attr):
+    def get_change_size_exp(obj_scale, ref_obj_scale):
+        if obj_scale < ref_obj_scale:
+            return random.choice(["smaller", "small"])
+        elif obj_scale > ref_obj_scale:
+            return random.choice(["larger", "bigger", "large", "big"])
+        else:
+            return "same size"
+    
+    ref_obj_size_exp = get_change_size_exp(obj_scale, ref_obj_scale)
+
+    if use_attr != "scale":
+        edit_instruction = random.choice(["transform", "convert", "turn"])
+        caption = f'{edit_instruction} the {ref_obj_name} into a {obj_name}'
+    else:
+        edit_instruction = random.choice(["make", "turn"])
+        caption = f'{edit_instruction} the {ref_obj_name} {ref_obj_size_exp}'
+    return caption
+
+def sample_unique_items(GSO_dict, num_samples):
+    unique_items = {}
+    sampled_values = set()    
+    active_keys = list(GSO_dict.keys())
+    
+    while len(unique_items) < num_samples:
+        key = random.choice(active_keys)
+        value = GSO_dict[key]
+        
+        if value not in sampled_values:
+            sampled_values.add(value)
+            unique_items[key] = value
+        
+        active_keys.remove(key)
+        if not active_keys:
+            break
+    
+    return list(unique_items.keys())
+
+# --- Common setups & resources
+print('Generate {} Sample'.format(FLAGS.generate_idx))
+scene, rng, output_dir, scratch_dir = kb.setup(FLAGS)
+output_dir = output_dir / FLAGS.sub_outputdir
+
+simulator = PyBullet(scene, scratch_dir)
+renderer = Blender(scene, scratch_dir, samples_per_pixel=64)
+kubasic = kb.AssetSource.from_manifest(FLAGS.kubasic_assets)
+gso = kb.AssetSource.from_manifest(FLAGS.gso_assets)
+hdri_source = kb.AssetSource.from_manifest(FLAGS.hdri_assets)
+
+# --- Populate the scene
+# background HDRI
+train_backgrounds, test_backgrounds = hdri_source.get_test_split(fraction=0.)
+logging.info("Choosing one of the %d training backgrounds...", len(train_backgrounds))
+hdri_id = rng.choice(train_backgrounds)
+
+background_hdri = hdri_source.create(asset_id=hdri_id)
+#assert isinstance(background_hdri, kb.Texture)
+logging.info("Using background %s", hdri_id)
+scene.metadata["background"] = hdri_id
+renderer._set_ambient_light_hdri(background_hdri.filename)
+
+
+# Dome
+dome = kubasic.create(asset_id="dome", name="dome",
+                      friction=FLAGS.floor_friction,
+                      restitution=FLAGS.floor_restitution,
+                      static=True, background=True)
+assert isinstance(dome, kb.FileBasedObject)
+scene += dome
+dome_blender = dome.linked_objects[renderer]
+texture_node = dome_blender.data.materials[0].node_tree.nodes["Image Texture"]
+texture_node.image = bpy.data.images.load(background_hdri.filename)
+
+def get_linear_camera_motion_start_end(
+    movement_speed: float,
+    inner_radius: float = 8.,
+    outer_radius: float = 12.,
+    z_offset: float = 0.1,
+):
+  """Sample a linear path which starts and ends within a half-sphere shell."""
+  while True:
+    camera_start = np.array(kb.sample_point_in_half_sphere_shell(inner_radius,
+                                                                 outer_radius,
+                                                                 z_offset))
+    direction = rng.rand(3) - 0.5
+    movement = direction / np.linalg.norm(direction) * movement_speed
+    camera_end = camera_start + movement
+    if (inner_radius <= np.linalg.norm(camera_end) <= outer_radius and
+        camera_end[2] > z_offset):
+      return camera_start, camera_end
+
+
+# Camera
+logging.info("Setting up the Camera...")
+scene.camera = kb.PerspectiveCamera(focal_length=35., sensor_width=36)
+if FLAGS.camera == "fixed_random":
+    # scene.camera.position = kb.sample_point_in_half_sphere_shell(
+    #     inner_radius=7., outer_radius=9., offset=4)
+    scene.camera.position = (0, -10, 12)
+    scene.camera.look_at((0, 0, 0))
+elif FLAGS.camera == "linear_movement":
+    camera_start, camera_end = get_linear_camera_motion_start_end(
+      movement_speed=rng.uniform(low=0., high=FLAGS.max_camera_movement)
+    )
+    # linearly interpolate the camera position between these two points
+    # while keeping it focused on the center of the scene
+    # we start one frame early and end one frame late to ensure that
+    # forward and backward flow are still consistent for the last and first frames
+    for frame in range(FLAGS.frame_start - 1, FLAGS.frame_end + 2):
+        interp = ((frame - FLAGS.frame_start + 1) /
+                  (FLAGS.frame_end - FLAGS.frame_start + 3))
+        scene.camera.position = (interp * np.array(camera_start) +
+                                 (1 - interp) * np.array(camera_end))
+        scene.camera.look_at((0, 0, 0))
+        scene.camera.keyframe_insert("position", frame)
+        scene.camera.keyframe_insert("quaternion", frame)
+
+
+# Add random objects
+active_split = list(GSO_dict_attr['base_set'].keys())
+num_objects = rng.randint(FLAGS.min_num_objects,
+                          FLAGS.max_num_objects+1)
+
+logging.info("Step 1: Randomly placing %d objects:", num_objects)
+object_state_save_dict = {}
+object_state_ref_dict = {}
+
+
+# not resample objects
+# object_id_list = random.sample(active_split, num_objects)
+object_id_list = sample_unique_items(GSO_dict, num_objects+1)
+
+for i in range(num_objects):
+    # object_id = rng.choice(active_split)
+    object_id = object_id_list[i]
+    obj = gso.create(asset_id=object_id)
+
+
+    assert isinstance(obj, kb.FileBasedObject)
+    scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+    obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+
+
+    obj_pos_z = - get_obj_z(obj.bounds, obj.scale)
+    SPAWN_REGION_OBJ[0][2], SPAWN_REGION_OBJ[1][2] = obj_pos_z, obj_pos_z
+    obj.position = rng.uniform(*SPAWN_REGION_OBJ)
+
+    obj.metadata["scale"] = scale
+    scene += obj
+    move_until_no_overlap(obj, simulator, spawn_region=SPAWN_REGION_OBJ, rng=rng)
+    # initialize velocity randomly but biased towards center
+    # obj.velocity = (rng.uniform(*VELOCITY_RANGE) -
+    #                 [obj.position[0], obj.position[1], 0])
+    # print(obj.position)
+    obj.velocity = [0, 0, 0]
+    logging.info("    Added %s at %s", obj.asset_id, obj.position)
+    object_state_save_dict[i] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+    object_state_ref_dict[i] = {'object': obj}
+
+
+
+# # choose the object to change the attribute
+# active_split_choose = random.choice(list(GSO_dict_attr['choose_set'].keys()))
+# object_choose1, object_choose2 = random.sample(list(GSO_dict_attr['choose_set'][active_split_choose].keys()), 2)
+# # choose the ref object and the location
+# ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+# ref_object_name = GSO_dict[ref_object.asset_id]
+# ref_location = ref_object.position
+
+# random choose two location
+LOC_SET = ['front', 'behind', 'left', 'right', 'on']
+use_location = random.sample(LOC_SET, 1)[0]
+ATTR_SET = [use_location, 'scale']
+use_attr = random.sample(ATTR_SET, 1)[0]
+
+if use_attr != 'scale':
+    # choose the object to change the attribute
+    active_split_choose = random.choice(list(GSO_dict_attr['choose_set'].keys()))
+    object_choose1, object_choose2 = random.sample(list(GSO_dict_attr['choose_set'][active_split_choose].keys()), 2)
+    # choose the ref object and the location
+    ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+    ref_object_name = GSO_dict[ref_object.asset_id]
+    ref_location = ref_object.position
+
+    # 1st
+    print('Generate the first scene.')
+    # object_id = rng.choice(active_split)
+    object_id = object_choose1
+    obj = gso.create(asset_id=object_id)
+    scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+    obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+    obj.metadata["scale"] = scale
+
+    new_object_name = GSO_dict_attr['choose_set'][active_split_choose][object_id]
+    print('Add new object {}'.format(new_object_name))
+
+
+    # obj 2
+    object2_id = object_choose2
+    obj2 = gso.create(asset_id=object2_id) 
+    # scale2 = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)  
+    # obj2.scale = scale2 / np.max(obj2.bounds[1] - obj2.bounds[0])  
+    # obj2.metadata["scale"] = scale2  
+    obj2.scale = scale / np.max(obj2.bounds[1] - obj2.bounds[0])  
+    obj2.metadata["scale"] = scale
+
+    new_object2_name = GSO_dict_attr['choose_set'][active_split_choose][object2_id]  # Updated to use object2_id
+    print('Add second object {}'.format(new_object2_name))  # Refers to new_object2_name
+    #obj 2
+
+    scene = add_new_obj(scene, obj, use_attr, ref_object, rng, max_trails=500)
+    if scene is None:
+        exit()
+    frame = renderer.render_still()
+
+    os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+    kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+    caption_1 = gen_caption(new_object_name, obj.metadata["scale"], new_object2_name, obj2.metadata["scale"], use_attr)
+    print(caption_1)
+
+    # 2nd
+    print('Generate the second scene.')
+    scene.remove(obj)
+    scene = add_new_obj(scene, obj2, use_attr, obj, rng, max_trails=500, second_obj=True)
+
+    if scene is None:
+        print('cannot put the object, break')
+        shutil.rmtree(output_dir / '{}'.format(FLAGS.generate_idx))
+        exit()
+
+    frame = renderer.render_still()
+    kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+    caption_2 = gen_caption(new_object2_name, obj2.metadata["scale"], new_object_name, obj.metadata["scale"], use_attr)
+    print(caption_2)
+else:
+    # choose the object to change the attribute
+    # active_split_choose = random.choice(list(GSO_dict_attr['choose_set'].keys()))
+    # object_choose1, object_choose2 = random.sample(list(GSO_dict_attr['choose_set'][active_split_choose].keys()), 2)
+    object_choose1 = random.choice(list(GSO_dict.keys()))
+
+    # choose the ref object and the location
+    ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+    ref_object_name = GSO_dict[ref_object.asset_id]
+    ref_location = ref_object.position
+
+    # 1st
+    print('Generate the first scene.')
+    # object_id = rng.choice(active_split)
+    object_id = object_choose1
+    obj = gso.create(asset_id=object_id)
+    scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+    obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+    obj.metadata["scale"] = scale
+
+    new_object_name = GSO_dict[object_id]
+    print('Add new object {}'.format(new_object_name))
+
+
+    # obj 2
+    object2_id = object_choose1
+    obj2 = gso.create(asset_id=object2_id) 
+    scale2 = rng.uniform(FLAGS.smallest_scale-1, FLAGS.largest_scale+2)  
+    obj2.scale = scale2 / np.max(obj2.bounds[1] - obj2.bounds[0])  
+    obj2.metadata["scale"] = scale2
+
+    new_object2_name = GSO_dict[object2_id]  # Updated to use object2_id
+    print('Add second object {}'.format(new_object2_name))  # Refers to new_object2_name
+    #obj 2
+
+    scene = add_new_obj(scene, obj, use_location, ref_object, rng, max_trails=500)
+    if scene is None:
+        exit()
+    frame = renderer.render_still()
+
+    os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+    kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+    caption_1 = gen_caption(new_object_name, obj.metadata["scale"], new_object2_name, obj2.metadata["scale"], use_attr)
+    print(caption_1)
+
+    # 2nd
+    print('Generate the second scene.')
+    scene.remove(obj)
+    scene = add_new_obj(scene, obj2, use_location, obj, rng, max_trails=500, second_obj=True)
+
+    if scene is None:
+        print('cannot put the object, break')
+        shutil.rmtree(output_dir / '{}'.format(FLAGS.generate_idx))
+        exit()
+
+    frame = renderer.render_still()
+    kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+    caption_2 = gen_caption(new_object2_name, obj2.metadata["scale"], new_object_name, obj.metadata["scale"], use_attr)
+    print(caption_2)
+
+local_ann = [
+    {
+        'input': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx), 
+        'output': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx), 
+        'instruction': caption_2,
+    },
+    {
+        'input': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx), 
+        'output': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx), 
+        'instruction': caption_1,
+    }
+]
+save_scene_instruction(f"{output_dir}/eq_kubric_{DATASET_TYPE}.json", local_ann, DATASET_TYPE, FLAGS.generate_idx)
+
+kb.done()
+
+# if FLAGS.save_state:
+#   logging.info("Saving the simulator state to '%s' prior to the simulation.",
+#                output_dir / "scene.bullet")
+#   simulator.save_state(output_dir / "scene.bullet")
+#
+# # Run dynamic objects simulation
+# logging.info("Running the simulation ...")
+# animation, collisions = simulator.run(frame_start=0,
+#                                       frame_end=scene.frame_end+1)
+#
+# # --- Rendering
+# if FLAGS.save_state:
+#   logging.info("Saving the renderer state to '%s' ",
+#                output_dir / "scene.blend")
+#   renderer.save_state(output_dir / "scene.blend")
+#
+#
+# logging.info("Rendering the scene ...")
+# data_stack = renderer.render()
+#
+# # --- Postprocessing
+# kb.compute_visibility(data_stack["segmentation"], scene.assets)
+# visible_foreground_assets = [asset for asset in scene.foreground_assets
+#                              if np.max(asset.metadata["visibility"]) > 0]
+# visible_foreground_assets = sorted(  # sort assets by their visibility
+#     visible_foreground_assets,
+#     key=lambda asset: np.sum(asset.metadata["visibility"]),
+#     reverse=True)
+#
+# data_stack["segmentation"] = kb.adjust_segmentation_idxs(
+#     data_stack["segmentation"],
+#     scene.assets,
+#     visible_foreground_assets)
+# scene.metadata["num_instances"] = len(visible_foreground_assets)
+#
+# # Save to image files
+# kb.write_image_dict(data_stack, output_dir)
+# kb.post_processing.compute_bboxes(data_stack["segmentation"],
+#                                   visible_foreground_assets)
+#
+# # --- Metadata
+# logging.info("Collecting and storing metadata for each object.")
+# kb.write_json(filename=output_dir / "metadata.json", data={
+#     "flags": vars(FLAGS),
+#     "metadata": kb.get_scene_metadata(scene),
+#     "camera": kb.get_camera_info(scene.camera),
+#     "instances": kb.get_instance_info(scene, visible_foreground_assets),
+# })
+# kb.write_json(filename=output_dir / "events.json", data={
+#     "collisions":  kb.process_collisions(
+#         collisions, scene, assets_subset=visible_foreground_assets),
+# })
+#
+# kb.done()

eq-kubric/my_kubric_twoframe_closer.py

@@ -0,0 +1,479 @@
+# Copyright 2022 The Kubric Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Worker file for the Multi-Object Video (MOVi) C (and CC) datasets.
+  * The number of objects is randomly chosen between
+    --min_num_objects (3) and --max_num_objects (10)
+  * The objects are randomly chosen from the Google Scanned Objects dataset
+
+  * Background is an random HDRI from the HDRI Haven dataset,
+    projected onto a Dome (half-sphere).
+    The HDRI is also used for lighting the scene.
+"""
+
+import logging
+
+import bpy
+import copy
+import os
+import kubric as kb
+from kubric.simulator import PyBullet
+from kubric.renderer import Blender
+import numpy as np
+import random
+import shutil
+
+from GSO_transfer import GSO_dict
+from utils import save_scene_instruction, dataset_dir
+
+# --- Some configuration values
+DATASET_TYPE = "closer"
+# the region in which to place objects [(min), (max)]
+SPAWN_REGION = [(-8, -8, 0), (8, 8, 5)]
+SPAWN_REGION_OBJ = [[-6, -6, 0.5], [6, 6, 0.5]]
+VELOCITY_RANGE = [(-4., -4., 0.), (4., 4., 0.)]
+
+# --- CLI arguments
+parser = kb.ArgumentParser()
+parser.add_argument("--objects_split", choices=["train", "test"],
+                    default="train")
+# Configuration for the objects of the scene
+parser.add_argument("--min_num_objects", type=int, default=1,
+                    help="minimum number of objects")
+parser.add_argument("--max_num_objects", type=int, default=5,
+                    help="maximum number of objects")
+# Configuration for the floor and background
+parser.add_argument("--floor_friction", type=float, default=0.3)
+parser.add_argument("--floor_restitution", type=float, default=0.5)
+parser.add_argument("--backgrounds_split", choices=["train", "test"],
+                    default="train")
+
+parser.add_argument("--camera", choices=["fixed_random", "linear_movement"],
+                    default="fixed_random")
+parser.add_argument("--max_camera_movement", type=float, default=4.0)
+parser.add_argument("--smallest_scale", type=float, default=2.)
+parser.add_argument("--largest_scale", type=float, default=4.)
+
+# Configuration for the source of the assets
+parser.add_argument("--kubasic_assets", type=str,
+                    default="gs://kubric-public/assets/KuBasic/KuBasic.json")
+parser.add_argument("--hdri_assets", type=str,
+                    default="gs://kubric-public/assets/HDRI_haven/HDRI_haven.json")
+parser.add_argument("--gso_assets", type=str,
+                    default="gs://kubric-public/assets/GSO/GSO.json")
+parser.add_argument("--save_state", dest="save_state", action="store_true")
+parser.set_defaults(save_state=False, frame_end=24, frame_rate=12,
+                    resolution=512)
+parser.add_argument("--sub_outputdir", type=str, default="test sub output dir")
+parser.add_argument("--generate_idx", type=int, default=-1, help="generation idx")
+FLAGS = parser.parse_args()
+
+
+import pyquaternion as pyquat
+def default_rng():
+  return np.random.RandomState()
+
+def random_rotation(axis=None, rng=default_rng()):
+  """ Compute a random rotation as a quaternion.
+  If axis is None the rotation is sampled uniformly over all possible orientations.
+  Otherwise it corresponds to a random rotation around the given axis."""
+
+  if axis is None:
+    # uniform across rotation space
+    # copied from pyquat.Quaternion.random to be able to use a custom rng
+    r1, r2, r3 = rng.random(3)
+
+    q1 = np.sqrt(1.0 - r1) * (np.sin(2 * np.pi * r2))
+    q2 = np.sqrt(1.0 - r1) * (np.cos(2 * np.pi * r2))
+    q3 = np.sqrt(r1) * (np.sin(2 * np.pi * r3))
+    q4 = np.sqrt(r1) * (np.cos(2 * np.pi * r3))
+
+    return q1, q2, q3, q4
+
+  else:
+    if isinstance(axis, str) and axis.upper() in ["X", "Y", "Z"]:
+      axis = {"X": (1., 0., 0.),
+              "Y": (0., 1., 0.),
+              "Z": (0., 0., 1.)}[axis.upper()]
+
+    # quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(0, 2*np.pi))
+    quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(-0.5*np.pi, 0.5*np.pi)) # -0.5pi -- 0.5pi
+    return tuple(quat)
+
+
+from kubric.core import objects
+def rotation_sampler(axis=None):
+  def _sampler(obj: objects.PhysicalObject, rng):
+    obj.quaternion = random_rotation(axis=axis, rng=rng)
+  return _sampler
+
+
+def move_until_no_overlap(asset, simulator, spawn_region=((-1, -1, -1), (1, 1, 1)), max_trials=100,
+                          rng=default_rng()):
+  return kb.randomness.resample_while(asset,
+                        # samplers=[rotation_sampler(axis='Z'), kb.randomness.position_sampler(spawn_region)],
+                        samplers=[kb.randomness.position_sampler(spawn_region)],
+                        condition=simulator.check_overlap,
+                        max_trials=max_trials,
+                        rng=rng)
+
+
+def check_ok(obj, pos, region):
+    # import pdb; pdb.set_trace()
+    x, y, z = pos
+    if pos[0]<region[0][0] or pos[0]>region[1][0] or pos[1]<region[0][1] or pos[1]>region[1][1]: #or pos[2]<region[0][2] or  pos[2]>region[1][2]:
+        return False
+
+    if simulator.check_overlap(obj):
+        return False
+
+    return True
+
+
+def get_obj_x_left(bound, scale):
+    return -bound[0][0] * scale[0]
+
+def get_obj_x_right(bound, scale):
+    return bound[1][0] * scale[0]
+
+def get_obj_y_front(bound, scale):
+    return -bound[0][1] * scale[1]
+
+def get_obj_y_behind(bound, scale):
+    return bound[1][1] * scale[1]
+
+def get_obj_z(bound, scale):
+    return bound[0][2] * scale[2]
+
+def get_obj_z_up(bound, scale):
+    return bound[1][2] * scale[2]
+
+
+# def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object,  rng):
+#     obj_z = - get_obj_z(bounds, scale)
+#     # import pdb; pdb.set_trace()
+#     ref_x_left, ref_x_right, ref_y_front, ref_y_behind = get_obj_x_left(ref_object.bounds, ref_object.scale), get_obj_x_right(ref_object.bounds, ref_object.scale), get_obj_y_front(ref_object.bounds, ref_object.scale), get_obj_y_behind(ref_object.bounds, ref_object.scale)
+#     ref_x, ref_y, ref_z = ref_pos
+#     if ref_location == 'front':
+#         return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y-ref_y_front-6, ref_y-ref_y_front-2), obj_z+0.02]
+#     elif ref_location == 'behind':
+#         return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y+ref_y_behind+2, ref_y+ref_y_behind+6), obj_z+0.02]
+#     elif ref_location == 'left':
+#         return [rng.uniform(ref_x-ref_x_left-6, ref_x-ref_x_left-2), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+#     elif ref_location == 'right':
+#         return [rng.uniform(ref_x+ref_x_right+2, ref_x+ref_x_right+6), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+#     elif ref_location == 'on':
+#         return [ref_x, ref_y, ref_z+ref_z_up+obj_z+1]
+
+def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+    # Calculate the z-position based on the object's bounds and scale
+    obj_z = -get_obj_z(bounds, scale) + 0.2  # Ensuring the object is slightly above the ground
+
+    # Extract the bounds from the SPAWN_REGION_OBJ variable
+    spawn_x_min, spawn_y_min, _ = SPAWN_REGION_OBJ[0]
+    spawn_x_max, spawn_y_max, _ = SPAWN_REGION_OBJ[1]
+
+    # Calculate the maximum offsets within the given spawn bounds
+    max_offset_x = spawn_x_max - spawn_x_min + 1
+    max_offset_y = spawn_y_max - spawn_y_min + 1
+
+    # Define absolute positions for each location using straightforward calculations
+    import random
+
+    # Return the position for the specified location
+    return locations.get(ref_location, [ref_pos[0], ref_pos[1], obj_z])  # Default position if location is not specified
+
+def add_new_obj(scene, new_obj, ref_location, ref_object, rng, max_trails=50):
+
+    ref_obj_pos = ref_object.position
+    # import pdb; pdb.set_trace()
+    ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+    new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+    new_obj.position = new_obj_pos
+    scene += new_obj
+
+    # import pdb; pdb.set_trace()
+    trails = 0
+    while not check_ok(new_obj, new_obj.position, SPAWN_REGION_OBJ):
+        trails += 1
+        # import pdb; pdb.set_trace()
+        new_obj.position = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+        # new_obj.quaternion = random_rotation(axis="Z", rng=rng)
+        if trails > max_trails:
+            print('cannot put the object, break')
+            # import pdb; pdb.set_trace()
+            return None
+    print('try {} times'.format(trails))
+    return scene
+
+def gen_caption(obj_name, obj_scale, ref_obj_name, ref_obj_scale, type='closer'):
+    if type == 'closer':
+        captions = [f'Move the {obj_name} and the {ref_obj_name} closer together.', f'Move the {obj_name} and the {ref_obj_name} closer.', f'Move the {obj_name} and the {ref_obj_name} closer to each other.', f'Move both objects closer', f'Move the two objects closer together.', f'Move the two objects closer to each other.']
+    elif type == 'further':
+        captions = [f'Move the {obj_name} further away from the {ref_obj_name}.', f'Move the {obj_name} and the {ref_obj_name} further apart.', f'Move the {obj_name} and the {ref_obj_name} further away from each other.', f'Move both objects further apart', f'Move the two objects further away from each other.', f'Move the two objects further apart.']
+    elif type == 'swap':
+        captions = [f'Swap the positions of the {obj_name} and the {ref_obj_name}.', f'Swap the positions of the {ref_obj_name} and the {obj_name}.', f'Swap the positions of the two objects.', f'Swap positions of both items.']
+    return random.choice(captions)
+
+
+# --- Common setups & resources
+print('Generate {} Sample'.format(FLAGS.generate_idx))
+scene, rng, output_dir, scratch_dir = kb.setup(FLAGS)
+output_dir = output_dir / FLAGS.sub_outputdir
+
+
+
+simulator = PyBullet(scene, scratch_dir)
+renderer = Blender(scene, scratch_dir, samples_per_pixel=64)
+kubasic = kb.AssetSource.from_manifest(FLAGS.kubasic_assets)
+gso = kb.AssetSource.from_manifest(FLAGS.gso_assets)
+hdri_source = kb.AssetSource.from_manifest(FLAGS.hdri_assets)
+
+
+# --- Populate the scene
+# background HDRI
+train_backgrounds, test_backgrounds = hdri_source.get_test_split(fraction=0.)
+logging.info("Choosing one of the %d training backgrounds...", len(train_backgrounds))
+hdri_id = rng.choice(train_backgrounds)
+
+background_hdri = hdri_source.create(asset_id=hdri_id)
+#assert isinstance(background_hdri, kb.Texture)
+logging.info("Using background %s", hdri_id)
+scene.metadata["background"] = hdri_id
+renderer._set_ambient_light_hdri(background_hdri.filename)
+
+
+# Dome
+dome = kubasic.create(asset_id="dome", name="dome",
+                      friction=FLAGS.floor_friction,
+                      restitution=FLAGS.floor_restitution,
+                      static=True, background=True)
+assert isinstance(dome, kb.FileBasedObject)
+scene += dome
+dome_blender = dome.linked_objects[renderer]
+texture_node = dome_blender.data.materials[0].node_tree.nodes["Image Texture"]
+texture_node.image = bpy.data.images.load(background_hdri.filename)
+
+
+
+def get_linear_camera_motion_start_end(
+    movement_speed: float,
+    inner_radius: float = 8.,
+    outer_radius: float = 12.,
+    z_offset: float = 0.1,
+):
+  """Sample a linear path which starts and ends within a half-sphere shell."""
+  while True:
+    camera_start = np.array(kb.sample_point_in_half_sphere_shell(inner_radius,
+                                                                 outer_radius,
+                                                                 z_offset))
+    direction = rng.rand(3) - 0.5
+    movement = direction / np.linalg.norm(direction) * movement_speed
+    camera_end = camera_start + movement
+    if (inner_radius <= np.linalg.norm(camera_end) <= outer_radius and
+        camera_end[2] > z_offset):
+      return camera_start, camera_end
+
+
+# Camera
+logging.info("Setting up the Camera...")
+scene.camera = kb.PerspectiveCamera(focal_length=35., sensor_width=36)
+if FLAGS.camera == "fixed_random":
+    # scene.camera.position = kb.sample_point_in_half_sphere_shell(
+    #     inner_radius=7., outer_radius=9., offset=4)
+    scene.camera.position = (0, -10, 15)
+    scene.camera.look_at((0, 0, 0))
+elif FLAGS.camera == "linear_movement":
+    camera_start, camera_end = get_linear_camera_motion_start_end(
+      movement_speed=rng.uniform(low=0., high=FLAGS.max_camera_movement)
+    )
+    # linearly interpolate the camera position between these two points
+    # while keeping it focused on the center of the scene
+    # we start one frame early and end one frame late to ensure that
+    # forward and backward flow are still consistent for the last and first frames
+    for frame in range(FLAGS.frame_start - 1, FLAGS.frame_end + 2):
+        interp = ((frame - FLAGS.frame_start + 1) /
+                  (FLAGS.frame_end - FLAGS.frame_start + 3))
+        scene.camera.position = (interp * np.array(camera_start) +
+                                 (1 - interp) * np.array(camera_end))
+        scene.camera.look_at((0, 0, 0))
+        scene.camera.keyframe_insert("position", frame)
+        scene.camera.keyframe_insert("quaternion", frame)
+
+
+# Add random objects
+train_split, test_split = gso.get_test_split(fraction=0.)
+# if FLAGS.objects_split == "train":
+logging.info("Choosing one of the %d training objects...", len(train_split))
+# active_split = train_split
+active_split = list(GSO_dict.keys())
+
+# num_objects = rng.randint(FLAGS.min_num_objects,
+                        #   FLAGS.max_num_objects+1)
+num_objects = 2
+
+logging.info("Step 1: Randomly placing %d objects:", num_objects)
+object_state_save_dict = {}
+object_state_ref_dict = {}
+
+
+# not resample objects
+object_id_list = random.sample(active_split, num_objects+1)
+
+for i in range(num_objects):
+    # object_id = rng.choice(active_split)
+    object_id = object_id_list[i]
+    obj = gso.create(asset_id=object_id)
+
+
+    assert isinstance(obj, kb.FileBasedObject)
+    scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+    obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+
+
+    obj_pos_z = - get_obj_z(obj.bounds, obj.scale)
+    SPAWN_REGION_OBJ[0][2], SPAWN_REGION_OBJ[1][2] = obj_pos_z, obj_pos_z
+    obj.position = rng.uniform(*SPAWN_REGION_OBJ)
+
+    obj.metadata["scale"] = scale
+    scene += obj
+    move_until_no_overlap(obj, simulator, spawn_region=SPAWN_REGION_OBJ, rng=rng)
+    # initialize velocity randomly but biased towards center
+    # obj.velocity = (rng.uniform(*VELOCITY_RANGE) -
+    #                 [obj.position[0], obj.position[1], 0])
+    # print(obj.position)
+    obj.velocity = [0, 0, 0]
+    logging.info("    Added %s at %s", obj.asset_id, obj.position)
+    object_state_save_dict[i] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+    object_state_ref_dict[i] = {'object': obj}
+
+
+ref_object = object_state_ref_dict[list(object_state_ref_dict.keys())[0]]['object']
+ref_object_name = GSO_dict[ref_object.asset_id]
+ref_location = ref_object.position
+
+obj = object_state_ref_dict[list(object_state_ref_dict.keys())[1]]['object']
+new_object_name = GSO_dict[obj.asset_id]
+
+# 1st
+print('Generate the first scene.')
+# object_id = rng.choice(active_split)
+# object_id = object_id_list[-1]
+# obj = gso.create(asset_id=object_id)
+# scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+# obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+# obj.metadata["scale"] = scale
+
+# new_object_name = GSO_dict[obj.asset_id]
+# print('Add new object {}'.format(new_object_name))
+
+
+# scene = add_new_obj(scene, obj, ref_location1, ref_object, rng, max_trails=500)
+if scene is None:
+    exit()
+frame = renderer.render_still()
+
+edits = ['close', 'swap']
+edit = random.choice(edits)
+
+os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+caption_1 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], type="further" if edit == 'close' else 'swap')
+print(caption_1)
+
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_pos': obj.position,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann1.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann1.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image1.blend'.format(FLAGS.generate_idx))
+
+
+
+# 2nd
+print('Generate the second scene.')
+# delete the last object to generate the second frame
+# import pdb; pdb.set_trace()
+# scene.remove(obj)
+# scene= add_new_obj(scene, obj, ref_location2, ref_object, rng, max_trails=100)
+ref_obj_pos = ref_object.position
+ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+logging.info(f'Object position: {obj.position}')
+
+obj1_pos = obj.position
+obj2_pos = ref_location
+if edit == 'close':
+    direction = obj2_pos - obj1_pos
+    factor1, factor2 = random.uniform(0.1, 0.3), random.uniform(0.1, 0.3)
+    obj.position = obj1_pos + direction * factor1
+    ref_object.position = obj2_pos - direction * factor2
+else:
+    obj.position = obj2_pos
+    ref_object.position = obj1_pos
+
+frame = renderer.render_still()
+kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+caption_2 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], type="closer" if edit == 'close' else 'swap')
+print(caption_2)
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_pos': obj.position,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann2.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann2.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image2.blend'.format(FLAGS.generate_idx))
+
+
+# save json
+# local_ann = {'image0':"{}/image0.png".format(FLAGS.generate_idx), 'caption0':caption_1,
+#              'image1':"{}/image1.png".format(FLAGS.generate_idx), 'caption1':caption_2,
+#              'ann_path':"{}/ann.json".format(FLAGS.generate_idx),
+#              'obj_num':num_objects+1}
+# json.dump(local_ann, open("{}/{}/ann.json".format(str(output_dir), FLAGS.generate_idx), 'w'))
+
+# import pdb; pdb.set_trace()
+# if not os.path.exists("{}/global_ann.json".format(str(output_dir))):
+#     json.dump([], open("{}/global_ann.json".format(str(output_dir)), 'w'))
+# with open("{}/global_ann.json".format(str(output_dir)), 'r') as f:
+#     old_data = json.load(f)
+#     old_data.append(local_ann)
+# with open("{}/global_ann.json".format(str(output_dir)), "w") as f:
+#     json.dump(old_data, f)
+
+local_ann = [{
+        'input': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx), 
+        'output': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx), 
+        'instruction': caption_2,
+    },
+    {
+        'input': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx), 
+        'output': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx), 
+        'instruction': caption_1,
+    }
+]
+save_scene_instruction(f"{output_dir}/eq_kubric_{DATASET_TYPE}.json", local_ann, DATASET_TYPE, FLAGS.generate_idx)
+
+kb.done()

eq-kubric/my_kubric_twoframe_rotate.py

@@ -0,0 +1,590 @@
+# Copyright 2022 The Kubric Authors
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#    https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Worker file for the Multi-Object Video (MOVi) C (and CC) datasets.
+  * The number of objects is randomly chosen between
+    --min_num_objects (3) and --max_num_objects (10)
+  * The objects are randomly chosen from the Google Scanned Objects dataset
+
+  * Background is an random HDRI from the HDRI Haven dataset,
+    projected onto a Dome (half-sphere).
+    The HDRI is also used for lighting the scene.
+"""
+
+import logging
+
+import bpy
+import copy
+import os
+import kubric as kb
+from kubric.simulator import PyBullet
+from kubric.renderer import Blender
+import numpy as np
+import random
+import shutil
+
+from GSO_transfer import GSO_dict
+from utils import save_scene_instruction, dataset_dir
+
+# --- Some configuration values
+DATASET_TYPE = "rotate"
+# the region in which to place objects [(min), (max)]
+SPAWN_REGION = [(-8, -8, 0), (8, 8, 5)]
+SPAWN_REGION_OBJ = [[-6, -6, 0.5], [6, 6, 0.5]]
+VELOCITY_RANGE = [(-4., -4., 0.), (4., 4., 0.)]
+
+# --- CLI arguments
+parser = kb.ArgumentParser()
+parser.add_argument("--objects_split", choices=["train", "test"],
+                    default="train")
+# Configuration for the objects of the scene
+parser.add_argument("--min_num_objects", type=int, default=1,
+                    help="minimum number of objects")
+parser.add_argument("--max_num_objects", type=int, default=5,
+                    help="maximum number of objects")
+# Configuration for the floor and background
+parser.add_argument("--floor_friction", type=float, default=0.3)
+parser.add_argument("--floor_restitution", type=float, default=0.5)
+parser.add_argument("--backgrounds_split", choices=["train", "test"],
+                    default="train")
+
+parser.add_argument("--camera", choices=["fixed_random", "linear_movement"],
+                    default="fixed_random")
+parser.add_argument("--max_camera_movement", type=float, default=4.0)
+parser.add_argument("--smallest_scale", type=float, default=2.)
+parser.add_argument("--largest_scale", type=float, default=4.)
+
+# Configuration for the source of the assets
+parser.add_argument("--kubasic_assets", type=str,
+                    default="gs://kubric-public/assets/KuBasic/KuBasic.json")
+parser.add_argument("--hdri_assets", type=str,
+                    default="gs://kubric-public/assets/HDRI_haven/HDRI_haven.json")
+parser.add_argument("--gso_assets", type=str,
+                    default="gs://kubric-public/assets/GSO/GSO.json")
+parser.add_argument("--save_state", dest="save_state", action="store_true")
+parser.set_defaults(save_state=False, frame_end=24, frame_rate=12,
+                    resolution=512)
+parser.add_argument("--sub_outputdir", type=str, default="test sub output dir")
+parser.add_argument("--generate_idx", type=int, default=-1, help="generation idx")
+FLAGS = parser.parse_args()
+
+
+import pyquaternion as pyquat
+def default_rng():
+  return np.random.RandomState()
+
+import numpy as np
+
+def rotation(axis='Z', degrees=0):
+    """ Compute a specific rotation as a quaternion along a given axis by a specified degree.
+    
+    Args:
+        axis (str): Axis to rotate around ('X', 'Y', 'Z').
+        degrees (float): Angle in degrees to rotate around the specified axis.
+    
+    Returns:
+        tuple: Quaternion representing the rotation.
+    """
+    # Convert degrees to radians
+    degrees = degrees + random.uniform(-10, 10)
+    radians = np.radians(degrees)
+    
+    # Define axes
+    axis_vectors = {
+        'X': (1., 0., 0.),
+        'Y': (0., 1., 0.),
+        'Z': (0., 0., 1.)
+    }
+    
+    # Get the axis vector
+    axis_vector = axis_vectors.get(axis.upper(), (0., 0., 1.))  # Default to Z-axis if unspecified
+    
+    # Create the quaternion for the rotation
+    quat = pyquat.Quaternion(axis=axis_vector, angle=radians)
+    return tuple(quat)
+
+def random_rotation(axis=None, rng=default_rng()):
+  """ Compute a random rotation as a quaternion.
+  If axis is None the rotation is sampled uniformly over all possible orientations.
+  Otherwise it corresponds to a random rotation around the given axis."""
+
+  if axis is None:
+    # uniform across rotation space
+    # copied from pyquat.Quaternion.random to be able to use a custom rng
+    r1, r2, r3 = rng.random(3)
+
+    q1 = np.sqrt(1.0 - r1) * (np.sin(2 * np.pi * r2))
+    q2 = np.sqrt(1.0 - r1) * (np.cos(2 * np.pi * r2))
+    q3 = np.sqrt(r1) * (np.sin(2 * np.pi * r3))
+    q4 = np.sqrt(r1) * (np.cos(2 * np.pi * r3))
+
+    return q1, q2, q3, q4
+
+  else:
+    if isinstance(axis, str) and axis.upper() in ["X", "Y", "Z"]:
+      axis = {"X": (1., 0., 0.),
+              "Y": (0., 1., 0.),
+              "Z": (0., 0., 1.)}[axis.upper()]
+
+    # quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(0, 2*np.pi))
+    quat = pyquat.Quaternion(axis=axis, angle=rng.uniform(-0.5*np.pi, 0.5*np.pi)) # -0.5pi -- 0.5pi
+    return tuple(quat)
+
+
+from kubric.core import objects
+def rotation_sampler(axis=None):
+  def _sampler(obj: objects.PhysicalObject, rng):
+    obj.quaternion = random_rotation(axis=axis, rng=rng)
+  return _sampler
+
+
+def move_until_no_overlap(asset, simulator, spawn_region=((-1, -1, -1), (1, 1, 1)), max_trials=100,
+                          rng=default_rng()):
+  return kb.randomness.resample_while(asset,
+                        # samplers=[rotation_sampler(axis='Z'), kb.randomness.position_sampler(spawn_region)],
+                        samplers=[kb.randomness.position_sampler(spawn_region)],
+                        condition=simulator.check_overlap,
+                        max_trials=max_trials,
+                        rng=rng)
+
+
+def check_ok(obj, pos, region):
+    # import pdb; pdb.set_trace()
+    x, y, z = pos
+    if pos[0]<region[0][0] or pos[0]>region[1][0] or pos[1]<region[0][1] or pos[1]>region[1][1]: #or pos[2]<region[0][2] or  pos[2]>region[1][2]:
+        return False
+
+    if simulator.check_overlap(obj):
+        return False
+
+    return True
+
+
+def get_obj_x_left(bound, scale):
+    return -bound[0][0] * scale[0]
+
+def get_obj_x_right(bound, scale):
+    return bound[1][0] * scale[0]
+
+def get_obj_y_front(bound, scale):
+    return -bound[0][1] * scale[1]
+
+def get_obj_y_behind(bound, scale):
+    return bound[1][1] * scale[1]
+
+def get_obj_z(bound, scale):
+    return bound[0][2] * scale[2]
+
+def get_obj_z_up(bound, scale):
+    return bound[1][2] * scale[2]
+
+
+# def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object,  rng):
+#     obj_z = - get_obj_z(bounds, scale)
+#     # import pdb; pdb.set_trace()
+#     ref_x_left, ref_x_right, ref_y_front, ref_y_behind = get_obj_x_left(ref_object.bounds, ref_object.scale), get_obj_x_right(ref_object.bounds, ref_object.scale), get_obj_y_front(ref_object.bounds, ref_object.scale), get_obj_y_behind(ref_object.bounds, ref_object.scale)
+#     ref_x, ref_y, ref_z = ref_pos
+#     if ref_location == 'front':
+#         return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y-ref_y_front-6, ref_y-ref_y_front-2), obj_z+0.02]
+#     elif ref_location == 'behind':
+#         return [rng.uniform(ref_x-0.5, ref_x+0.5), rng.uniform(ref_y+ref_y_behind+2, ref_y+ref_y_behind+6), obj_z+0.02]
+#     elif ref_location == 'left':
+#         return [rng.uniform(ref_x-ref_x_left-6, ref_x-ref_x_left-2), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+#     elif ref_location == 'right':
+#         return [rng.uniform(ref_x+ref_x_right+2, ref_x+ref_x_right+6), rng.uniform(ref_y-0.5, ref_y+0.5), obj_z+0.02]
+#     elif ref_location == 'on':
+#         return [ref_x, ref_y, ref_z+ref_z_up+obj_z+1]
+
+def sample_unique_items(GSO_dict, num_samples):
+    unique_items = {}
+    sampled_values = set()    
+    active_keys = list(GSO_dict.keys())
+    
+    while len(unique_items) < num_samples:
+        key = random.choice(active_keys)
+        value = GSO_dict[key]
+        
+        if value not in sampled_values:
+            sampled_values.add(value)
+            unique_items[key] = value
+        
+        active_keys.remove(key)
+        if not active_keys:
+            break
+    
+    return list(unique_items.keys())
+
+
+def get_new_pos(bounds, scale, ref_location, ref_pos, ref_z_up, ref_object, rng):
+    # Calculate the z-position based on the object's bounds and scale
+    obj_z = -get_obj_z(bounds, scale) + 0.2  # Ensuring the object is slightly above the ground
+
+    # Extract the bounds from the SPAWN_REGION_OBJ variable
+    spawn_x_min, spawn_y_min, _ = SPAWN_REGION_OBJ[0]
+    spawn_x_max, spawn_y_max, _ = SPAWN_REGION_OBJ[1]
+
+    # Calculate the maximum offsets within the given spawn bounds
+    max_offset_x = spawn_x_max - spawn_x_min + 1
+    max_offset_y = spawn_y_max - spawn_y_min + 1
+
+    # Define absolute positions for each location using straightforward calculations
+    import random
+
+    locations = {
+        'closer': [ref_pos[0], max(spawn_y_min, ref_pos[1] - max_offset_y) * random.uniform(0.5, 1.2), obj_z],
+        'further away': [ref_pos[0], min(spawn_y_max, ref_pos[1] + max_offset_y) * random.uniform(0.5, 1.2), obj_z],
+        'further left': [max(spawn_x_min, ref_pos[0] - max_offset_x) * random.uniform(0.5, 1.2), ref_pos[1], obj_z],
+        'further right': [min(spawn_x_max, ref_pos[0] + max_offset_x) * random.uniform(0.5, 1.2), ref_pos[1], obj_z],
+    }
+
+    # Return the position for the specified location
+    return locations.get(ref_location, [ref_pos[0], ref_pos[1], obj_z])  # Default position if location is not specified
+
+def add_new_obj(scene, new_obj, ref_location, ref_object, rng, max_trails=50):
+
+    ref_obj_pos = ref_object.position
+    # import pdb; pdb.set_trace()
+    ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+    new_obj_pos = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+    new_obj.position = new_obj_pos
+    scene += new_obj
+
+    # import pdb; pdb.set_trace()
+    trails = 0
+    while not check_ok(new_obj, new_obj.position, SPAWN_REGION_OBJ):
+        trails += 1
+        # import pdb; pdb.set_trace()
+        new_obj.position = get_new_pos(new_obj.bounds, new_obj.scale, ref_location, ref_obj_pos, ref_obj_z_up, ref_object, rng)
+        # new_obj.quaternion = random_rotation(axis="Z", rng=rng)
+        if trails > max_trails:
+            print('cannot put the object, break')
+            # import pdb; pdb.set_trace()
+            return None
+    print('try {} times'.format(trails))
+    return scene
+
+def gen_caption(obj_name, obj_scale, ref_obj_name, ref_obj_scale, rotation):
+
+    if rotation == "flipped upside down":
+        captions = [f'the {obj_name} is flipped upside down', f'flip the {obj_name} upside down', f'Turn the {obj_name} upside down']
+    elif rotation == "turn around":
+        captions = [f'turn the {obj_name} around']
+    elif rotation == "turn left":
+        captions = [f'turn the {obj_name} 90 degrees', f'rotate the {obj_name} 90 degrees']
+    elif rotation == "turn right":
+        captions = [f'turn the {obj_name} 90 degrees', f'rotate the {obj_name} 90 degrees']
+    elif rotation == "fall down":
+        captions = [f'let the {obj_name} fall down', f'push the {obj_name} down', f'let the {obj_name} drop']
+    else:
+        captions = ['Fail']
+
+    # edit_verb = random.choice(['put', 'shift', 'move'])
+    # # caption = f'the{obj_size_exp} {obj_name} {verb_exp} {location_exp} the{ref_obj_size_exp} {ref_obj_name}'
+    # caption = f'{edit_verb} the {obj_name} {location_exp}'
+    
+    return captions[random.randint(0, len(captions)-1)]
+
+
+
+# --- Common setups & resources
+print('Generate {} Sample'.format(FLAGS.generate_idx))
+scene, rng, output_dir, scratch_dir = kb.setup(FLAGS)
+output_dir = output_dir / FLAGS.sub_outputdir
+
+
+
+simulator = PyBullet(scene, scratch_dir)
+renderer = Blender(scene, scratch_dir, samples_per_pixel=64)
+kubasic = kb.AssetSource.from_manifest(FLAGS.kubasic_assets)
+gso = kb.AssetSource.from_manifest(FLAGS.gso_assets)
+hdri_source = kb.AssetSource.from_manifest(FLAGS.hdri_assets)
+
+
+# --- Populate the scene
+# background HDRI
+train_backgrounds, test_backgrounds = hdri_source.get_test_split(fraction=0.)
+logging.info("Choosing one of the %d training backgrounds...", len(train_backgrounds))
+hdri_id = rng.choice(train_backgrounds)
+
+background_hdri = hdri_source.create(asset_id=hdri_id)
+#assert isinstance(background_hdri, kb.Texture)
+logging.info("Using background %s", hdri_id)
+scene.metadata["background"] = hdri_id
+renderer._set_ambient_light_hdri(background_hdri.filename)
+
+
+# Dome
+dome = kubasic.create(asset_id="dome", name="dome",
+                      friction=FLAGS.floor_friction,
+                      restitution=FLAGS.floor_restitution,
+                      static=True, background=True)
+assert isinstance(dome, kb.FileBasedObject)
+scene += dome
+dome_blender = dome.linked_objects[renderer]
+texture_node = dome_blender.data.materials[0].node_tree.nodes["Image Texture"]
+texture_node.image = bpy.data.images.load(background_hdri.filename)
+
+
+
+def get_linear_camera_motion_start_end(
+    movement_speed: float,
+    inner_radius: float = 8.,
+    outer_radius: float = 12.,
+    z_offset: float = 0.1,
+):
+  """Sample a linear path which starts and ends within a half-sphere shell."""
+  while True:
+    camera_start = np.array(kb.sample_point_in_half_sphere_shell(inner_radius,
+                                                                 outer_radius,
+                                                                 z_offset))
+    direction = rng.rand(3) - 0.5
+    movement = direction / np.linalg.norm(direction) * movement_speed
+    camera_end = camera_start + movement
+    if (inner_radius <= np.linalg.norm(camera_end) <= outer_radius and
+        camera_end[2] > z_offset):
+      return camera_start, camera_end
+
+
+# Camera
+logging.info("Setting up the Camera...")
+scene.camera = kb.PerspectiveCamera(focal_length=35., sensor_width=36)
+if FLAGS.camera == "fixed_random":
+    # scene.camera.position = kb.sample_point_in_half_sphere_shell(
+    #     inner_radius=7., outer_radius=9., offset=4)
+    y = 10 + rng.uniform(-1, 1)
+    z = 12 + rng.uniform(-3, 3)
+    scene.camera.position = (0, y, z)
+    scene.camera.look_at((0, 0, 0))
+elif FLAGS.camera == "linear_movement":
+    camera_start, camera_end = get_linear_camera_motion_start_end(
+      movement_speed=rng.uniform(low=0., high=FLAGS.max_camera_movement)
+    )
+    # linearly interpolate the camera position between these two points
+    # while keeping it focused on the center of the scene
+    # we start one frame early and end one frame late to ensure that
+    # forward and backward flow are still consistent for the last and first frames
+    for frame in range(FLAGS.frame_start - 1, FLAGS.frame_end + 2):
+        interp = ((frame - FLAGS.frame_start + 1) /
+                  (FLAGS.frame_end - FLAGS.frame_start + 3))
+        scene.camera.position = (interp * np.array(camera_start) +
+                                 (1 - interp) * np.array(camera_end))
+        scene.camera.look_at((0, 0, 0))
+        scene.camera.keyframe_insert("position", frame)
+        scene.camera.keyframe_insert("quaternion", frame)
+
+
+# Add random objects
+train_split, test_split = gso.get_test_split(fraction=0.)
+# if FLAGS.objects_split == "train":
+logging.info("Choosing one of the %d training objects...", len(train_split))
+# active_split = train_split
+active_split = list(GSO_dict.keys())
+
+num_objects = rng.randint(FLAGS.min_num_objects,
+                          FLAGS.max_num_objects+1 - 2)
+
+logging.info("Step 1: Randomly placing %d objects:", num_objects)
+object_state_save_dict = {}
+object_state_ref_dict = {}
+
+
+# not resample objects
+# object_id_list = random.sample(active_split, num_objects+1)
+object_id_list = sample_unique_items(GSO_dict, num_objects+1)
+
+
+for i in range(num_objects):
+    # object_id = rng.choice(active_split)
+    object_id = object_id_list[i]
+    obj = gso.create(asset_id=object_id)
+
+
+    assert isinstance(obj, kb.FileBasedObject)
+    scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+    obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+
+
+    obj_pos_z = - get_obj_z(obj.bounds, obj.scale)
+    SPAWN_REGION_OBJ[0][2], SPAWN_REGION_OBJ[1][2] = obj_pos_z, obj_pos_z
+    obj.position = rng.uniform(*SPAWN_REGION_OBJ)
+
+    obj.metadata["scale"] = scale
+    scene += obj
+    move_until_no_overlap(obj, simulator, spawn_region=SPAWN_REGION_OBJ, rng=rng)
+    # initialize velocity randomly but biased towards center
+    # obj.velocity = (rng.uniform(*VELOCITY_RANGE) -
+    #                 [obj.position[0], obj.position[1], 0])
+    # print(obj.position)
+    obj.velocity = [0, 0, 0]
+    logging.info("    Added %s at %s", obj.asset_id, obj.position)
+    object_state_save_dict[i] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+    object_state_ref_dict[i] = {'object': obj}
+
+
+ref_object = object_state_ref_dict[rng.choice(list(object_state_ref_dict.keys()))]['object'] # random choose an reference object
+ref_object_name = GSO_dict[ref_object.asset_id]
+ref_location = ref_object.position
+# random choose two location
+# LOC_SET = ['front', 'behind', 'left', 'right', 'on']
+LOC_SET = ['further right', 'further left', 'further away', 'closer']
+ref_location1 = random.sample(LOC_SET, 1)[0]
+if ref_location1 == 'further right':
+    ref_location2 = 'further left'
+elif ref_location1 == 'further left':
+    ref_location2 = 'further right'
+elif ref_location1 == 'further away':
+    ref_location2 = 'closer'
+elif ref_location1 == 'closer':
+    ref_location2 = 'further away'
+
+# 1st
+print('Generate the first scene.')
+# object_id = rng.choice(active_split)
+object_id = object_id_list[-1]
+obj = gso.create(asset_id=object_id)
+scale = rng.uniform(FLAGS.smallest_scale, FLAGS.largest_scale)
+obj.scale = scale / np.max(obj.bounds[1] - obj.bounds[0])
+obj.metadata["scale"] = scale
+
+new_object_name = GSO_dict[obj.asset_id]
+print('Add new object {}'.format(new_object_name))
+
+
+scene = add_new_obj(scene, obj, ref_location1, ref_object, rng, max_trails=500)
+if scene is None:
+    exit()
+frame = renderer.render_still()
+
+os.makedirs(output_dir/'{}'.format(FLAGS.generate_idx), exist_ok=True)
+kb.write_png(frame["rgba"], output_dir/"{}/image0.png".format(FLAGS.generate_idx))
+# caption_1 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], ref_location1)
+# print(caption_1)
+
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_pos': obj.position,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann1.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann1.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image1.blend'.format(FLAGS.generate_idx))
+
+
+
+# 2nd
+print('Generate the second scene.')
+# delete the last object to generate the second frame
+# import pdb; pdb.set_trace()
+# scene.remove(obj)
+# scene= add_new_obj(scene, obj, ref_location2, ref_object, rng, max_trails=100)
+ref_obj_pos = ref_object.position
+ref_obj_z_up = get_obj_z_up(ref_object.bounds, ref_object.scale)
+logging.info(f'Object position: {obj.position}')
+# new_obj_pos = get_new_pos(obj.bounds, obj.scale, ref_location2, obj.position, ref_obj_z_up, ref_object, rng)
+# logging.info(f'New object position: {new_obj_pos}')
+# obj.position = new_obj_pos
+
+text2rotation = {
+    "flipped upside down": [rotation(axis='X', degrees=180), rotation(axis='Y', degrees=180)],
+    # "turn around": [rotation(axis='Z', degrees=180)],
+    # "turn left": [rotation(axis='Z', degrees=-90)],
+    # "turn righ": [rotation(axis='Z', degrees=90)],
+    # "fall down": [rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90), rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90)]
+}
+
+nope = ['towel', 'cloth', 'tape']
+round_words = ['mug', 'bowl', 'plate', 'pot', 'saucer', 'hat', 'tape', 'mat', 'bottle', 'pan', 'ramekin']
+can_fall = ['pot', 'mug', 'figure', 'toy', 'boot', 'bottle', 'lamp', 'refrigerator']
+
+nope_cond, round_cond, fall_cond = False, False, False
+for token in new_object_name.split():
+    if token in nope:
+        nope_cond = True
+    if token in round_words:
+        round_cond = True
+    if token in can_fall:
+        fall_cond = True
+
+if nope_cond:
+    exit()
+
+if not round_cond:
+    text2rotation.update({
+        "turn around": [rotation(axis='Z', degrees=180)],
+        "turn left": [rotation(axis='Z', degrees=-90)],
+        "turn right": [rotation(axis='Z', degrees=90)]
+    })
+
+if fall_cond:
+    text2rotation.update({
+        "fall down": [rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90), rotation(axis='X', degrees=90), rotation(axis='Y', degrees=90)]
+    })
+
+sampled = random.sample(list(text2rotation.keys()), 1)
+rotation_func = text2rotation[sampled[0]][random.randint(0, len(sampled)-1)]
+obj.quaternion = rotation_func
+
+frame = renderer.render_still()
+kb.write_png(frame["rgba"], output_dir/"{}/image1.png".format(FLAGS.generate_idx))
+caption_2 = gen_caption(new_object_name, obj.metadata["scale"], ref_object_name, ref_object.metadata["scale"], sampled[0])
+print(caption_2)
+
+# save meta ann
+object_state_save_dict[i+1] = {'object_id': object_id,
+                               'object_scale': obj.scale,
+                               'object_pos': obj.position,
+                               'object_quaternion': obj.quaternion,
+                               'object_bounds': obj.bounds}
+# import json
+# json.dump(object_state_save_dict, open(output_dir/'{}/meta_ann2.json'.format(FLAGS.generate_idx), 'w'))
+# np.save(output_dir/'{}/meta_ann2.npy'.format(FLAGS.generate_idx), object_state_save_dict)
+# renderer.save_state(output_dir/'{}/image2.blend'.format(FLAGS.generate_idx))
+
+
+# save json
+# local_ann = {'image0':"{}/image0.png".format(FLAGS.generate_idx), 'caption0':caption_1,
+#              'image1':"{}/image1.png".format(FLAGS.generate_idx), 'caption1':caption_2,
+#              'ann_path':"{}/ann.json".format(FLAGS.generate_idx),
+#              'obj_num':num_objects+1}
+# json.dump(local_ann, open("{}/{}/ann.json".format(str(output_dir), FLAGS.generate_idx), 'w'))
+
+# import pdb; pdb.set_trace()
+# if not os.path.exists("{}/global_ann.json".format(str(output_dir))):
+#     json.dump([], open("{}/global_ann.json".format(str(output_dir)), 'w'))
+# with open("{}/global_ann.json".format(str(output_dir)), 'r') as f:
+#     old_data = json.load(f)
+#     old_data.append(local_ann)
+# with open("{}/global_ann.json".format(str(output_dir)), "w") as f:
+#     json.dump(old_data, f)
+
+local_ann = [{
+        'input': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx), 
+        'output': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx), 
+        'instruction': caption_2,
+    }
+    # {
+    #     'input': dataset_dir(DATASET_TYPE) + "{}/image1.png".format(FLAGS.generate_idx), 
+    #     'output': dataset_dir(DATASET_TYPE) + "{}/image0.png".format(FLAGS.generate_idx), 
+    #     'instruction': caption_1,
+    # }
+]
+save_scene_instruction(f"{output_dir}/eq_kubric_{DATASET_TYPE}.json", local_ann, DATASET_TYPE, FLAGS.generate_idx)
+
+kb.done()

eq-kubric/utils/__init__.py

@@ -0,0 +1,49 @@
+import os
+import shutil
+import json
+
+def setup_output_files(dataset_type: str) -> None:
+    """
+    Sets up the necessary directories and files for the script to run.
+    """
+    setup_logs()
+    start_output_file(dataset_type)
+
+def setup_logs(log_dir="logs") -> None:
+    """
+    Sets up the logging directory by removing it if it exists and then recreating it.
+    
+    Args:
+    log_dir (str): The path to the log directory to set up.
+    """
+    if os.path.exists(log_dir):
+        shutil.rmtree(log_dir)
+    os.makedirs(log_dir, exist_ok=True)
+
+def start_output_file(dataset_type: str) -> None:  
+    output_json = f"output/{dataset_type}/eq_kubric_{dataset_type}.json"
+    os.makedirs(f"output/{dataset_type}", exist_ok=True)
+    with open(output_json, "w") as response_file:
+        response_file.write("[\n")
+
+def end_output_file(dataset_type: str) -> None:  
+    output_json = f"output/{dataset_type}/eq_kubric_{dataset_type}.json"
+    with open(output_json, "ab+") as response_file:
+        response_file.seek(-2, os.SEEK_END)
+        response_file.truncate()
+        response_file.write(b"\n]")
+
+def dataset_dir(dataset_type: str) -> str:
+    return f"../../change_descriptions/eqmod/{dataset_type}/"
+
+def save_scene_instruction(output_file_path: str, entries: list, dataset_type: str, index: int, log_file="logs/error_log.txt") -> None:
+    try:
+        for entry in entries:
+            with open(output_file_path, "a") as file:
+                json_string = json.dumps(entry, indent=4)
+                indented_json_string = "\n    ".join(json_string.splitlines())
+                file.write(f"    {indented_json_string},\n")
+    except Exception as e:
+        error_message = f"{e}\nFailed to save a scene text: Index: {index+1}, Dataset Type: '{dataset_type}'."
+        with open(log_file, "a") as file:
+            file.write(f"{error_message}\n")

eval_disc_edit.py

@@ -0,0 +1,33 @@
+import json
+import math
+
+tasks = ['whatsup', 'something', 'ag', 'kubric', 'clevr']
+ckpts = [
+    'checkpoints_magic_reproduce_epoch=000047-step=000012999.ckpt_results.json',
+    'logs_logs_finetune_magicbrush_ag_something_kubric_15-15-1-1_init-magic_first_checkpoints_trainstep_checkpoints_step=000041999.ckpt_results.json'
+]
+
+for ckpt in ckpts:
+    print(ckpt)
+    skill_scores_latent_l2 = {task: [] for task in tasks}
+    for task in tasks:
+        results = json.load(open(f'itm_evaluation/test/{task}/{ckpt}'))
+        samples = 4
+
+        for idx, result in results.items():
+            pos_latent_l2s = result['pos']['latent_l2']
+            neg_latent_l2s = result['neg']['latent_l2']
+            if task == 'flickr_edit':
+                skills = result['task'].split(',')
+                skills = [skill.strip() for skill in skills]
+                for skill in skills:
+                    skill_scores_latent_l2[skill] += [1 if pos_latent_l2s[i] < neg_latent_l2s[i] else 0 for i in range(len(pos_latent_l2s))]
+            skill_scores_latent_l2[task] += [1 if pos_latent_l2s[i] < neg_latent_l2s[i] else 0 for i in range(len(pos_latent_l2s))]
+
+    # make latex row with each task's score
+    row = ''
+    for k, v in skill_scores_latent_l2.items():
+        final_score = sum(v) / len(v)
+        se = math.sqrt(final_score * (1 - final_score) / len(v))
+        row += f' & {final_score:.3f} \pm {se:.3f}'
+    print(row)

hf_push.py

@@ -0,0 +1,15 @@
+from huggingface_hub import HfApi
+
+model_name = "AURORA"
+
+api = HfApi()
+#api.create_repo("yfqiu-nlp/"+model_name.replace('+', '-'), repo_type="model")
+
+from huggingface_hub import HfApi
+
+api = HfApi()
+api.upload_large_folder(
+    folder_path='./',
+    repo_id="yfqiu-nlp/AURORA",
+    repo_type="dataset",
+)

main.py

@@ -0,0 +1,800 @@
+import argparse, os, sys, datetime, glob
+import numpy as np
+import time
+import torch
+import torchvision
+import pytorch_lightning as pl
+import json
+import pickle
+
+from packaging import version
+from omegaconf import OmegaConf
+from torch.utils.data import DataLoader, Dataset
+from functools import partial
+from PIL import Image
+
+import torch.distributed as dist
+from pytorch_lightning import seed_everything
+from pytorch_lightning.trainer import Trainer
+from pytorch_lightning.callbacks import ModelCheckpoint, Callback, LearningRateMonitor
+from pytorch_lightning.utilities.distributed import rank_zero_only
+from pytorch_lightning.utilities import rank_zero_info
+from pytorch_lightning.plugins import DDPPlugin
+
+sys.path.append("./stable_diffusion")
+
+from ldm.data.base import Txt2ImgIterableBaseDataset
+from ldm.util import instantiate_from_config
+
+
+def get_parser(**parser_kwargs):
+    def str2bool(v):
+        if isinstance(v, bool):
+            return v
+        if v.lower() in ("yes", "true", "t", "y", "1"):
+            return True
+        elif v.lower() in ("no", "false", "f", "n", "0"):
+            return False
+        else:
+            raise argparse.ArgumentTypeError("Boolean value expected.")
+
+    parser = argparse.ArgumentParser(**parser_kwargs)
+    parser.add_argument(
+        "-n",
+        "--name",
+        type=str,
+        const=True,
+        default="train",
+        nargs="?",
+        help="postfix for logdir",
+    )
+    parser.add_argument(
+        "-r",
+        "--resume",
+        type=str,
+        const=True,
+        default="",
+        nargs="?",
+        help="resume from logdir or checkpoint in logdir",
+    )
+    parser.add_argument(
+        "-b",
+        "--base",
+        nargs="*",
+        default='configs/finetune_magicbrush_ag_something_kubric_15-15-1-1_init-magic.yaml',
+        help="paths to base configs. Loaded from left-to-right."
+             "Parameters can be overwritten or added with command-line options of the form `--key value`.",
+    )
+    parser.add_argument(
+        "-t",
+        "--train",
+        type=str2bool,
+        const=True,
+        default=True,
+        nargs="?",
+        help="train",
+    )
+    parser.add_argument(
+        "--no-test",
+        type=str2bool,
+        const=True,
+        default=False,
+        nargs="?",
+        help="disable test",
+    )
+    parser.add_argument(
+        "-p",
+        "--project",
+        help="name of new or path to existing project"
+    )
+    parser.add_argument(
+        "-d",
+        "--debug",
+        type=str2bool,
+        nargs="?",
+        const=True,
+        default=False,
+        help="enable post-mortem debugging",
+    )
+    parser.add_argument(
+        "-s",
+        "--seed",
+        type=int,
+        default=23,
+        help="seed for seed_everything",
+    )
+    parser.add_argument(
+        "-f",
+        "--postfix",
+        type=str,
+        default="",
+        help="post-postfix for default name",
+    )
+    parser.add_argument(
+        "-l",
+        "--logdir",
+        type=str,
+        default="/mnt/research/scratch/bkroje/logs",
+        help="directory for logging dat shit",
+    )
+    parser.add_argument(
+        "--scale_lr",
+        action="store_true",
+        default=False,
+        help="scale base-lr by ngpu * batch_size * n_accumulate",
+    )
+    return parser
+
+
+def nondefault_trainer_args(opt):
+    parser = argparse.ArgumentParser()
+    parser = Trainer.add_argparse_args(parser)
+    args = parser.parse_args([])
+    return sorted(k for k in vars(args) if getattr(opt, k) != getattr(args, k))
+
+
+class WrappedDataset(Dataset):
+    """Wraps an arbitrary object with __len__ and __getitem__ into a pytorch dataset"""
+
+    def __init__(self, dataset):
+        self.data = dataset
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, idx):
+        return self.data[idx]
+
+
+def worker_init_fn(_):
+    worker_info = torch.utils.data.get_worker_info()
+
+    dataset = worker_info.dataset
+    worker_id = worker_info.id
+
+    if isinstance(dataset, Txt2ImgIterableBaseDataset):
+        split_size = dataset.num_records // worker_info.num_workers
+        # reset num_records to the true number to retain reliable length information
+        dataset.sample_ids = dataset.valid_ids[worker_id * split_size:(worker_id + 1) * split_size]
+        current_id = np.random.choice(len(np.random.get_state()[1]), 1)
+        return np.random.seed(np.random.get_state()[1][current_id] + worker_id)
+    else:
+        return np.random.seed(np.random.get_state()[1][0] + worker_id)
+
+
+class DataModuleFromConfig(pl.LightningDataModule):
+    def __init__(self, batch_size, train=None, validation=None, test=None, predict=None,
+                 wrap=False, num_workers=None, shuffle_test_loader=False, use_worker_init_fn=False,
+                 shuffle_val_dataloader=False):
+        super().__init__()
+        self.batch_size = batch_size
+        self.dataset_configs = dict()
+        self.num_workers = num_workers if num_workers is not None else batch_size * 2
+        self.use_worker_init_fn = use_worker_init_fn
+        if train is not None:
+            self.dataset_configs["train"] = train
+            self.train_dataloader = self._train_dataloader
+        if validation is not None:
+            self.dataset_configs["validation"] = validation
+            self.val_dataloader = partial(self._val_dataloader, shuffle=shuffle_val_dataloader)
+        if test is not None:
+            self.dataset_configs["test"] = test
+            self.test_dataloader = partial(self._test_dataloader, shuffle=shuffle_test_loader)
+        if predict is not None:
+            self.dataset_configs["predict"] = predict
+            self.predict_dataloader = self._predict_dataloader
+        self.wrap = wrap
+
+    def prepare_data(self):
+        for data_cfg in self.dataset_configs.values():
+            instantiate_from_config(data_cfg)
+
+    def setup(self, stage=None):
+        self.datasets = dict(
+            (k, instantiate_from_config(self.dataset_configs[k]))
+            for k in self.dataset_configs)
+        if self.wrap:
+            for k in self.datasets:
+                self.datasets[k] = WrappedDataset(self.datasets[k])
+
+    def _train_dataloader(self):
+        is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+        if is_iterable_dataset or self.use_worker_init_fn:
+            init_fn = worker_init_fn
+        else:
+            init_fn = None
+        return DataLoader(self.datasets["train"], batch_size=self.batch_size,
+                          num_workers=self.num_workers, shuffle=False if is_iterable_dataset else True,
+                          worker_init_fn=init_fn, persistent_workers=True)
+
+    def _val_dataloader(self, shuffle=False):
+        if isinstance(self.datasets['validation'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+            init_fn = worker_init_fn
+        else:
+            init_fn = None
+        return DataLoader(self.datasets["validation"],
+                          batch_size=self.batch_size,
+                          num_workers=self.num_workers,
+                          worker_init_fn=init_fn,
+                          shuffle=shuffle, persistent_workers=True)
+
+    def _test_dataloader(self, shuffle=False):
+        is_iterable_dataset = isinstance(self.datasets['train'], Txt2ImgIterableBaseDataset)
+        if is_iterable_dataset or self.use_worker_init_fn:
+            init_fn = worker_init_fn
+        else:
+            init_fn = None
+
+        # do not shuffle dataloader for iterable dataset
+        shuffle = shuffle and (not is_iterable_dataset)
+
+        return DataLoader(self.datasets["test"], batch_size=self.batch_size,
+                          num_workers=self.num_workers, worker_init_fn=init_fn, shuffle=shuffle, persistent_workers=True)
+
+    def _predict_dataloader(self, shuffle=False):
+        if isinstance(self.datasets['predict'], Txt2ImgIterableBaseDataset) or self.use_worker_init_fn:
+            init_fn = worker_init_fn
+        else:
+            init_fn = None
+        return DataLoader(self.datasets["predict"], batch_size=self.batch_size,
+                          num_workers=self.num_workers, worker_init_fn=init_fn, persistent_workers=True)
+
+
+class SetupCallback(Callback):
+    def __init__(self, resume, now, logdir, ckptdir, cfgdir, config, lightning_config):
+        super().__init__()
+        self.resume = resume
+        self.now = now
+        self.logdir = logdir
+        self.ckptdir = ckptdir
+        self.cfgdir = cfgdir
+        self.config = config
+        self.lightning_config = lightning_config
+
+    def on_keyboard_interrupt(self, trainer, pl_module):
+        if trainer.global_rank == 0:
+            print("Summoning checkpoint.")
+            ckpt_path = os.path.join(self.ckptdir, "last.ckpt")
+            trainer.save_checkpoint(ckpt_path)
+
+    def on_pretrain_routine_start(self, trainer, pl_module):
+        if trainer.global_rank == 0:
+            # Create logdirs and save configs
+            # os.makedirs(self.logdir, exist_ok=True)
+            # os.makedirs(self.ckptdir, exist_ok=True)
+            # os.makedirs(self.cfgdir, exist_ok=True)
+
+            if "callbacks" in self.lightning_config:
+                if 'metrics_over_trainsteps_checkpoint' in self.lightning_config['callbacks']:
+                    os.makedirs(os.path.join(self.ckptdir, 'trainstep_checkpoints'), exist_ok=True)
+            print("Project config")
+            print(OmegaConf.to_yaml(self.config))
+            OmegaConf.save(self.config,
+                           os.path.join(self.cfgdir, "{}-project.yaml".format(self.now)))
+
+            print("Lightning config")
+            print(OmegaConf.to_yaml(self.lightning_config))
+            OmegaConf.save(OmegaConf.create({"lightning": self.lightning_config}),
+                           os.path.join(self.cfgdir, "{}-lightning.yaml".format(self.now)))
+
+def get_world_size():
+    if not dist.is_available():
+        return 1
+    if not dist.is_initialized():
+        return 1
+    return dist.get_world_size()
+
+def all_gather(data):
+    """
+    Run all_gather on arbitrary picklable data (not necessarily tensors)
+    Args:
+        data: any picklable object
+    Returns:
+        list[data]: list of data gathered from each rank
+    """
+    world_size = get_world_size()
+    if world_size == 1:
+        return [data]
+
+    # serialized to a Tensor
+    origin_size = None
+    if not isinstance(data, torch.Tensor):
+        buffer = pickle.dumps(data)
+        storage = torch.ByteStorage.from_buffer(buffer)
+        tensor = torch.ByteTensor(storage).to("cuda")
+    else:
+        origin_size = data.size()
+        tensor = data.reshape(-1)
+
+    tensor_type = tensor.dtype
+
+    # obtain Tensor size of each rank
+    local_size = torch.LongTensor([tensor.numel()]).to("cuda")
+    size_list = [torch.LongTensor([0]).to("cuda") for _ in range(world_size)]
+    dist.all_gather(size_list, local_size)
+    size_list = [int(size.item()) for size in size_list]
+    max_size = max(size_list)
+
+    # receiving Tensor from all ranks
+    # we pad the tensor because torch all_gather does not support
+    # gathering tensors of different shapes
+    tensor_list = []
+    for _ in size_list:
+        tensor_list.append(torch.FloatTensor(size=(max_size,)).cuda().to(tensor_type))
+    if local_size != max_size:
+        padding = torch.FloatTensor(size=(max_size - local_size,)).cuda().to(tensor_type)
+        tensor = torch.cat((tensor, padding), dim=0)
+    dist.all_gather(tensor_list, tensor)
+
+    data_list = []
+    for size, tensor in zip(size_list, tensor_list):
+        if origin_size is None:
+            buffer = tensor.cpu().numpy().tobytes()[:size]
+            data_list.append(pickle.loads(buffer))
+        else:
+            buffer = tensor[:size]
+            data_list.append(buffer)
+
+    if origin_size is not None:
+        new_shape = [-1] + list(origin_size[1:])
+        resized_list = []
+        for data in data_list:
+            # suppose the difference of tensor size exist in first dimension
+            data = data.reshape(new_shape)
+            resized_list.append(data)
+
+        return resized_list
+    else:
+        return data_list
+
+class ImageLogger(Callback):
+    def __init__(self, batch_frequency, max_images, clamp=True, increase_log_steps=True,
+                 rescale=True, disabled=False, log_on_batch_idx=False, log_first_step=False,
+                 log_images_kwargs=None):
+        super().__init__()
+        self.rescale = rescale
+        self.batch_freq = batch_frequency
+        self.max_images = max_images
+        self.logger_log_images = {
+            pl.loggers.TestTubeLogger: self._testtube,
+        }
+        self.log_steps = [2 ** n for n in range(6, int(np.log2(self.batch_freq)) + 1)]
+        if not increase_log_steps:
+            self.log_steps = [self.batch_freq]
+        self.clamp = clamp
+        self.disabled = disabled
+        self.log_on_batch_idx = log_on_batch_idx
+        self.log_images_kwargs = log_images_kwargs if log_images_kwargs else {}
+        self.log_first_step = log_first_step
+
+    @rank_zero_only
+    def _testtube(self, pl_module, images, batch_idx, split):
+        for k in images:
+            grid = torchvision.utils.make_grid(images[k])
+            grid = (grid + 1.0) / 2.0  # -1,1 -> 0,1; c,h,w
+
+            tag = f"{split}/{k}"
+            pl_module.logger.experiment.add_image(
+                tag, grid,
+                global_step=pl_module.global_step)
+
+    @rank_zero_only
+    def log_local(self, save_dir, split, images, prompts,
+                  global_step, current_epoch, batch_idx):
+        root = os.path.join(save_dir, "images", split)
+        names = {"reals": "before", "inputs": "after", "reconstruction": "before-vq", "samples": "after-gen"}
+        # print(root)
+        for k in images:
+            grid = torchvision.utils.make_grid(images[k], nrow=8)
+            if self.rescale:
+                grid = (grid + 1.0) / 2.0  # -1,1 -> 0,1; c,h,w
+            grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
+            grid = grid.numpy()
+            grid = (grid * 255).astype(np.uint8)
+            filename = "global_step-{:06}_epoch-{:06}_batch-{:06}_{}.png".format(
+                global_step,
+                current_epoch,
+                batch_idx,
+                names[k])
+            path = os.path.join(root, filename)
+            os.makedirs(os.path.split(path)[0], exist_ok=True)
+            # print(path)
+            Image.fromarray(grid).save(path)
+
+        filename = "global_step-{:06}_epoch-{:06}_batch-{:06}_prompt.json".format(
+            global_step,
+            current_epoch,
+            batch_idx)
+        path = os.path.join(root, filename)
+        with open(path, "w") as f:
+            for p in prompts:
+                f.write(f"{json.dumps(p)}\n")
+
+    def log_img(self, pl_module, batch, batch_idx, split="train"):
+        check_idx = batch_idx if self.log_on_batch_idx else pl_module.global_step
+        if (self.check_frequency(check_idx) and  # batch_idx % self.batch_freq == 0
+                hasattr(pl_module, "log_images") and
+                callable(pl_module.log_images) and
+                self.max_images > 0) or (split == "val" and batch_idx == 0):
+            logger = type(pl_module.logger)
+
+            is_train = pl_module.training
+            if is_train:
+                pl_module.eval()
+
+            with torch.no_grad():
+                images = pl_module.log_images(batch, split=split, **self.log_images_kwargs)
+
+            prompts = batch["edit"]["c_crossattn"][:self.max_images]
+            prompts = [p for ps in all_gather(prompts) for p in ps]
+
+            for k in images:
+                N = min(images[k].shape[0], self.max_images)
+                images[k] = images[k][:N]
+                images[k] = torch.cat(all_gather(images[k][:N]))
+                if isinstance(images[k], torch.Tensor):
+                    images[k] = images[k].detach().cpu()
+                    if self.clamp:
+                        images[k] = torch.clamp(images[k], -1., 1.)
+
+            self.log_local(pl_module.logger.save_dir, split, images, prompts,
+                           pl_module.global_step, pl_module.current_epoch, batch_idx)
+
+            logger_log_images = self.logger_log_images.get(logger, lambda *args, **kwargs: None)
+            logger_log_images(pl_module, images, pl_module.global_step, split)
+
+            if is_train:
+                pl_module.train()
+
+    def check_frequency(self, check_idx):
+        if ((check_idx % self.batch_freq) == 0 or (check_idx in self.log_steps)) and (
+                check_idx > 0 or self.log_first_step):
+            if len(self.log_steps) > 0:
+                self.log_steps.pop(0)
+            return True
+        return False
+
+    # def on_train_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+    #     if not self.disabled and (pl_module.global_step > 0 or self.log_first_step):
+    #         self.log_img(pl_module, batch, batch_idx, split="train")
+
+    # def on_validation_batch_end(self, trainer, pl_module, outputs, batch, batch_idx, dataloader_idx):
+    #     if not self.disabled and pl_module.global_step > 0:
+    #         self.log_img(pl_module, batch, batch_idx, split="val")
+    #     if hasattr(pl_module, 'calibrate_grad_norm'):
+    #         if (pl_module.calibrate_grad_norm and batch_idx % 25 == 0) and batch_idx > 0:
+    #             self.log_gradients(trainer, pl_module, batch_idx=batch_idx)
+
+
+class CUDACallback(Callback):
+    # see https://github.com/SeanNaren/minGPT/blob/master/mingpt/callback.py
+    def on_train_epoch_start(self, trainer, pl_module):
+        # Reset the memory use counter
+        torch.cuda.reset_peak_memory_stats(trainer.root_gpu)
+        torch.cuda.synchronize(trainer.root_gpu)
+        self.start_time = time.time()
+
+    def on_train_epoch_end(self, trainer, pl_module, outputs):
+        torch.cuda.synchronize(trainer.root_gpu)
+        max_memory = torch.cuda.max_memory_allocated(trainer.root_gpu) / 2 ** 20
+        epoch_time = time.time() - self.start_time
+
+        try:
+            max_memory = trainer.training_type_plugin.reduce(max_memory)
+            epoch_time = trainer.training_type_plugin.reduce(epoch_time)
+
+            rank_zero_info(f"Average Epoch time: {epoch_time:.2f} seconds")
+            rank_zero_info(f"Average Peak memory {max_memory:.2f}MiB")
+        except AttributeError:
+            pass
+
+
+if __name__ == "__main__":
+    # custom parser to specify config files, train, test and debug mode,
+    # postfix, resume.
+    # `--key value` arguments are interpreted as arguments to the trainer.
+    # `nested.key=value` arguments are interpreted as config parameters.
+    # configs are merged from left-to-right followed by command line parameters.
+
+    # model:
+    #   base_learning_rate: float
+    #   target: path to lightning module
+    #   params:
+    #       key: value
+    # data:
+    #   target: main.DataModuleFromConfig
+    #   params:
+    #      batch_size: int
+    #      wrap: bool
+    #      train:
+    #          target: path to train dataset
+    #          params:
+    #              key: value
+    #      validation:
+    #          target: path to validation dataset
+    #          params:
+    #              key: value
+    #      test:
+    #          target: path to test dataset
+    #          params:
+    #              key: value
+    # lightning: (optional, has sane defaults and can be specified on cmdline)
+    #   trainer:
+    #       additional arguments to trainer
+    #   logger:
+    #       logger to instantiate
+    #   modelcheckpoint:
+    #       modelcheckpoint to instantiate
+    #   callbacks:
+    #       callback1:
+    #           target: importpath
+    #           params:
+    #               key: value
+
+    now = datetime.datetime.now().strftime("%Y-%m-%dT%H-%M-%S")
+
+    # add cwd for convenience and to make classes in this file available when
+    # running as `python main.py`
+    # (in particular `main.DataModuleFromConfig`)
+    sys.path.append(os.getcwd())
+
+    parser = get_parser()
+    parser = Trainer.add_argparse_args(parser)
+
+    opt, unknown = parser.parse_known_args()
+
+    assert opt.name
+    cfg_fname = os.path.split(opt.base[0])[-1]
+    cfg_name = os.path.splitext(cfg_fname)[0]
+    nowname = f"{cfg_name}_{opt.name}"
+    logdir = os.path.join(opt.logdir, nowname)
+    ckpt = os.path.join(logdir, "checkpoints", "last.ckpt")
+    resume = False
+
+    if os.path.isfile(ckpt):
+        opt.resume_from_checkpoint = ckpt
+        base_configs = sorted(glob.glob(os.path.join(logdir, "configs/*.yaml")))
+        opt.base = base_configs + opt.base
+        _tmp = logdir.split("/")
+        nowname = _tmp[-1]
+        resume = True
+
+    ckptdir = os.path.join(logdir, "checkpoints")
+    cfgdir = os.path.join(logdir, "configs")
+
+    os.makedirs(logdir, exist_ok=True)
+    os.makedirs(ckptdir, exist_ok=True)
+    os.makedirs(cfgdir, exist_ok=True)
+
+    try:
+        # init and save configs
+        configs = [OmegaConf.load(opt.base)]
+        cli = OmegaConf.from_dotlist(unknown)
+        config = OmegaConf.merge(*configs, cli)
+
+        if resume:
+            # By default, when finetuning from Stable Diffusion, we load the EMA-only checkpoint to initialize all weights.
+            # If resuming InstructPix2Pix from a finetuning checkpoint, instead load both EMA and non-EMA weights.
+            config.model.params.load_ema = True
+
+        lightning_config = config.pop("lightning", OmegaConf.create())
+        # merge trainer cli with config
+        trainer_config = lightning_config.get("trainer", OmegaConf.create())
+        # default to ddp
+        trainer_config["accelerator"] = "ddp"
+        for k in nondefault_trainer_args(opt):
+            trainer_config[k] = getattr(opt, k)
+        if not "gpus" in trainer_config:
+            del trainer_config["accelerator"]
+            cpu = True
+        else:
+            gpuinfo = trainer_config["gpus"]
+            print(f"Running on GPUs {gpuinfo}")
+            cpu = False
+        trainer_opt = argparse.Namespace(**trainer_config)
+        lightning_config.trainer = trainer_config
+
+        # model
+        model = instantiate_from_config(config.model)
+
+        # trainer and callbacks
+        trainer_kwargs = dict()
+
+        # default logger configs
+        default_logger_cfgs = {
+            "wandb": {
+                "target": "pytorch_lightning.loggers.WandbLogger",
+                "params": {
+                    "name": nowname,
+                    "save_dir": logdir,
+                    "id": nowname,
+                }
+            },
+            "testtube": {
+                "target": "pytorch_lightning.loggers.TestTubeLogger",
+                "params": {
+                    "name": "testtube",
+                    "save_dir": logdir,
+                }
+            },
+        }
+        default_logger_cfg = default_logger_cfgs["wandb"]
+        if "logger" in lightning_config:
+            logger_cfg = lightning_config.logger
+        else:
+            logger_cfg = OmegaConf.create()
+        logger_cfg = OmegaConf.merge(default_logger_cfg, logger_cfg)
+        trainer_kwargs["logger"] = instantiate_from_config(logger_cfg)
+
+        # modelcheckpoint - use TrainResult/EvalResult(checkpoint_on=metric) to
+        # specify which metric is used to determine best models
+        default_modelckpt_cfg = {
+            "target": "pytorch_lightning.callbacks.ModelCheckpoint",
+            "params": {
+                "dirpath": ckptdir,
+                "filename": "{epoch:06}",
+                'filename': 'last',
+                "verbose": True,
+                "save_last": True,
+                "save_top_k": 0,
+            }
+        }
+
+        if "modelcheckpoint" in lightning_config:
+            modelckpt_cfg = lightning_config.modelcheckpoint
+        else:
+            modelckpt_cfg =  OmegaConf.create()
+        modelckpt_cfg = OmegaConf.merge(default_modelckpt_cfg, modelckpt_cfg)
+        print(f"Merged modelckpt-cfg: \n{modelckpt_cfg}")
+        if version.parse(pl.__version__) < version.parse('1.4.0'):
+            trainer_kwargs["checkpoint_callback"] = instantiate_from_config(modelckpt_cfg)
+
+        # add callback which sets up log directory
+        default_callbacks_cfg = {
+            "setup_callback": {
+                "target": "main.SetupCallback",
+                "params": {
+                    "resume": opt.resume,
+                    "now": now,
+                    "logdir": logdir,
+                    "ckptdir": ckptdir,
+                    "cfgdir": cfgdir,
+                    "config": config,
+                    "lightning_config": lightning_config,
+                }
+            },
+            "image_logger": {
+                "target": "main.ImageLogger",
+                "params": {
+                    "batch_frequency": 750,
+                    "max_images": 8,
+                    "clamp": True
+                }
+            },
+            "learning_rate_logger": {
+                "target": "main.LearningRateMonitor",
+                "params": {
+                    "logging_interval": "step",
+                    # "log_momentum": True
+                }
+            },
+            "cuda_callback": {
+                "target": "main.CUDACallback"
+            },
+        }
+        if version.parse(pl.__version__) >= version.parse('1.4.0'):
+            default_callbacks_cfg.update({'checkpoint_callback': modelckpt_cfg})
+
+        if "callbacks" in lightning_config:
+            callbacks_cfg = lightning_config.callbacks
+        else:
+            callbacks_cfg = OmegaConf.create()
+
+        print(
+            'Caution: Saving checkpoints every n train steps without deleting. This might require some free space.')
+        default_metrics_over_trainsteps_ckpt_dict = {
+            'metrics_over_trainsteps_checkpoint': {
+                "target": 'pytorch_lightning.callbacks.ModelCheckpoint',
+                'params': {
+                    "dirpath": os.path.join(ckptdir, 'trainstep_checkpoints'),
+                    "filename": "{epoch:06}-{step:09}",
+                    "verbose": True,
+                    'save_top_k': -1,
+                    'every_n_train_steps': 1000,
+                    'save_weights_only': True
+                }
+            }
+        }
+        default_callbacks_cfg.update(default_metrics_over_trainsteps_ckpt_dict)
+
+        callbacks_cfg = OmegaConf.merge(default_callbacks_cfg, callbacks_cfg)
+        if 'ignore_keys_callback' in callbacks_cfg and hasattr(trainer_opt, 'resume_from_checkpoint'):
+            callbacks_cfg.ignore_keys_callback.params['ckpt_path'] = trainer_opt.resume_from_checkpoint
+        elif 'ignore_keys_callback' in callbacks_cfg:
+            del callbacks_cfg['ignore_keys_callback']
+
+        trainer_kwargs["callbacks"] = [instantiate_from_config(callbacks_cfg[k]) for k in callbacks_cfg]
+
+        trainer = Trainer.from_argparse_args(trainer_opt, plugins=DDPPlugin(find_unused_parameters=False), **trainer_kwargs)
+        trainer.logdir = logdir  ###
+
+        # data
+        data = instantiate_from_config(config.data)
+        # NOTE according to https://pytorch-lightning.readthedocs.io/en/latest/datamodules.html
+        # calling these ourselves should not be necessary but it is.
+        # lightning still takes care of proper multiprocessing though
+        data.prepare_data()
+        data.setup()
+        print("#### Data #####")
+        for k in data.datasets:
+            print(f"{k}, {data.datasets[k].__class__.__name__}, {len(data.datasets[k])}")
+
+        # configure learning rate
+        bs, base_lr = config.data.params.batch_size, config.model.base_learning_rate
+        if not cpu:
+            ngpu = len(lightning_config.trainer.gpus.strip(",").split(','))
+        else:
+            ngpu = 1
+        if 'accumulate_grad_batches' in lightning_config.trainer:
+            accumulate_grad_batches = lightning_config.trainer.accumulate_grad_batches
+        else:
+            accumulate_grad_batches = 1
+        print(f"accumulate_grad_batches = {accumulate_grad_batches}")
+        lightning_config.trainer.accumulate_grad_batches = accumulate_grad_batches
+        if opt.scale_lr:
+            model.learning_rate = accumulate_grad_batches * ngpu * bs * base_lr
+            print(
+                "Setting learning rate to {:.2e} = {} (accumulate_grad_batches) * {} (num_gpus) * {} (batchsize) * {:.2e} (base_lr)".format(
+                    model.learning_rate, accumulate_grad_batches, ngpu, bs, base_lr))
+        else:
+            model.learning_rate = base_lr
+            print("++++ NOT USING LR SCALING ++++")
+            print(f"Setting learning rate to {model.learning_rate:.2e}")
+
+
+        # allow checkpointing via USR1
+        def melk(*args, **kwargs):
+            # run all checkpoint hooks
+            if trainer.global_rank == 0:
+                print("Summoning checkpoint.")
+                ckpt_path = os.path.join(ckptdir, "last.ckpt")
+                trainer.save_checkpoint(ckpt_path)
+
+
+        def divein(*args, **kwargs):
+            if trainer.global_rank == 0:
+                import pudb;
+                pudb.set_trace()
+
+
+        import signal
+
+        signal.signal(signal.SIGUSR1, melk)
+        signal.signal(signal.SIGUSR2, divein)
+
+        # run
+        if opt.train:
+            try:
+                trainer.fit(model, data)
+            except Exception:
+                melk()
+                raise
+        if not opt.no_test and not trainer.interrupted:
+            trainer.test(model, data)
+    except Exception:
+        if opt.debug and trainer.global_rank == 0:
+            try:
+                import pudb as debugger
+            except ImportError:
+                import pdb as debugger
+            debugger.post_mortem()
+        raise
+    finally:
+        # move newly created debug project to debug_runs
+        if opt.debug and not opt.resume and trainer.global_rank == 0:
+            dst, name = os.path.split(logdir)
+            dst = os.path.join(dst, "debug_runs", name)
+            os.makedirs(os.path.split(dst)[0], exist_ok=True)
+            os.rename(logdir, dst)
+        if trainer.global_rank == 0:
+            print(trainer.profiler.summary())

requirements.txt

@@ -0,0 +1,229 @@
+absl-py==2.0.0
+accelerate==0.26.1
+addict==2.4.0
+aiofiles==23.2.1
+aiohttp==3.9.1
+aiosignal==1.3.1
+albumentations==0.4.3
+altair==5.2.0
+annotated-types==0.6.0
+antlr4-python3-runtime==4.8
+anyio==4.2.0
+appdirs==1.4.4
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==23.2.0
+beautifulsoup4==4.12.2
+blinker==1.7.0
+cachetools==5.3.2
+certifi==2023.11.17
+charset-normalizer==3.3.2
+clean-fid==0.1.35
+click==8.1.7
+-e git+https://github.com/openai/CLIP.git@a1d071733d7111c9c014f024669f959182114e33#egg=clip
+clip-anytorch==2.5.2
+cmake==3.28.1
+colorama==0.4.6
+contourpy==1.2.0
+cycler==0.12.1
+datasets==2.17.1
+dctorch==0.1.2
+diffusers==0.25.0
+dill==0.3.6
+distro==1.9.0
+docker-pycreds==0.4.0
+easydict==1.12
+einops==0.3.0
+exceptiongroup==1.2.0
+executing==2.0.1
+facexlib==0.3.0
+fancycompleter==0.9.1
+fastapi==0.109.0
+ffmpy==0.3.1
+filelock==3.13.1
+filterpy==1.4.5
+fonttools==4.47.2
+frozenlist==1.4.1
+fschat==0.2.35
+fsspec==2023.10.0
+ftfy==6.1.3
+future==0.18.3
+gdown==4.7.1
+gitdb==4.0.11
+GitPython==3.1.41
+google-auth==2.26.2
+google-auth-oauthlib==1.2.0
+gradio==3.50.2
+gradio_client==0.6.1
+grpcio==1.60.0
+h11==0.14.0
+httpcore==1.0.2
+httpx==0.26.0
+huggingface-hub==0.20.2
+icecream==2.1.3
+idna==3.6
+imageio==2.9.0
+imageio-ffmpeg==0.4.2
+imgaug==0.2.6
+importlib-metadata==7.0.1
+importlib-resources==6.1.1
+inquirerpy==0.3.4
+invisible-watermark==0.2.0
+Jinja2==3.1.3
+joblib==1.4.2
+jsonmerge==1.9.2
+jsonschema==4.20.0
+jsonschema-specifications==2023.12.1
+k-diffusion @ git+https://github.com/crowsonkb/k-diffusion.git@cc49cf6182284e577e896943f8e29c7c9d1a7f2c
+kiwisolver==1.4.5
+kornia==0.6.0
+lazy_loader==0.3
+lit==17.0.6
+llvmlite==0.42.0
+lmdb==1.4.1
+Markdown==3.5.2
+markdown-it-py==3.0.0
+markdown2==2.4.12
+MarkupSafe==2.1.3
+matplotlib==3.8.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.0.4
+multiprocess==0.70.14
+networkx==3.2.1
+nh3==0.2.15
+numba==0.59.1
+numpy==1.24.4
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu11==11.7.101
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu11==8.5.0.96
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu11==10.9.0.58
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu11==10.2.10.91
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu11==11.4.0.1
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu11==11.7.4.91
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu11==2.14.3
+nvidia-nccl-cu12==2.18.1
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu11==11.7.91
+nvidia-nvtx-cu12==12.1.105
+oauthlib==3.2.2
+omegaconf==2.1.1
+open-clip-torch==2.24.0
+openai==1.7.0
+openai-clip==1.0.1
+opencv-python==4.9.0.80
+opencv-python-headless==4.9.0.80
+orjson==3.9.10
+packaging==23.2
+pandas==2.1.4
+patsy==0.5.6
+peft==0.8.1
+pfzy==0.3.4
+pillow==10.2.0
+platformdirs==4.2.1
+prompt-toolkit==3.0.43
+protobuf==4.23.4
+psutil==5.9.7
+pudb==2019.2
+pyarrow==14.0.2
+pyarrow-hotfix==0.6
+pyasn1==0.5.1
+pyasn1-modules==0.3.0
+pydantic==1.10.14
+pydantic_core==2.14.6
+pydeck==0.8.1b0
+pyDeprecate==0.3.1
+pydub==0.25.1
+Pygments==2.17.2
+pyiqa==0.1.11
+pyparsing==3.1.1
+pyrepl==0.9.0
+PySocks==1.7.1
+python-dateutil==2.8.2
+python-multipart==0.0.6
+pytorch-lightning==1.4.2
+pytube==15.0.0
+pytz==2023.3.post1
+PyWavelets==1.5.0
+PyYAML==6.0.1
+referencing==0.32.1
+regex==2023.12.25
+requests==2.31.0
+requests-oauthlib==1.3.1
+responses==0.18.0
+rich==13.7.0
+rpds-py==0.16.2
+rsa==4.9
+safetensors==0.4.1
+scikit-image==0.20.0
+scipy==1.9.1
+seaborn==0.13.1
+semantic-version==2.10.0
+sentencepiece==0.1.99
+sentry-sdk==1.39.2
+setproctitle==1.3.3
+shellingham==1.5.4
+shortuuid==1.0.11
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.0
+soupsieve==2.5
+starlette==0.35.1
+statsmodels==0.14.2
+streamlit==1.30.0
+svgwrite==1.4.3
+sympy==1.12
+-e git+https://github.com/CompVis/taming-transformers.git@master#egg=taming-transformers
+tenacity==8.2.3
+tensorboard==2.15.1
+tensorboard-data-server==0.7.2
+test_tube==0.7.5
+tifffile==2023.12.9
+tiktoken==0.5.2
+timm==0.9.12
+tokenizers==0.15.1
+toml==0.10.2
+tomli==2.0.1
+tomlkit==0.12.0
+toolz==0.12.0
+torch==2.0.1
+torch-fidelity==0.3.0
+torchdiffeq==0.2.3
+torchmetrics==0.6.0
+torchsde==0.2.6
+torchvision==0.15.2
+tornado==6.4
+tqdm==4.66.1
+trampoline==0.1.2
+transformers==4.37.2
+triton==2.0.0
+typer==0.9.0
+typing_extensions==4.9.0
+tzdata==2023.4
+tzlocal==5.2
+urllib3==2.1.0
+urwid==2.4.2
+uvicorn==0.25.0
+validators==0.22.0
+wandb==0.16.3
+watchdog==3.0.0
+wavedrom==2.0.3.post3
+wcwidth==0.2.13
+websockets==11.0.3
+Werkzeug==3.0.1
+wmctrl==0.5
+xxhash==3.4.1
+yapf==0.40.2
+yarl==1.9.4
+zipp==3.17.0

stable_diffusion/LICENSE

@@ -0,0 +1,82 @@
+Copyright (c) 2022 Robin Rombach and Patrick Esser and contributors
+
+CreativeML Open RAIL-M
+dated August 22, 2022
+
+Section I: PREAMBLE
+
+Multimodal generative models are being widely adopted and used, and have the potential to transform the way artists, among other individuals, conceive and benefit from AI or ML technologies as a tool for content creation.
+
+Notwithstanding the current and potential benefits that these artifacts can bring to society at large, there are also concerns about potential misuses of them, either due to their technical limitations or ethical considerations.
+
+In short, this license strives for both the open and responsible downstream use of the accompanying model. When it comes to the open character, we took inspiration from open source permissive licenses regarding the grant of IP rights. Referring to the downstream responsible use, we added use-based restrictions not permitting the use of the Model in very specific scenarios, in order for the licensor to be able to enforce the license in case potential misuses of the Model may occur. At the same time, we strive to promote open and responsible research on generative models for art and content generation.
+
+Even though downstream derivative versions of the model could be released under different licensing terms, the latter will always have to include - at minimum - the same use-based restrictions as the ones in the original license (this license). We believe in the intersection between open and responsible AI development; thus, this License aims to strike a balance between both in order to enable responsible open-science in the field of AI.
+
+This License governs the use of the model (and its derivatives) and is informed by the model card associated with the model.
+
+NOW THEREFORE, You and Licensor agree as follows:
+
+1. Definitions
+
+- "License" means the terms and conditions for use, reproduction, and Distribution as defined in this document.
+- "Data" means a collection of information and/or content extracted from the dataset used with the Model, including to train, pretrain, or otherwise evaluate the Model. The Data is not licensed under this License.
+- "Output" means the results of operating a Model as embodied in informational content resulting therefrom.
+- "Model" means any accompanying machine-learning based assemblies (including checkpoints), consisting of learnt weights, parameters (including optimizer states), corresponding to the model architecture as embodied in the Complementary Material, that have been trained or tuned, in whole or in part on the Data, using the Complementary Material.
+- "Derivatives of the Model" means all modifications to the Model, works based on the Model, or any other model which is created or initialized by transfer of patterns of the weights, parameters, activations or output of the Model, to the other model, in order to cause the other model to perform similarly to the Model, including - but not limited to - distillation methods entailing the use of intermediate data representations or methods based on the generation of synthetic data by the Model for training the other model.
+- "Complementary Material" means the accompanying source code and scripts used to define, run, load, benchmark or evaluate the Model, and used to prepare data for training or evaluation, if any. This includes any accompanying documentation, tutorials, examples, etc, if any.
+- "Distribution" means any transmission, reproduction, publication or other sharing of the Model or Derivatives of the Model to a third party, including providing the Model as a hosted service made available by electronic or other remote means - e.g. API-based or web access.
+- "Licensor" means the copyright owner or entity authorized by the copyright owner that is granting the License, including the persons or entities that may have rights in the Model and/or distributing the Model.
+- "You" (or "Your") means an individual or Legal Entity exercising permissions granted by this License and/or making use of the Model for whichever purpose and in any field of use, including usage of the Model in an end-use application - e.g. chatbot, translator, image generator.
+- "Third Parties" means individuals or legal entities that are not under common control with Licensor or You.
+- "Contribution" means any work of authorship, including the original version of the Model and any modifications or additions to that Model or Derivatives of the Model thereof, that is intentionally submitted to Licensor for inclusion in the Model by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Model, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
+- "Contributor" means Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Model.
+
+Section II: INTELLECTUAL PROPERTY RIGHTS
+
+Both copyright and patent grants apply to the Model, Derivatives of the Model and Complementary Material. The Model and Derivatives of the Model are subject to additional terms as described in Section III.
+
+2. Grant of Copyright License. Subject to the terms and conditions of this License, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare, publicly display, publicly perform, sublicense, and distribute the Complementary Material, the Model, and Derivatives of the Model.
+3. Grant of Patent License. Subject to the terms and conditions of this License and where and as applicable, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this paragraph) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Model and the Complementary Material, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Model to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Model and/or Complementary Material or a Contribution incorporated within the Model and/or Complementary Material constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for the Model and/or Work shall terminate as of the date such litigation is asserted or filed.
+
+Section III: CONDITIONS OF USAGE, DISTRIBUTION AND REDISTRIBUTION
+
+4. Distribution and Redistribution. You may host for Third Party remote access purposes (e.g. software-as-a-service), reproduce and distribute copies of the Model or Derivatives of the Model thereof in any medium, with or without modifications, provided that You meet the following conditions:
+Use-based restrictions as referenced in paragraph 5 MUST be included as an enforceable provision by You in any type of legal agreement (e.g. a license) governing the use and/or distribution of the Model or Derivatives of the Model, and You shall give notice to subsequent users You Distribute to, that the Model or Derivatives of the Model are subject to paragraph 5. This provision does not apply to the use of Complementary Material.
+You must give any Third Party recipients of the Model or Derivatives of the Model a copy of this License;
+You must cause any modified files to carry prominent notices stating that You changed the files;
+You must retain all copyright, patent, trademark, and attribution notices excluding those notices that do not pertain to any part of the Model, Derivatives of the Model.
+You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions - respecting paragraph 4.a. - for use, reproduction, or Distribution of Your modifications, or for any such Derivatives of the Model as a whole, provided Your use, reproduction, and Distribution of the Model otherwise complies with the conditions stated in this License.
+5. Use-based restrictions. The restrictions set forth in Attachment A are considered Use-based restrictions. Therefore You cannot use the Model and the Derivatives of the Model for the specified restricted uses. You may use the Model subject to this License, including only for lawful purposes and in accordance with the License. Use may include creating any content with, finetuning, updating, running, training, evaluating and/or reparametrizing the Model. You shall require all of Your users who use the Model or a Derivative of the Model to comply with the terms of this paragraph (paragraph 5).
+6. The Output You Generate. Except as set forth herein, Licensor claims no rights in the Output You generate using the Model. You are accountable for the Output you generate and its subsequent uses. No use of the output can contravene any provision as stated in the License.
+
+Section IV: OTHER PROVISIONS
+
+7. Updates and Runtime Restrictions. To the maximum extent permitted by law, Licensor reserves the right to restrict (remotely or otherwise) usage of the Model in violation of this License, update the Model through electronic means, or modify the Output of the Model based on updates. You shall undertake reasonable efforts to use the latest version of the Model.
+8. Trademarks and related. Nothing in this License permits You to make use of Licensors’ trademarks, trade names, logos or to otherwise suggest endorsement or misrepresent the relationship between the parties; and any rights not expressly granted herein are reserved by the Licensors.
+9. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Model and the Complementary Material (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Model, Derivatives of the Model, and the Complementary Material and assume any risks associated with Your exercise of permissions under this License.
+10. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Model and the Complementary Material (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
+11. Accepting Warranty or Additional Liability. While redistributing the Model, Derivatives of the Model and the Complementary Material thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
+12. If any provision of this License is held to be invalid, illegal or unenforceable, the remaining provisions shall be unaffected thereby and remain valid as if such provision had not been set forth herein.
+
+END OF TERMS AND CONDITIONS
+
+
+
+
+Attachment A
+
+Use Restrictions
+
+You agree not to use the Model or Derivatives of the Model:
+- In any way that violates any applicable national, federal, state, local or international law or regulation;
+- For the purpose of exploiting, harming or attempting to exploit or harm minors in any way;
+- To generate or disseminate verifiably false information and/or content with the purpose of harming others;
+- To generate or disseminate personal identifiable information that can be used to harm an individual;
+- To defame, disparage or otherwise harass others;
+- For fully automated decision making that adversely impacts an individual’s legal rights or otherwise creates or modifies a binding, enforceable obligation;
+- For any use intended to or which has the effect of discriminating against or harming individuals or groups based on online or offline social behavior or known or predicted personal or personality characteristics;
+- To exploit any of the vulnerabilities of a specific group of persons based on their age, social, physical or mental characteristics, in order to materially distort the behavior of a person pertaining to that group in a manner that causes or is likely to cause that person or another person physical or psychological harm;
+- For any use intended to or which has the effect of discriminating against individuals or groups based on legally protected characteristics or categories;
+- To provide medical advice and medical results interpretation;
+- To generate or disseminate information for the purpose to be used for administration of justice, law enforcement, immigration or asylum processes, such as predicting an individual will commit fraud/crime commitment (e.g. by text profiling, drawing causal relationships between assertions made in documents, indiscriminate and arbitrarily-targeted use).

stable_diffusion/README.md

@@ -0,0 +1,215 @@
+# Stable Diffusion
+*Stable Diffusion was made possible thanks to a collaboration with [Stability AI](https://stability.ai/) and [Runway](https://runwayml.com/) and builds upon our previous work:*
+
+[**High-Resolution Image Synthesis with Latent Diffusion Models**](https://ommer-lab.com/research/latent-diffusion-models/)<br/>
+[Robin Rombach](https://github.com/rromb)\*,
+[Andreas Blattmann](https://github.com/ablattmann)\*,
+[Dominik Lorenz](https://github.com/qp-qp)\,
+[Patrick Esser](https://github.com/pesser),
+[Björn Ommer](https://hci.iwr.uni-heidelberg.de/Staff/bommer)<br/>
+_[CVPR '22 Oral](https://openaccess.thecvf.com/content/CVPR2022/html/Rombach_High-Resolution_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2022_paper.html) |
+[GitHub](https://github.com/CompVis/latent-diffusion) | [arXiv](https://arxiv.org/abs/2112.10752) | [Project page](https://ommer-lab.com/research/latent-diffusion-models/)_
+
+![txt2img-stable2](assets/stable-samples/txt2img/merged-0006.png)
+[Stable Diffusion](#stable-diffusion-v1) is a latent text-to-image diffusion
+model.
+Thanks to a generous compute donation from [Stability AI](https://stability.ai/) and support from [LAION](https://laion.ai/), we were able to train a Latent Diffusion Model on 512x512 images from a subset of the [LAION-5B](https://laion.ai/blog/laion-5b/) database. 
+Similar to Google's [Imagen](https://arxiv.org/abs/2205.11487), 
+this model uses a frozen CLIP ViT-L/14 text encoder to condition the model on text prompts.
+With its 860M UNet and 123M text encoder, the model is relatively lightweight and runs on a GPU with at least 10GB VRAM.
+See [this section](#stable-diffusion-v1) below and the [model card](https://huggingface.co/CompVis/stable-diffusion).
+
+  
+## Requirements
+A suitable [conda](https://conda.io/) environment named `ldm` can be created
+and activated with:
+
+```
+conda env create -f environment.yaml
+conda activate ldm
+```
+
+You can also update an existing [latent diffusion](https://github.com/CompVis/latent-diffusion) environment by running
+
+```
+conda install pytorch torchvision -c pytorch
+pip install transformers==4.19.2 diffusers invisible-watermark
+pip install -e .
+``` 
+
+
+## Stable Diffusion v1
+
+Stable Diffusion v1 refers to a specific configuration of the model
+architecture that uses a downsampling-factor 8 autoencoder with an 860M UNet
+and CLIP ViT-L/14 text encoder for the diffusion model. The model was pretrained on 256x256 images and 
+then finetuned on 512x512 images.
+
+*Note: Stable Diffusion v1 is a general text-to-image diffusion model and therefore mirrors biases and (mis-)conceptions that are present
+in its training data. 
+Details on the training procedure and data, as well as the intended use of the model can be found in the corresponding [model card](Stable_Diffusion_v1_Model_Card.md).*
+
+The weights are available via [the CompVis organization at Hugging Face](https://huggingface.co/CompVis) under [a license which contains specific use-based restrictions to prevent misuse and harm as informed by the model card, but otherwise remains permissive](LICENSE). While commercial use is permitted under the terms of the license, **we do not recommend using the provided weights for services or products without additional safety mechanisms and considerations**, since there are [known limitations and biases](Stable_Diffusion_v1_Model_Card.md#limitations-and-bias) of the weights, and research on safe and ethical deployment of general text-to-image models is an ongoing effort. **The weights are research artifacts and should be treated as such.**
+
+[The CreativeML OpenRAIL M license](LICENSE) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.
+
+### Weights
+
+We currently provide the following checkpoints:
+
+- `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
+  194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
+- `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`.
+  515k steps at resolution `512x512` on [laion-aesthetics v2 5+](https://laion.ai/blog/laion-aesthetics/) (a subset of laion2B-en with estimated aesthetics score `> 5.0`, and additionally
+filtered to images with an original size `>= 512x512`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the [LAION-5B](https://laion.ai/blog/laion-5b/) metadata, the aesthetics score is estimated using the [LAION-Aesthetics Predictor V2](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
+- `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+- `sd-v1-4.ckpt`: Resumed from `sd-v1-2.ckpt`. 225k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+
+Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
+5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
+steps show the relative improvements of the checkpoints:
+![sd evaluation results](assets/v1-variants-scores.jpg)
+
+
+
+### Text-to-Image with Stable Diffusion
+![txt2img-stable2](assets/stable-samples/txt2img/merged-0005.png)
+![txt2img-stable2](assets/stable-samples/txt2img/merged-0007.png)
+
+Stable Diffusion is a latent diffusion model conditioned on the (non-pooled) text embeddings of a CLIP ViT-L/14 text encoder.
+We provide a [reference script for sampling](#reference-sampling-script), but
+there also exists a [diffusers integration](#diffusers-integration), which we
+expect to see more active community development.
+
+#### Reference Sampling Script
+
+We provide a reference sampling script, which incorporates
+
+- a [Safety Checker Module](https://github.com/CompVis/stable-diffusion/pull/36),
+  to reduce the probability of explicit outputs,
+- an [invisible watermarking](https://github.com/ShieldMnt/invisible-watermark)
+  of the outputs, to help viewers [identify the images as machine-generated](scripts/tests/test_watermark.py).
+
+After [obtaining the `stable-diffusion-v1-*-original` weights](#weights), link them
+```
+mkdir -p models/ldm/stable-diffusion-v1/
+ln -s <path/to/model.ckpt> models/ldm/stable-diffusion-v1/model.ckpt 
+```
+and sample with
+```
+python scripts/txt2img.py --prompt "a photograph of an astronaut riding a horse" --plms 
+```
+
+By default, this uses a guidance scale of `--scale 7.5`, [Katherine Crowson's implementation](https://github.com/CompVis/latent-diffusion/pull/51) of the [PLMS](https://arxiv.org/abs/2202.09778) sampler, 
+and renders images of size 512x512 (which it was trained on) in 50 steps. All supported arguments are listed below (type `python scripts/txt2img.py --help`).
+
+
+```commandline
+usage: txt2img.py [-h] [--prompt [PROMPT]] [--outdir [OUTDIR]] [--skip_grid] [--skip_save] [--ddim_steps DDIM_STEPS] [--plms] [--laion400m] [--fixed_code] [--ddim_eta DDIM_ETA]
+                  [--n_iter N_ITER] [--H H] [--W W] [--C C] [--f F] [--n_samples N_SAMPLES] [--n_rows N_ROWS] [--scale SCALE] [--from-file FROM_FILE] [--config CONFIG] [--ckpt CKPT]
+                  [--seed SEED] [--precision {full,autocast}]
+
+optional arguments:
+  -h, --help            show this help message and exit
+  --prompt [PROMPT]     the prompt to render
+  --outdir [OUTDIR]     dir to write results to
+  --skip_grid           do not save a grid, only individual samples. Helpful when evaluating lots of samples
+  --skip_save           do not save individual samples. For speed measurements.
+  --ddim_steps DDIM_STEPS
+                        number of ddim sampling steps
+  --plms                use plms sampling
+  --laion400m           uses the LAION400M model
+  --fixed_code          if enabled, uses the same starting code across samples
+  --ddim_eta DDIM_ETA   ddim eta (eta=0.0 corresponds to deterministic sampling
+  --n_iter N_ITER       sample this often
+  --H H                 image height, in pixel space
+  --W W                 image width, in pixel space
+  --C C                 latent channels
+  --f F                 downsampling factor
+  --n_samples N_SAMPLES
+                        how many samples to produce for each given prompt. A.k.a. batch size
+  --n_rows N_ROWS       rows in the grid (default: n_samples)
+  --scale SCALE         unconditional guidance scale: eps = eps(x, empty) + scale * (eps(x, cond) - eps(x, empty))
+  --from-file FROM_FILE
+                        if specified, load prompts from this file
+  --config CONFIG       path to config which constructs model
+  --ckpt CKPT           path to checkpoint of model
+  --seed SEED           the seed (for reproducible sampling)
+  --precision {full,autocast}
+                        evaluate at this precision
+```
+Note: The inference config for all v1 versions is designed to be used with EMA-only checkpoints. 
+For this reason `use_ema=False` is set in the configuration, otherwise the code will try to switch from
+non-EMA to EMA weights. If you want to examine the effect of EMA vs no EMA, we provide "full" checkpoints
+which contain both types of weights. For these, `use_ema=False` will load and use the non-EMA weights.
+
+
+#### Diffusers Integration
+
+A simple way to download and sample Stable Diffusion is by using the [diffusers library](https://github.com/huggingface/diffusers/tree/main#new--stable-diffusion-is-now-fully-compatible-with-diffusers):
+```py
+# make sure you're logged in with `huggingface-cli login`
+from torch import autocast
+from diffusers import StableDiffusionPipeline
+
+pipe = StableDiffusionPipeline.from_pretrained(
+	"CompVis/stable-diffusion-v1-4", 
+	use_auth_token=True
+).to("cuda")
+
+prompt = "a photo of an astronaut riding a horse on mars"
+with autocast("cuda"):
+    image = pipe(prompt)["sample"][0]  
+    
+image.save("astronaut_rides_horse.png")
+```
+
+
+### Image Modification with Stable Diffusion
+
+By using a diffusion-denoising mechanism as first proposed by [SDEdit](https://arxiv.org/abs/2108.01073), the model can be used for different 
+tasks such as text-guided image-to-image translation and upscaling. Similar to the txt2img sampling script, 
+we provide a script to perform image modification with Stable Diffusion.  
+
+The following describes an example where a rough sketch made in [Pinta](https://www.pinta-project.com/) is converted into a detailed artwork.
+```
+python scripts/img2img.py --prompt "A fantasy landscape, trending on artstation" --init-img <path-to-img.jpg> --strength 0.8
+```
+Here, strength is a value between 0.0 and 1.0, that controls the amount of noise that is added to the input image. 
+Values that approach 1.0 allow for lots of variations but will also produce images that are not semantically consistent with the input. See the following example.
+
+**Input**
+
+![sketch-in](assets/stable-samples/img2img/sketch-mountains-input.jpg)
+
+**Outputs**
+
+![out3](assets/stable-samples/img2img/mountains-3.png)
+![out2](assets/stable-samples/img2img/mountains-2.png)
+
+This procedure can, for example, also be used to upscale samples from the base model.
+
+
+## Comments 
+
+- Our codebase for the diffusion models builds heavily on [OpenAI's ADM codebase](https://github.com/openai/guided-diffusion)
+and [https://github.com/lucidrains/denoising-diffusion-pytorch](https://github.com/lucidrains/denoising-diffusion-pytorch). 
+Thanks for open-sourcing!
+
+- The implementation of the transformer encoder is from [x-transformers](https://github.com/lucidrains/x-transformers) by [lucidrains](https://github.com/lucidrains?tab=repositories). 
+
+
+## BibTeX
+
+```
+@misc{rombach2021highresolution,
+      title={High-Resolution Image Synthesis with Latent Diffusion Models}, 
+      author={Robin Rombach and Andreas Blattmann and Dominik Lorenz and Patrick Esser and Björn Ommer},
+      year={2021},
+      eprint={2112.10752},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```
+
+

stable_diffusion/Stable_Diffusion_v1_Model_Card.md

@@ -0,0 +1,144 @@
+# Stable Diffusion v1 Model Card
+This model card focuses on the model associated with the Stable Diffusion model, available [here](https://github.com/CompVis/stable-diffusion).
+
+## Model Details
+- **Developed by:** Robin Rombach, Patrick Esser
+- **Model type:** Diffusion-based text-to-image generation model
+- **Language(s):** English
+- **License:** [Proprietary](LICENSE)
+- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487).
+- **Resources for more information:** [GitHub Repository](https://github.com/CompVis/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752).
+- **Cite as:**
+
+      @InProceedings{Rombach_2022_CVPR,
+          author    = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
+          title     = {High-Resolution Image Synthesis With Latent Diffusion Models},
+          booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+          month     = {June},
+          year      = {2022},
+          pages     = {10684-10695}
+      }
+
+# Uses
+
+## Direct Use 
+The model is intended for research purposes only. Possible research areas and
+tasks include
+
+- Safe deployment of models which have the potential to generate harmful content.
+- Probing and understanding the limitations and biases of generative models.
+- Generation of artworks and use in design and other artistic processes.
+- Applications in educational or creative tools.
+- Research on generative models.
+
+Excluded uses are described below.
+
+ ### Misuse, Malicious Use, and Out-of-Scope Use
+_Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), but applies in the same way to Stable Diffusion v1_.
+
+The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
+
+#### Out-of-Scope Use
+The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
+
+#### Misuse and Malicious Use
+Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
+
+- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
+- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
+- Impersonating individuals without their consent.
+- Sexual content without consent of the people who might see it.
+- Mis- and disinformation
+- Representations of egregious violence and gore
+- Sharing of copyrighted or licensed material in violation of its terms of use.
+- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
+
+## Limitations and Bias
+
+### Limitations
+
+- The model does not achieve perfect photorealism
+- The model cannot render legible text
+- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
+- Faces and people in general may not be generated properly.
+- The model was trained mainly with English captions and will not work as well in other languages.
+- The autoencoding part of the model is lossy
+- The model was trained on a large-scale dataset
+  [LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material
+  and is not fit for product use without additional safety mechanisms and
+  considerations.
+- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data.
+  The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
+
+### Bias
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases. 
+Stable Diffusion v1 was primarily trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/), 
+which consists of images that are limited to English descriptions. 
+Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for. 
+This affects the overall output of the model, as white and western cultures are often set as the default. Further, the 
+ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
+Stable Diffusion v1 mirrors and exacerbates biases to such a degree that viewer discretion must be advised irrespective of the input or its intent.
+
+
+## Training
+
+**Training Data**
+The model developers used the following dataset for training the model:
+
+- LAION-5B and subsets thereof (see next section)
+
+**Training Procedure**
+Stable Diffusion v1 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, 
+
+- Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
+- Text prompts are encoded through a ViT-L/14 text-encoder.
+- The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention.
+- The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet.
+
+We currently provide the following checkpoints:
+
+- `sd-v1-1.ckpt`: 237k steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
+  194k steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
+- `sd-v1-2.ckpt`: Resumed from `sd-v1-1.ckpt`.
+  515k steps at resolution `512x512` on [laion-aesthetics v2 5+](https://laion.ai/blog/laion-aesthetics/) (a subset of laion2B-en with estimated aesthetics score `> 5.0`, and additionally
+filtered to images with an original size `>= 512x512`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the [LAION-5B](https://laion.ai/blog/laion-5b/) metadata, the aesthetics score is estimated using the [LAION-Aesthetics Predictor V2](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
+- `sd-v1-3.ckpt`: Resumed from `sd-v1-2.ckpt`. 195k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+- `sd-v1-4.ckpt`: Resumed from `sd-v1-2.ckpt`. 225k steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10\% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
+
+- **Hardware:** 32 x 8 x A100 GPUs
+- **Optimizer:** AdamW
+- **Gradient Accumulations**: 2
+- **Batch:** 32 x 8 x 2 x 4 = 2048
+- **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
+
+## Evaluation Results 
+Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
+5.0, 6.0, 7.0, 8.0) and 50 PLMS sampling
+steps show the relative improvements of the checkpoints:
+
+![pareto](assets/v1-variants-scores.jpg) 
+
+Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution.  Not optimized for FID scores.
+
+## Environmental Impact
+
+**Stable Diffusion v1** **Estimated Emissions**
+Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
+
+- **Hardware Type:** A100 PCIe 40GB
+- **Hours used:** 150000
+- **Cloud Provider:** AWS
+- **Compute Region:** US-east
+- **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 11250 kg CO2 eq.
+
+## Citation
+    @InProceedings{Rombach_2022_CVPR,
+        author    = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
+        title     = {High-Resolution Image Synthesis With Latent Diffusion Models},
+        booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
+        month     = {June},
+        year      = {2022},
+        pages     = {10684-10695}
+    }
+
+*This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).*

stable_diffusion/assets/stable-samples/txt2img/merged-0006.png.REMOVED.git-id

@@ -0,0 +1 @@
+999f3703230580e8c89e9081abd6a1f8f50896d4

stable_diffusion/assets/stable-samples/txt2img/merged-0007.png.REMOVED.git-id

@@ -0,0 +1 @@
+af390acaf601283782d6f479d4cade4d78e30b26

stable_diffusion/assets/txt2img-preview.png.REMOVED.git-id

@@ -0,0 +1 @@
+51ee1c235dfdc63d4c41de7d303d03730e43c33c

stable_diffusion/configs/autoencoder/autoencoder_kl_16x16x16.yaml

@@ -0,0 +1,54 @@
+model:
+  base_learning_rate: 4.5e-6
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: "val/rec_loss"
+    embed_dim: 16
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 0.000001
+        disc_weight: 0.5
+
+    ddconfig:
+      double_z: True
+      z_channels: 16
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult: [ 1,1,2,2,4]  # num_down = len(ch_mult)-1
+      num_res_blocks: 2
+      attn_resolutions: [16]
+      dropout: 0.0
+
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 12
+    wrap: True
+    train:
+      target: ldm.data.imagenet.ImageNetSRTrain
+      params:
+        size: 256
+        degradation: pil_nearest
+    validation:
+      target: ldm.data.imagenet.ImageNetSRValidation
+      params:
+        size: 256
+        degradation: pil_nearest
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: True
+
+  trainer:
+    benchmark: True
+    accumulate_grad_batches: 2

stable_diffusion/configs/autoencoder/autoencoder_kl_32x32x4.yaml

@@ -0,0 +1,53 @@
+model:
+  base_learning_rate: 4.5e-6
+  target: ldm.models.autoencoder.AutoencoderKL
+  params:
+    monitor: "val/rec_loss"
+    embed_dim: 4
+    lossconfig:
+      target: ldm.modules.losses.LPIPSWithDiscriminator
+      params:
+        disc_start: 50001
+        kl_weight: 0.000001
+        disc_weight: 0.5
+
+    ddconfig:
+      double_z: True
+      z_channels: 4
+      resolution: 256
+      in_channels: 3
+      out_ch: 3
+      ch: 128
+      ch_mult: [ 1,2,4,4 ]  # num_down = len(ch_mult)-1
+      num_res_blocks: 2
+      attn_resolutions: [ ]
+      dropout: 0.0
+
+data:
+  target: main.DataModuleFromConfig
+  params:
+    batch_size: 12
+    wrap: True
+    train:
+      target: ldm.data.imagenet.ImageNetSRTrain
+      params:
+        size: 256
+        degradation: pil_nearest
+    validation:
+      target: ldm.data.imagenet.ImageNetSRValidation
+      params:
+        size: 256
+        degradation: pil_nearest
+
+lightning:
+  callbacks:
+    image_logger:
+      target: main.ImageLogger
+      params:
+        batch_frequency: 1000
+        max_images: 8
+        increase_log_steps: True
+
+  trainer:
+    benchmark: True
+    accumulate_grad_batches: 2

stable_diffusion/data/example_conditioning/text_conditional/sample_0.txt

@@ -0,0 +1 @@
+A basket of cerries

stable_diffusion/ldm/data/base.py

@@ -0,0 +1,23 @@
+from abc import abstractmethod
+from torch.utils.data import Dataset, ConcatDataset, ChainDataset, IterableDataset
+
+
+class Txt2ImgIterableBaseDataset(IterableDataset):
+    '''
+    Define an interface to make the IterableDatasets for text2img data chainable
+    '''
+    def __init__(self, num_records=0, valid_ids=None, size=256):
+        super().__init__()
+        self.num_records = num_records
+        self.valid_ids = valid_ids
+        self.sample_ids = valid_ids
+        self.size = size
+
+        print(f'{self.__class__.__name__} dataset contains {self.__len__()} examples.')
+
+    def __len__(self):
+        return self.num_records
+
+    @abstractmethod
+    def __iter__(self):
+        pass

stable_diffusion/ldm/data/imagenet.py

@@ -0,0 +1,394 @@
+import os, yaml, pickle, shutil, tarfile, glob
+import cv2
+import albumentations
+import PIL
+import numpy as np
+import torchvision.transforms.functional as TF
+from omegaconf import OmegaConf
+from functools import partial
+from PIL import Image
+from tqdm import tqdm
+from torch.utils.data import Dataset, Subset
+
+import taming.data.utils as tdu
+from taming.data.imagenet import str_to_indices, give_synsets_from_indices, download, retrieve
+from taming.data.imagenet import ImagePaths
+
+from ldm.modules.image_degradation import degradation_fn_bsr, degradation_fn_bsr_light
+
+
+def synset2idx(path_to_yaml="data/index_synset.yaml"):
+    with open(path_to_yaml) as f:
+        di2s = yaml.load(f)
+    return dict((v,k) for k,v in di2s.items())
+
+
+class ImageNetBase(Dataset):
+    def __init__(self, config=None):
+        self.config = config or OmegaConf.create()
+        if not type(self.config)==dict:
+            self.config = OmegaConf.to_container(self.config)
+        self.keep_orig_class_label = self.config.get("keep_orig_class_label", False)
+        self.process_images = True  # if False we skip loading & processing images and self.data contains filepaths
+        self._prepare()
+        self._prepare_synset_to_human()
+        self._prepare_idx_to_synset()
+        self._prepare_human_to_integer_label()
+        self._load()
+
+    def __len__(self):
+        return len(self.data)
+
+    def __getitem__(self, i):
+        return self.data[i]
+
+    def _prepare(self):
+        raise NotImplementedError()
+
+    def _filter_relpaths(self, relpaths):
+        ignore = set([
+            "n06596364_9591.JPEG",
+        ])
+        relpaths = [rpath for rpath in relpaths if not rpath.split("/")[-1] in ignore]
+        if "sub_indices" in self.config:
+            indices = str_to_indices(self.config["sub_indices"])
+            synsets = give_synsets_from_indices(indices, path_to_yaml=self.idx2syn)  # returns a list of strings
+            self.synset2idx = synset2idx(path_to_yaml=self.idx2syn)
+            files = []
+            for rpath in relpaths:
+                syn = rpath.split("/")[0]
+                if syn in synsets:
+                    files.append(rpath)
+            return files
+        else:
+            return relpaths
+
+    def _prepare_synset_to_human(self):
+        SIZE = 2655750
+        URL = "https://heibox.uni-heidelberg.de/f/9f28e956cd304264bb82/?dl=1"
+        self.human_dict = os.path.join(self.root, "synset_human.txt")
+        if (not os.path.exists(self.human_dict) or
+                not os.path.getsize(self.human_dict)==SIZE):
+            download(URL, self.human_dict)
+
+    def _prepare_idx_to_synset(self):
+        URL = "https://heibox.uni-heidelberg.de/f/d835d5b6ceda4d3aa910/?dl=1"
+        self.idx2syn = os.path.join(self.root, "index_synset.yaml")
+        if (not os.path.exists(self.idx2syn)):
+            download(URL, self.idx2syn)
+
+    def _prepare_human_to_integer_label(self):
+        URL = "https://heibox.uni-heidelberg.de/f/2362b797d5be43b883f6/?dl=1"
+        self.human2integer = os.path.join(self.root, "imagenet1000_clsidx_to_labels.txt")
+        if (not os.path.exists(self.human2integer)):
+            download(URL, self.human2integer)
+        with open(self.human2integer, "r") as f:
+            lines = f.read().splitlines()
+            assert len(lines) == 1000
+            self.human2integer_dict = dict()
+            for line in lines:
+                value, key = line.split(":")
+                self.human2integer_dict[key] = int(value)
+
+    def _load(self):
+        with open(self.txt_filelist, "r") as f:
+            self.relpaths = f.read().splitlines()
+            l1 = len(self.relpaths)
+            self.relpaths = self._filter_relpaths(self.relpaths)
+            print("Removed {} files from filelist during filtering.".format(l1 - len(self.relpaths)))
+
+        self.synsets = [p.split("/")[0] for p in self.relpaths]
+        self.abspaths = [os.path.join(self.datadir, p) for p in self.relpaths]
+
+        unique_synsets = np.unique(self.synsets)
+        class_dict = dict((synset, i) for i, synset in enumerate(unique_synsets))
+        if not self.keep_orig_class_label:
+            self.class_labels = [class_dict[s] for s in self.synsets]
+        else:
+            self.class_labels = [self.synset2idx[s] for s in self.synsets]
+
+        with open(self.human_dict, "r") as f:
+            human_dict = f.read().splitlines()
+            human_dict = dict(line.split(maxsplit=1) for line in human_dict)
+
+        self.human_labels = [human_dict[s] for s in self.synsets]
+
+        labels = {
+            "relpath": np.array(self.relpaths),
+            "synsets": np.array(self.synsets),
+            "class_label": np.array(self.class_labels),
+            "human_label": np.array(self.human_labels),
+        }
+
+        if self.process_images:
+            self.size = retrieve(self.config, "size", default=256)
+            self.data = ImagePaths(self.abspaths,
+                                   labels=labels,
+                                   size=self.size,
+                                   random_crop=self.random_crop,
+                                   )
+        else:
+            self.data = self.abspaths
+
+
+class ImageNetTrain(ImageNetBase):
+    NAME = "ILSVRC2012_train"
+    URL = "http://www.image-net.org/challenges/LSVRC/2012/"
+    AT_HASH = "a306397ccf9c2ead27155983c254227c0fd938e2"
+    FILES = [
+        "ILSVRC2012_img_train.tar",
+    ]
+    SIZES = [
+        147897477120,
+    ]
+
+    def __init__(self, process_images=True, data_root=None, **kwargs):
+        self.process_images = process_images
+        self.data_root = data_root
+        super().__init__(**kwargs)
+
+    def _prepare(self):
+        if self.data_root:
+            self.root = os.path.join(self.data_root, self.NAME)
+        else:
+            cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
+            self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
+
+        self.datadir = os.path.join(self.root, "data")
+        self.txt_filelist = os.path.join(self.root, "filelist.txt")
+        self.expected_length = 1281167
+        self.random_crop = retrieve(self.config, "ImageNetTrain/random_crop",
+                                    default=True)
+        if not tdu.is_prepared(self.root):
+            # prep
+            print("Preparing dataset {} in {}".format(self.NAME, self.root))
+
+            datadir = self.datadir
+            if not os.path.exists(datadir):
+                path = os.path.join(self.root, self.FILES[0])
+                if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
+                    import academictorrents as at
+                    atpath = at.get(self.AT_HASH, datastore=self.root)
+                    assert atpath == path
+
+                print("Extracting {} to {}".format(path, datadir))
+                os.makedirs(datadir, exist_ok=True)
+                with tarfile.open(path, "r:") as tar:
+                    tar.extractall(path=datadir)
+
+                print("Extracting sub-tars.")
+                subpaths = sorted(glob.glob(os.path.join(datadir, "*.tar")))
+                for subpath in tqdm(subpaths):
+                    subdir = subpath[:-len(".tar")]
+                    os.makedirs(subdir, exist_ok=True)
+                    with tarfile.open(subpath, "r:") as tar:
+                        tar.extractall(path=subdir)
+
+            filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
+            filelist = [os.path.relpath(p, start=datadir) for p in filelist]
+            filelist = sorted(filelist)
+            filelist = "\n".join(filelist)+"\n"
+            with open(self.txt_filelist, "w") as f:
+                f.write(filelist)
+
+            tdu.mark_prepared(self.root)
+
+
+class ImageNetValidation(ImageNetBase):
+    NAME = "ILSVRC2012_validation"
+    URL = "http://www.image-net.org/challenges/LSVRC/2012/"
+    AT_HASH = "5d6d0df7ed81efd49ca99ea4737e0ae5e3a5f2e5"
+    VS_URL = "https://heibox.uni-heidelberg.de/f/3e0f6e9c624e45f2bd73/?dl=1"
+    FILES = [
+        "ILSVRC2012_img_val.tar",
+        "validation_synset.txt",
+    ]
+    SIZES = [
+        6744924160,
+        1950000,
+    ]
+
+    def __init__(self, process_images=True, data_root=None, **kwargs):
+        self.data_root = data_root
+        self.process_images = process_images
+        super().__init__(**kwargs)
+
+    def _prepare(self):
+        if self.data_root:
+            self.root = os.path.join(self.data_root, self.NAME)
+        else:
+            cachedir = os.environ.get("XDG_CACHE_HOME", os.path.expanduser("~/.cache"))
+            self.root = os.path.join(cachedir, "autoencoders/data", self.NAME)
+        self.datadir = os.path.join(self.root, "data")
+        self.txt_filelist = os.path.join(self.root, "filelist.txt")
+        self.expected_length = 50000
+        self.random_crop = retrieve(self.config, "ImageNetValidation/random_crop",
+                                    default=False)
+        if not tdu.is_prepared(self.root):
+            # prep
+            print("Preparing dataset {} in {}".format(self.NAME, self.root))
+
+            datadir = self.datadir
+            if not os.path.exists(datadir):
+                path = os.path.join(self.root, self.FILES[0])
+                if not os.path.exists(path) or not os.path.getsize(path)==self.SIZES[0]:
+                    import academictorrents as at
+                    atpath = at.get(self.AT_HASH, datastore=self.root)
+                    assert atpath == path
+
+                print("Extracting {} to {}".format(path, datadir))
+                os.makedirs(datadir, exist_ok=True)
+                with tarfile.open(path, "r:") as tar:
+                    tar.extractall(path=datadir)
+
+                vspath = os.path.join(self.root, self.FILES[1])
+                if not os.path.exists(vspath) or not os.path.getsize(vspath)==self.SIZES[1]:
+                    download(self.VS_URL, vspath)
+
+                with open(vspath, "r") as f:
+                    synset_dict = f.read().splitlines()
+                    synset_dict = dict(line.split() for line in synset_dict)
+
+                print("Reorganizing into synset folders")
+                synsets = np.unique(list(synset_dict.values()))
+                for s in synsets:
+                    os.makedirs(os.path.join(datadir, s), exist_ok=True)
+                for k, v in synset_dict.items():
+                    src = os.path.join(datadir, k)
+                    dst = os.path.join(datadir, v)
+                    shutil.move(src, dst)
+
+            filelist = glob.glob(os.path.join(datadir, "**", "*.JPEG"))
+            filelist = [os.path.relpath(p, start=datadir) for p in filelist]
+            filelist = sorted(filelist)
+            filelist = "\n".join(filelist)+"\n"
+            with open(self.txt_filelist, "w") as f:
+                f.write(filelist)
+
+            tdu.mark_prepared(self.root)
+
+
+
+class ImageNetSR(Dataset):
+    def __init__(self, size=None,
+                 degradation=None, downscale_f=4, min_crop_f=0.5, max_crop_f=1.,
+                 random_crop=True):
+        """
+        Imagenet Superresolution Dataloader
+        Performs following ops in order:
+        1.  crops a crop of size s from image either as random or center crop
+        2.  resizes crop to size with cv2.area_interpolation
+        3.  degrades resized crop with degradation_fn
+
+        :param size: resizing to size after cropping
+        :param degradation: degradation_fn, e.g. cv_bicubic or bsrgan_light
+        :param downscale_f: Low Resolution Downsample factor
+        :param min_crop_f: determines crop size s,
+          where s = c * min_img_side_len with c sampled from interval (min_crop_f, max_crop_f)
+        :param max_crop_f: ""
+        :param data_root:
+        :param random_crop:
+        """
+        self.base = self.get_base()
+        assert size
+        assert (size / downscale_f).is_integer()
+        self.size = size
+        self.LR_size = int(size / downscale_f)
+        self.min_crop_f = min_crop_f
+        self.max_crop_f = max_crop_f
+        assert(max_crop_f <= 1.)
+        self.center_crop = not random_crop
+
+        self.image_rescaler = albumentations.SmallestMaxSize(max_size=size, interpolation=cv2.INTER_AREA)
+
+        self.pil_interpolation = False # gets reset later if incase interp_op is from pillow
+
+        if degradation == "bsrgan":
+            self.degradation_process = partial(degradation_fn_bsr, sf=downscale_f)
+
+        elif degradation == "bsrgan_light":
+            self.degradation_process = partial(degradation_fn_bsr_light, sf=downscale_f)
+
+        else:
+            interpolation_fn = {
+            "cv_nearest": cv2.INTER_NEAREST,
+            "cv_bilinear": cv2.INTER_LINEAR,
+            "cv_bicubic": cv2.INTER_CUBIC,
+            "cv_area": cv2.INTER_AREA,
+            "cv_lanczos": cv2.INTER_LANCZOS4,
+            "pil_nearest": PIL.Image.NEAREST,
+            "pil_bilinear": PIL.Image.BILINEAR,
+            "pil_bicubic": PIL.Image.BICUBIC,
+            "pil_box": PIL.Image.BOX,
+            "pil_hamming": PIL.Image.HAMMING,
+            "pil_lanczos": PIL.Image.LANCZOS,
+            }[degradation]
+
+            self.pil_interpolation = degradation.startswith("pil_")
+
+            if self.pil_interpolation:
+                self.degradation_process = partial(TF.resize, size=self.LR_size, interpolation=interpolation_fn)
+
+            else:
+                self.degradation_process = albumentations.SmallestMaxSize(max_size=self.LR_size,
+                                                                          interpolation=interpolation_fn)
+
+    def __len__(self):
+        return len(self.base)
+
+    def __getitem__(self, i):
+        example = self.base[i]
+        image = Image.open(example["file_path_"])
+
+        if not image.mode == "RGB":
+            image = image.convert("RGB")
+
+        image = np.array(image).astype(np.uint8)
+
+        min_side_len = min(image.shape[:2])
+        crop_side_len = min_side_len * np.random.uniform(self.min_crop_f, self.max_crop_f, size=None)
+        crop_side_len = int(crop_side_len)
+
+        if self.center_crop:
+            self.cropper = albumentations.CenterCrop(height=crop_side_len, width=crop_side_len)
+
+        else:
+            self.cropper = albumentations.RandomCrop(height=crop_side_len, width=crop_side_len)
+
+        image = self.cropper(image=image)["image"]
+        image = self.image_rescaler(image=image)["image"]
+
+        if self.pil_interpolation:
+            image_pil = PIL.Image.fromarray(image)
+            LR_image = self.degradation_process(image_pil)
+            LR_image = np.array(LR_image).astype(np.uint8)
+
+        else:
+            LR_image = self.degradation_process(image=image)["image"]
+
+        example["image"] = (image/127.5 - 1.0).astype(np.float32)
+        example["LR_image"] = (LR_image/127.5 - 1.0).astype(np.float32)
+
+        return example
+
+
+class ImageNetSRTrain(ImageNetSR):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def get_base(self):
+        with open("data/imagenet_train_hr_indices.p", "rb") as f:
+            indices = pickle.load(f)
+        dset = ImageNetTrain(process_images=False,)
+        return Subset(dset, indices)
+
+
+class ImageNetSRValidation(ImageNetSR):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def get_base(self):
+        with open("data/imagenet_val_hr_indices.p", "rb") as f:
+            indices = pickle.load(f)
+        dset = ImageNetValidation(process_images=False,)
+        return Subset(dset, indices)

stable_diffusion/ldm/data/lsun.py

@@ -0,0 +1,92 @@
+import os
+import numpy as np
+import PIL
+from PIL import Image
+from torch.utils.data import Dataset
+from torchvision import transforms
+
+
+class LSUNBase(Dataset):
+    def __init__(self,
+                 txt_file,
+                 data_root,
+                 size=None,
+                 interpolation="bicubic",
+                 flip_p=0.5
+                 ):
+        self.data_paths = txt_file
+        self.data_root = data_root
+        with open(self.data_paths, "r") as f:
+            self.image_paths = f.read().splitlines()
+        self._length = len(self.image_paths)
+        self.labels = {
+            "relative_file_path_": [l for l in self.image_paths],
+            "file_path_": [os.path.join(self.data_root, l)
+                           for l in self.image_paths],
+        }
+
+        self.size = size
+        self.interpolation = {"linear": PIL.Image.LINEAR,
+                              "bilinear": PIL.Image.BILINEAR,
+                              "bicubic": PIL.Image.BICUBIC,
+                              "lanczos": PIL.Image.LANCZOS,
+                              }[interpolation]
+        self.flip = transforms.RandomHorizontalFlip(p=flip_p)
+
+    def __len__(self):
+        return self._length
+
+    def __getitem__(self, i):
+        example = dict((k, self.labels[k][i]) for k in self.labels)
+        image = Image.open(example["file_path_"])
+        if not image.mode == "RGB":
+            image = image.convert("RGB")
+
+        # default to score-sde preprocessing
+        img = np.array(image).astype(np.uint8)
+        crop = min(img.shape[0], img.shape[1])
+        h, w, = img.shape[0], img.shape[1]
+        img = img[(h - crop) // 2:(h + crop) // 2,
+              (w - crop) // 2:(w + crop) // 2]
+
+        image = Image.fromarray(img)
+        if self.size is not None:
+            image = image.resize((self.size, self.size), resample=self.interpolation)
+
+        image = self.flip(image)
+        image = np.array(image).astype(np.uint8)
+        example["image"] = (image / 127.5 - 1.0).astype(np.float32)
+        return example
+
+
+class LSUNChurchesTrain(LSUNBase):
+    def __init__(self, **kwargs):
+        super().__init__(txt_file="data/lsun/church_outdoor_train.txt", data_root="data/lsun/churches", **kwargs)
+
+
+class LSUNChurchesValidation(LSUNBase):
+    def __init__(self, flip_p=0., **kwargs):
+        super().__init__(txt_file="data/lsun/church_outdoor_val.txt", data_root="data/lsun/churches",
+                         flip_p=flip_p, **kwargs)
+
+
+class LSUNBedroomsTrain(LSUNBase):
+    def __init__(self, **kwargs):
+        super().__init__(txt_file="data/lsun/bedrooms_train.txt", data_root="data/lsun/bedrooms", **kwargs)
+
+
+class LSUNBedroomsValidation(LSUNBase):
+    def __init__(self, flip_p=0.0, **kwargs):
+        super().__init__(txt_file="data/lsun/bedrooms_val.txt", data_root="data/lsun/bedrooms",
+                         flip_p=flip_p, **kwargs)
+
+
+class LSUNCatsTrain(LSUNBase):
+    def __init__(self, **kwargs):
+        super().__init__(txt_file="data/lsun/cat_train.txt", data_root="data/lsun/cats", **kwargs)
+
+
+class LSUNCatsValidation(LSUNBase):
+    def __init__(self, flip_p=0., **kwargs):
+        super().__init__(txt_file="data/lsun/cat_val.txt", data_root="data/lsun/cats",
+                         flip_p=flip_p, **kwargs)

stable_diffusion/ldm/lr_scheduler.py

@@ -0,0 +1,98 @@
+import numpy as np
+
+
+class LambdaWarmUpCosineScheduler:
+    """
+    note: use with a base_lr of 1.0
+    """
+    def __init__(self, warm_up_steps, lr_min, lr_max, lr_start, max_decay_steps, verbosity_interval=0):
+        self.lr_warm_up_steps = warm_up_steps
+        self.lr_start = lr_start
+        self.lr_min = lr_min
+        self.lr_max = lr_max
+        self.lr_max_decay_steps = max_decay_steps
+        self.last_lr = 0.
+        self.verbosity_interval = verbosity_interval
+
+    def schedule(self, n, **kwargs):
+        if self.verbosity_interval > 0:
+            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_lr}")
+        if n < self.lr_warm_up_steps:
+            lr = (self.lr_max - self.lr_start) / self.lr_warm_up_steps * n + self.lr_start
+            self.last_lr = lr
+            return lr
+        else:
+            t = (n - self.lr_warm_up_steps) / (self.lr_max_decay_steps - self.lr_warm_up_steps)
+            t = min(t, 1.0)
+            lr = self.lr_min + 0.5 * (self.lr_max - self.lr_min) * (
+                    1 + np.cos(t * np.pi))
+            self.last_lr = lr
+            return lr
+
+    def __call__(self, n, **kwargs):
+        return self.schedule(n,**kwargs)
+
+
+class LambdaWarmUpCosineScheduler2:
+    """
+    supports repeated iterations, configurable via lists
+    note: use with a base_lr of 1.0.
+    """
+    def __init__(self, warm_up_steps, f_min, f_max, f_start, cycle_lengths, verbosity_interval=0):
+        assert len(warm_up_steps) == len(f_min) == len(f_max) == len(f_start) == len(cycle_lengths)
+        self.lr_warm_up_steps = warm_up_steps
+        self.f_start = f_start
+        self.f_min = f_min
+        self.f_max = f_max
+        self.cycle_lengths = cycle_lengths
+        self.cum_cycles = np.cumsum([0] + list(self.cycle_lengths))
+        self.last_f = 0.
+        self.verbosity_interval = verbosity_interval
+
+    def find_in_interval(self, n):
+        interval = 0
+        for cl in self.cum_cycles[1:]:
+            if n <= cl:
+                return interval
+            interval += 1
+
+    def schedule(self, n, **kwargs):
+        cycle = self.find_in_interval(n)
+        n = n - self.cum_cycles[cycle]
+        if self.verbosity_interval > 0:
+            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
+                                                       f"current cycle {cycle}")
+        if n < self.lr_warm_up_steps[cycle]:
+            f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
+            self.last_f = f
+            return f
+        else:
+            t = (n - self.lr_warm_up_steps[cycle]) / (self.cycle_lengths[cycle] - self.lr_warm_up_steps[cycle])
+            t = min(t, 1.0)
+            f = self.f_min[cycle] + 0.5 * (self.f_max[cycle] - self.f_min[cycle]) * (
+                    1 + np.cos(t * np.pi))
+            self.last_f = f
+            return f
+
+    def __call__(self, n, **kwargs):
+        return self.schedule(n, **kwargs)
+
+
+class LambdaLinearScheduler(LambdaWarmUpCosineScheduler2):
+
+    def schedule(self, n, **kwargs):
+        cycle = self.find_in_interval(n)
+        n = n - self.cum_cycles[cycle]
+        if self.verbosity_interval > 0:
+            if n % self.verbosity_interval == 0: print(f"current step: {n}, recent lr-multiplier: {self.last_f}, "
+                                                       f"current cycle {cycle}")
+
+        if n < self.lr_warm_up_steps[cycle]:
+            f = (self.f_max[cycle] - self.f_start[cycle]) / self.lr_warm_up_steps[cycle] * n + self.f_start[cycle]
+            self.last_f = f
+            return f
+        else:
+            f = self.f_min[cycle] + (self.f_max[cycle] - self.f_min[cycle]) * (self.cycle_lengths[cycle] - n) / (self.cycle_lengths[cycle])
+            self.last_f = f
+            return f
+

stable_diffusion/ldm/models/diffusion/ddim.py

@@ -0,0 +1,241 @@
+"""SAMPLING ONLY."""
+
+import torch
+import numpy as np
+from tqdm import tqdm
+from functools import partial
+
+from ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like, \
+    extract_into_tensor
+
+
+class DDIMSampler(object):
+    def __init__(self, model, schedule="linear", **kwargs):
+        super().__init__()
+        self.model = model
+        self.ddpm_num_timesteps = model.num_timesteps
+        self.schedule = schedule
+
+    def register_buffer(self, name, attr):
+        if type(attr) == torch.Tensor:
+            if attr.device != torch.device("cuda"):
+                attr = attr.to(torch.device("cuda"))
+        setattr(self, name, attr)
+
+    def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True):
+        self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps,
+                                                  num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose)
+        alphas_cumprod = self.model.alphas_cumprod
+        assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep'
+        to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device)
+
+        self.register_buffer('betas', to_torch(self.model.betas))
+        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+        self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev))
+
+        # calculations for diffusion q(x_t | x_{t-1}) and others
+        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu())))
+        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu())))
+        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu())))
+        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu())))
+        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1)))
+
+        # ddim sampling parameters
+        ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(),
+                                                                                   ddim_timesteps=self.ddim_timesteps,
+                                                                                   eta=ddim_eta,verbose=verbose)
+        self.register_buffer('ddim_sigmas', ddim_sigmas)
+        self.register_buffer('ddim_alphas', ddim_alphas)
+        self.register_buffer('ddim_alphas_prev', ddim_alphas_prev)
+        self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas))
+        sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt(
+            (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * (
+                        1 - self.alphas_cumprod / self.alphas_cumprod_prev))
+        self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps)
+
+    @torch.no_grad()
+    def sample(self,
+               S,
+               batch_size,
+               shape,
+               conditioning=None,
+               callback=None,
+               normals_sequence=None,
+               img_callback=None,
+               quantize_x0=False,
+               eta=0.,
+               mask=None,
+               x0=None,
+               temperature=1.,
+               noise_dropout=0.,
+               score_corrector=None,
+               corrector_kwargs=None,
+               verbose=True,
+               x_T=None,
+               log_every_t=100,
+               unconditional_guidance_scale=1.,
+               unconditional_conditioning=None,
+               # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+               **kwargs
+               ):
+        if conditioning is not None:
+            if isinstance(conditioning, dict):
+                cbs = conditioning[list(conditioning.keys())[0]].shape[0]
+                if cbs != batch_size:
+                    print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+            else:
+                if conditioning.shape[0] != batch_size:
+                    print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+        self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
+        # sampling
+        C, H, W = shape
+        size = (batch_size, C, H, W)
+        print(f'Data shape for DDIM sampling is {size}, eta {eta}')
+
+        samples, intermediates = self.ddim_sampling(conditioning, size,
+                                                    callback=callback,
+                                                    img_callback=img_callback,
+                                                    quantize_denoised=quantize_x0,
+                                                    mask=mask, x0=x0,
+                                                    ddim_use_original_steps=False,
+                                                    noise_dropout=noise_dropout,
+                                                    temperature=temperature,
+                                                    score_corrector=score_corrector,
+                                                    corrector_kwargs=corrector_kwargs,
+                                                    x_T=x_T,
+                                                    log_every_t=log_every_t,
+                                                    unconditional_guidance_scale=unconditional_guidance_scale,
+                                                    unconditional_conditioning=unconditional_conditioning,
+                                                    )
+        return samples, intermediates
+
+    @torch.no_grad()
+    def ddim_sampling(self, cond, shape,
+                      x_T=None, ddim_use_original_steps=False,
+                      callback=None, timesteps=None, quantize_denoised=False,
+                      mask=None, x0=None, img_callback=None, log_every_t=100,
+                      temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+                      unconditional_guidance_scale=1., unconditional_conditioning=None,):
+        device = self.model.betas.device
+        b = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=device)
+        else:
+            img = x_T
+
+        if timesteps is None:
+            timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps
+        elif timesteps is not None and not ddim_use_original_steps:
+            subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1
+            timesteps = self.ddim_timesteps[:subset_end]
+
+        intermediates = {'x_inter': [img], 'pred_x0': [img]}
+        time_range = reversed(range(0,timesteps)) if ddim_use_original_steps else np.flip(timesteps)
+        total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0]
+        print(f"Running DDIM Sampling with {total_steps} timesteps")
+
+        iterator = tqdm(time_range, desc='DDIM Sampler', total=total_steps)
+
+        for i, step in enumerate(iterator):
+            index = total_steps - i - 1
+            ts = torch.full((b,), step, device=device, dtype=torch.long)
+
+            if mask is not None:
+                assert x0 is not None
+                img_orig = self.model.q_sample(x0, ts)  # TODO: deterministic forward pass?
+                img = img_orig * mask + (1. - mask) * img
+
+            outs = self.p_sample_ddim(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
+                                      quantize_denoised=quantize_denoised, temperature=temperature,
+                                      noise_dropout=noise_dropout, score_corrector=score_corrector,
+                                      corrector_kwargs=corrector_kwargs,
+                                      unconditional_guidance_scale=unconditional_guidance_scale,
+                                      unconditional_conditioning=unconditional_conditioning)
+            img, pred_x0 = outs
+            if callback: callback(i)
+            if img_callback: img_callback(pred_x0, i)
+
+            if index % log_every_t == 0 or index == total_steps - 1:
+                intermediates['x_inter'].append(img)
+                intermediates['pred_x0'].append(pred_x0)
+
+        return img, intermediates
+
+    @torch.no_grad()
+    def p_sample_ddim(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
+                      temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+                      unconditional_guidance_scale=1., unconditional_conditioning=None):
+        b, *_, device = *x.shape, x.device
+
+        if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
+            e_t = self.model.apply_model(x, t, c)
+        else:
+            x_in = torch.cat([x] * 2)
+            t_in = torch.cat([t] * 2)
+            c_in = torch.cat([unconditional_conditioning, c])
+            e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
+            e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
+
+        if score_corrector is not None:
+            assert self.model.parameterization == "eps"
+            e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
+
+        alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
+        alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
+        sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
+        sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
+        # select parameters corresponding to the currently considered timestep
+        a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
+        a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
+        sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
+        sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
+
+        # current prediction for x_0
+        pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
+        if quantize_denoised:
+            pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
+        # direction pointing to x_t
+        dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
+        noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
+        if noise_dropout > 0.:
+            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+        x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
+        return x_prev, pred_x0
+
+    @torch.no_grad()
+    def stochastic_encode(self, x0, t, use_original_steps=False, noise=None):
+        # fast, but does not allow for exact reconstruction
+        # t serves as an index to gather the correct alphas
+        if use_original_steps:
+            sqrt_alphas_cumprod = self.sqrt_alphas_cumprod
+            sqrt_one_minus_alphas_cumprod = self.sqrt_one_minus_alphas_cumprod
+        else:
+            sqrt_alphas_cumprod = torch.sqrt(self.ddim_alphas)
+            sqrt_one_minus_alphas_cumprod = self.ddim_sqrt_one_minus_alphas
+
+        if noise is None:
+            noise = torch.randn_like(x0)
+        return (extract_into_tensor(sqrt_alphas_cumprod, t, x0.shape) * x0 +
+                extract_into_tensor(sqrt_one_minus_alphas_cumprod, t, x0.shape) * noise)
+
+    @torch.no_grad()
+    def decode(self, x_latent, cond, t_start, unconditional_guidance_scale=1.0, unconditional_conditioning=None,
+               use_original_steps=False):
+
+        timesteps = np.arange(self.ddpm_num_timesteps) if use_original_steps else self.ddim_timesteps
+        timesteps = timesteps[:t_start]
+
+        time_range = np.flip(timesteps)
+        total_steps = timesteps.shape[0]
+        print(f"Running DDIM Sampling with {total_steps} timesteps")
+
+        iterator = tqdm(time_range, desc='Decoding image', total=total_steps)
+        x_dec = x_latent
+        for i, step in enumerate(iterator):
+            index = total_steps - i - 1
+            ts = torch.full((x_latent.shape[0],), step, device=x_latent.device, dtype=torch.long)
+            x_dec, _ = self.p_sample_ddim(x_dec, cond, ts, index=index, use_original_steps=use_original_steps,
+                                          unconditional_guidance_scale=unconditional_guidance_scale,
+                                          unconditional_conditioning=unconditional_conditioning)
+        return x_dec

stable_diffusion/ldm/models/diffusion/ddpm.py

@@ -0,0 +1,1445 @@
+"""
+wild mixture of
+https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
+https://github.com/CompVis/taming-transformers
+-- merci
+"""
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+__conditioning_keys__ = {'concat': 'c_concat',
+                         'crossattn': 'c_crossattn',
+                         'adm': 'y'}
+
+
+def disabled_train(self, mode=True):
+    """Overwrite model.train with this function to make sure train/eval mode
+    does not change anymore."""
+    return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+    return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPM(pl.LightningModule):
+    # classic DDPM with Gaussian diffusion, in image space
+    def __init__(self,
+                 unet_config,
+                 timesteps=1000,
+                 beta_schedule="linear",
+                 loss_type="l2",
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 load_only_unet=False,
+                 monitor="val/loss",
+                 use_ema=True,
+                 first_stage_key="image",
+                 image_size=256,
+                 channels=3,
+                 log_every_t=100,
+                 clip_denoised=True,
+                 linear_start=1e-4,
+                 linear_end=2e-2,
+                 cosine_s=8e-3,
+                 given_betas=None,
+                 original_elbo_weight=0.,
+                 v_posterior=0.,  # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+                 l_simple_weight=1.,
+                 conditioning_key=None,
+                 parameterization="eps",  # all assuming fixed variance schedules
+                 scheduler_config=None,
+                 use_positional_encodings=False,
+                 learn_logvar=False,
+                 logvar_init=0.,
+                 ):
+        super().__init__()
+        assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+        self.parameterization = parameterization
+        print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+        self.cond_stage_model = None
+        self.clip_denoised = clip_denoised
+        self.log_every_t = log_every_t
+        self.first_stage_key = first_stage_key
+        self.image_size = image_size  # try conv?
+        self.channels = channels
+        self.use_positional_encodings = use_positional_encodings
+        self.model = DiffusionWrapper(unet_config, conditioning_key)
+        count_params(self.model, verbose=True)
+        self.use_ema = use_ema
+        if self.use_ema:
+            self.model_ema = LitEma(self.model)
+            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        self.use_scheduler = scheduler_config is not None
+        if self.use_scheduler:
+            self.scheduler_config = scheduler_config
+
+        self.v_posterior = v_posterior
+        self.original_elbo_weight = original_elbo_weight
+        self.l_simple_weight = l_simple_weight
+
+        if monitor is not None:
+            self.monitor = monitor
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+        self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+                               linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+        self.loss_type = loss_type
+
+        self.learn_logvar = learn_logvar
+        self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+        if self.learn_logvar:
+            self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+    def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        if exists(given_betas):
+            betas = given_betas
+        else:
+            betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+                                       cosine_s=cosine_s)
+        alphas = 1. - betas
+        alphas_cumprod = np.cumprod(alphas, axis=0)
+        alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+        timesteps, = betas.shape
+        self.num_timesteps = int(timesteps)
+        self.linear_start = linear_start
+        self.linear_end = linear_end
+        assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+        to_torch = partial(torch.tensor, dtype=torch.float32)
+
+        self.register_buffer('betas', to_torch(betas))
+        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+        self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+        # calculations for diffusion q(x_t | x_{t-1}) and others
+        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+        # calculations for posterior q(x_{t-1} | x_t, x_0)
+        posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+                    1. - alphas_cumprod) + self.v_posterior * betas
+        # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+        self.register_buffer('posterior_variance', to_torch(posterior_variance))
+        # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+        self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+        self.register_buffer('posterior_mean_coef1', to_torch(
+            betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+        self.register_buffer('posterior_mean_coef2', to_torch(
+            (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+        if self.parameterization == "eps":
+            lvlb_weights = self.betas ** 2 / (
+                        2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+        elif self.parameterization == "x0":
+            lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+        else:
+            raise NotImplementedError("mu not supported")
+        # TODO how to choose this term
+        lvlb_weights[0] = lvlb_weights[1]
+        self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+        assert not torch.isnan(self.lvlb_weights).all()
+
+    @contextmanager
+    def ema_scope(self, context=None):
+        if self.use_ema:
+            self.model_ema.store(self.model.parameters())
+            self.model_ema.copy_to(self.model)
+            if context is not None:
+                print(f"{context}: Switched to EMA weights")
+        try:
+            yield None
+        finally:
+            if self.use_ema:
+                self.model_ema.restore(self.model.parameters())
+                if context is not None:
+                    print(f"{context}: Restored training weights")
+
+    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+        sd = torch.load(path, map_location="cpu")
+        if "state_dict" in list(sd.keys()):
+            sd = sd["state_dict"]
+        keys = list(sd.keys())
+        for k in keys:
+            for ik in ignore_keys:
+                if k.startswith(ik):
+                    print("Deleting key {} from state_dict.".format(k))
+                    del sd[k]
+        missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+            sd, strict=False)
+        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+        if len(missing) > 0:
+            print(f"Missing Keys: {missing}")
+        if len(unexpected) > 0:
+            print(f"Unexpected Keys: {unexpected}")
+
+    def q_mean_variance(self, x_start, t):
+        """
+        Get the distribution q(x_t | x_0).
+        :param x_start: the [N x C x ...] tensor of noiseless inputs.
+        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+        :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+        """
+        mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+        variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+        log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+        return mean, variance, log_variance
+
+    def predict_start_from_noise(self, x_t, t, noise):
+        return (
+                extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+                extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+        )
+
+    def q_posterior(self, x_start, x_t, t):
+        posterior_mean = (
+                extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+                extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+        )
+        posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+        posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+        return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+    def p_mean_variance(self, x, t, clip_denoised: bool):
+        model_out = self.model(x, t)
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+        b, *_, device = *x.shape, x.device
+        model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+        noise = noise_like(x.shape, device, repeat_noise)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+        return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def p_sample_loop(self, shape, return_intermediates=False):
+        device = self.betas.device
+        b = shape[0]
+        img = torch.randn(shape, device=device)
+        intermediates = [img]
+        for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+            img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+                                clip_denoised=self.clip_denoised)
+            if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+                intermediates.append(img)
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, batch_size=16, return_intermediates=False):
+        image_size = self.image_size
+        channels = self.channels
+        return self.p_sample_loop((batch_size, channels, image_size, image_size),
+                                  return_intermediates=return_intermediates)
+
+    def q_sample(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+    def get_loss(self, pred, target, mean=True):
+        if self.loss_type == 'l1':
+            loss = (target - pred).abs()
+            if mean:
+                loss = loss.mean()
+        elif self.loss_type == 'l2':
+            if mean:
+                loss = torch.nn.functional.mse_loss(target, pred)
+            else:
+                loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+        else:
+            raise NotImplementedError("unknown loss type '{loss_type}'")
+
+        return loss
+
+    def p_losses(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_out = self.model(x_noisy, t)
+
+        loss_dict = {}
+        if self.parameterization == "eps":
+            target = noise
+        elif self.parameterization == "x0":
+            target = x_start
+        else:
+            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+        loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+        log_prefix = 'train' if self.training else 'val'
+
+        loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+        loss_simple = loss.mean() * self.l_simple_weight
+
+        loss_vlb = (self.lvlb_weights[t] * loss).mean()
+        loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+        loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+        loss_dict.update({f'{log_prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def forward(self, x, *args, **kwargs):
+        # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+        # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        return self.p_losses(x, t, *args, **kwargs)
+
+    def get_input(self, batch, k):
+        x = batch[k]
+        if len(x.shape) == 3:
+            x = x[..., None]
+        x = rearrange(x, 'b h w c -> b c h w')
+        x = x.to(memory_format=torch.contiguous_format).float()
+        return x
+
+    def shared_step(self, batch):
+        x = self.get_input(batch, self.first_stage_key)
+        loss, loss_dict = self(x)
+        return loss, loss_dict
+
+    def training_step(self, batch, batch_idx):
+        loss, loss_dict = self.shared_step(batch)
+
+        self.log_dict(loss_dict, prog_bar=True,
+                      logger=True, on_step=True, on_epoch=True)
+
+        self.log("global_step", self.global_step,
+                 prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        if self.use_scheduler:
+            lr = self.optimizers().param_groups[0]['lr']
+            self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        return loss
+
+    @torch.no_grad()
+    def validation_step(self, batch, batch_idx):
+        _, loss_dict_no_ema = self.shared_step(batch)
+        with self.ema_scope():
+            _, loss_dict_ema = self.shared_step(batch)
+            loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+        self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+        self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+    def on_train_batch_end(self, *args, **kwargs):
+        if self.use_ema:
+            self.model_ema(self.model)
+
+    def _get_rows_from_list(self, samples):
+        n_imgs_per_row = len(samples)
+        denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    @torch.no_grad()
+    def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+        log = dict()
+        x = self.get_input(batch, self.first_stage_key)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        x = x.to(self.device)[:N]
+        log["inputs"] = x
+
+        # get diffusion row
+        diffusion_row = list()
+        x_start = x[:n_row]
+
+        for t in range(self.num_timesteps):
+            if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                t = t.to(self.device).long()
+                noise = torch.randn_like(x_start)
+                x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+                diffusion_row.append(x_noisy)
+
+        log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+            log["samples"] = samples
+            log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.learn_logvar:
+            params = params + [self.logvar]
+        opt = torch.optim.AdamW(params, lr=lr)
+        return opt
+
+
+class LatentDiffusion(DDPM):
+    """main class"""
+    def __init__(self,
+                 first_stage_config,
+                 cond_stage_config,
+                 num_timesteps_cond=None,
+                 cond_stage_key="image",
+                 cond_stage_trainable=False,
+                 concat_mode=True,
+                 cond_stage_forward=None,
+                 conditioning_key=None,
+                 scale_factor=1.0,
+                 scale_by_std=False,
+                 *args, **kwargs):
+        self.num_timesteps_cond = default(num_timesteps_cond, 1)
+        self.scale_by_std = scale_by_std
+        assert self.num_timesteps_cond <= kwargs['timesteps']
+        # for backwards compatibility after implementation of DiffusionWrapper
+        if conditioning_key is None:
+            conditioning_key = 'concat' if concat_mode else 'crossattn'
+        if cond_stage_config == '__is_unconditional__':
+            conditioning_key = None
+        ckpt_path = kwargs.pop("ckpt_path", None)
+        ignore_keys = kwargs.pop("ignore_keys", [])
+        super().__init__(conditioning_key=conditioning_key, *args, **kwargs)
+        self.concat_mode = concat_mode
+        self.cond_stage_trainable = cond_stage_trainable
+        self.cond_stage_key = cond_stage_key
+        try:
+            self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+        except:
+            self.num_downs = 0
+        if not scale_by_std:
+            self.scale_factor = scale_factor
+        else:
+            self.register_buffer('scale_factor', torch.tensor(scale_factor))
+        self.instantiate_first_stage(first_stage_config)
+        self.instantiate_cond_stage(cond_stage_config)
+        self.cond_stage_forward = cond_stage_forward
+        self.clip_denoised = False
+        self.bbox_tokenizer = None  
+
+        self.restarted_from_ckpt = False
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys)
+            self.restarted_from_ckpt = True
+
+    def make_cond_schedule(self, ):
+        self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+        ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+        self.cond_ids[:self.num_timesteps_cond] = ids
+
+    @rank_zero_only
+    @torch.no_grad()
+    def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+        # only for very first batch
+        if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+            assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+            # set rescale weight to 1./std of encodings
+            print("### USING STD-RESCALING ###")
+            x = super().get_input(batch, self.first_stage_key)
+            x = x.to(self.device)
+            encoder_posterior = self.encode_first_stage(x)
+            z = self.get_first_stage_encoding(encoder_posterior).detach()
+            del self.scale_factor
+            self.register_buffer('scale_factor', 1. / z.flatten().std())
+            print(f"setting self.scale_factor to {self.scale_factor}")
+            print("### USING STD-RESCALING ###")
+
+    def register_schedule(self,
+                          given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+        self.shorten_cond_schedule = self.num_timesteps_cond > 1
+        if self.shorten_cond_schedule:
+            self.make_cond_schedule()
+
+    def instantiate_first_stage(self, config):
+        model = instantiate_from_config(config)
+        self.first_stage_model = model.eval()
+        self.first_stage_model.train = disabled_train
+        for param in self.first_stage_model.parameters():
+            param.requires_grad = False
+
+    def instantiate_cond_stage(self, config):
+        if not self.cond_stage_trainable:
+            if config == "__is_first_stage__":
+                print("Using first stage also as cond stage.")
+                self.cond_stage_model = self.first_stage_model
+            elif config == "__is_unconditional__":
+                print(f"Training {self.__class__.__name__} as an unconditional model.")
+                self.cond_stage_model = None
+                # self.be_unconditional = True
+            else:
+                model = instantiate_from_config(config)
+                self.cond_stage_model = model.eval()
+                self.cond_stage_model.train = disabled_train
+                for param in self.cond_stage_model.parameters():
+                    param.requires_grad = False
+        else:
+            assert config != '__is_first_stage__'
+            assert config != '__is_unconditional__'
+            model = instantiate_from_config(config)
+            self.cond_stage_model = model
+
+    def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+        denoise_row = []
+        for zd in tqdm(samples, desc=desc):
+            denoise_row.append(self.decode_first_stage(zd.to(self.device),
+                                                            force_not_quantize=force_no_decoder_quantization))
+        n_imgs_per_row = len(denoise_row)
+        denoise_row = torch.stack(denoise_row)  # n_log_step, n_row, C, H, W
+        denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    def get_first_stage_encoding(self, encoder_posterior):
+        if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+            z = encoder_posterior.sample()
+        elif isinstance(encoder_posterior, torch.Tensor):
+            z = encoder_posterior
+        else:
+            raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+        return self.scale_factor * z
+
+    def get_learned_conditioning(self, c):
+        if self.cond_stage_forward is None:
+            if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+                c = self.cond_stage_model.encode(c)
+                if isinstance(c, DiagonalGaussianDistribution):
+                    c = c.mode()
+            else:
+                c = self.cond_stage_model(c)
+        else:
+            assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+            c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+        return c
+
+    def meshgrid(self, h, w):
+        y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+        x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+        arr = torch.cat([y, x], dim=-1)
+        return arr
+
+    def delta_border(self, h, w):
+        """
+        :param h: height
+        :param w: width
+        :return: normalized distance to image border,
+         wtith min distance = 0 at border and max dist = 0.5 at image center
+        """
+        lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+        arr = self.meshgrid(h, w) / lower_right_corner
+        dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+        dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+        edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+        return edge_dist
+
+    def get_weighting(self, h, w, Ly, Lx, device):
+        weighting = self.delta_border(h, w)
+        weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+                               self.split_input_params["clip_max_weight"], )
+        weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+        if self.split_input_params["tie_braker"]:
+            L_weighting = self.delta_border(Ly, Lx)
+            L_weighting = torch.clip(L_weighting,
+                                     self.split_input_params["clip_min_tie_weight"],
+                                     self.split_input_params["clip_max_tie_weight"])
+
+            L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+            weighting = weighting * L_weighting
+        return weighting
+
+    def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1):  # todo load once not every time, shorten code
+        """
+        :param x: img of size (bs, c, h, w)
+        :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+        """
+        bs, nc, h, w = x.shape
+
+        # number of crops in image
+        Ly = (h - kernel_size[0]) // stride[0] + 1
+        Lx = (w - kernel_size[1]) // stride[1] + 1
+
+        if uf == 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+            weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h, w)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+        elif uf > 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+                                dilation=1, padding=0,
+                                stride=(stride[0] * uf, stride[1] * uf))
+            fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h * uf, w * uf)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+        elif df > 1 and uf == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+                                dilation=1, padding=0,
+                                stride=(stride[0] // df, stride[1] // df))
+            fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h // df, w // df)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+        else:
+            raise NotImplementedError
+
+        return fold, unfold, normalization, weighting
+
+    @torch.no_grad()
+    def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+                  cond_key=None, return_original_cond=False, bs=None):
+        x = super().get_input(batch, k)
+        if bs is not None:
+            x = x[:bs]
+        x = x.to(self.device)
+        encoder_posterior = self.encode_first_stage(x)
+        z = self.get_first_stage_encoding(encoder_posterior).detach()
+
+        if self.model.conditioning_key is not None:
+            if cond_key is None:
+                cond_key = self.cond_stage_key
+            if cond_key != self.first_stage_key:
+                if cond_key in ['caption', 'coordinates_bbox']:
+                    xc = batch[cond_key]
+                elif cond_key == 'class_label':
+                    xc = batch
+                else:
+                    xc = super().get_input(batch, cond_key).to(self.device)
+            else:
+                xc = x
+            if not self.cond_stage_trainable or force_c_encode:
+                if isinstance(xc, dict) or isinstance(xc, list):
+                    # import pudb; pudb.set_trace()
+                    c = self.get_learned_conditioning(xc)
+                else:
+                    c = self.get_learned_conditioning(xc.to(self.device))
+            else:
+                c = xc
+            if bs is not None:
+                c = c[:bs]
+
+            if self.use_positional_encodings:
+                pos_x, pos_y = self.compute_latent_shifts(batch)
+                ckey = __conditioning_keys__[self.model.conditioning_key]
+                c = {ckey: c, 'pos_x': pos_x, 'pos_y': pos_y}
+
+        else:
+            c = None
+            xc = None
+            if self.use_positional_encodings:
+                pos_x, pos_y = self.compute_latent_shifts(batch)
+                c = {'pos_x': pos_x, 'pos_y': pos_y}
+        out = [z, c]
+        if return_first_stage_outputs:
+            xrec = self.decode_first_stage(z)
+            out.extend([x, xrec])
+        if return_original_cond:
+            out.append(xc)
+        return out
+
+    @torch.no_grad()
+    def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    # same as above but without decorator
+    def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):  
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    @torch.no_grad()
+    def encode_first_stage(self, x):
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                df = self.split_input_params["vqf"]
+                self.split_input_params['original_image_size'] = x.shape[-2:]
+                bs, nc, h, w = x.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+                z = unfold(x)  # (bn, nc * prod(**ks), L)
+                # Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+                               for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)
+                o = o * weighting
+
+                # Reverse reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization
+                return decoded
+
+            else:
+                return self.first_stage_model.encode(x)
+        else:
+            return self.first_stage_model.encode(x)
+
+    def shared_step(self, batch, **kwargs):
+        x, c = self.get_input(batch, self.first_stage_key)
+        loss = self(x, c)
+        return loss
+
+    def forward(self, x, c, *args, **kwargs):
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        if self.model.conditioning_key is not None:
+            assert c is not None
+            if self.cond_stage_trainable:
+                c = self.get_learned_conditioning(c)
+            if self.shorten_cond_schedule:  # TODO: drop this option
+                tc = self.cond_ids[t].to(self.device)
+                c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+        return self.p_losses(x, c, t, *args, **kwargs)
+
+    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
+        def rescale_bbox(bbox):
+            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+            return x0, y0, w, h
+
+        return [rescale_bbox(b) for b in bboxes]
+
+    def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+        if isinstance(cond, dict):
+            # hybrid case, cond is exptected to be a dict
+            pass
+        else:
+            if not isinstance(cond, list):
+                cond = [cond]
+            key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+            cond = {key: cond}
+
+        if hasattr(self, "split_input_params"):
+            assert len(cond) == 1  # todo can only deal with one conditioning atm
+            assert not return_ids  
+            ks = self.split_input_params["ks"]  # eg. (128, 128)
+            stride = self.split_input_params["stride"]  # eg. (64, 64)
+
+            h, w = x_noisy.shape[-2:]
+
+            fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+            z = unfold(x_noisy)  # (bn, nc * prod(**ks), L)
+            # Reshape to img shape
+            z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+            z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+            if self.cond_stage_key in ["image", "LR_image", "segmentation",
+                                       'bbox_img'] and self.model.conditioning_key:  # todo check for completeness
+                c_key = next(iter(cond.keys()))  # get key
+                c = next(iter(cond.values()))  # get value
+                assert (len(c) == 1)  # todo extend to list with more than one elem
+                c = c[0]  # get element
+
+                c = unfold(c)
+                c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+            elif self.cond_stage_key == 'coordinates_bbox':
+                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+                # assuming padding of unfold is always 0 and its dilation is always 1
+                n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+                full_img_h, full_img_w = self.split_input_params['original_image_size']
+                # as we are operating on latents, we need the factor from the original image size to the
+                # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+                num_downs = self.first_stage_model.encoder.num_resolutions - 1
+                rescale_latent = 2 ** (num_downs)
+
+                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # need to rescale the tl patch coordinates to be in between (0,1)
+                tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+                                         rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+                                        for patch_nr in range(z.shape[-1])]
+
+                # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+                patch_limits = [(x_tl, y_tl,
+                                 rescale_latent * ks[0] / full_img_w,
+                                 rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+                # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+                # tokenize crop coordinates for the bounding boxes of the respective patches
+                patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+                                      for bbox in patch_limits]  # list of length l with tensors of shape (1, 2)
+                print(patch_limits_tknzd[0].shape)
+                # cut tknzd crop position from conditioning
+                assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+                cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+                print(cut_cond.shape)
+
+                adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+                adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+                print(adapted_cond.shape)
+                adapted_cond = self.get_learned_conditioning(adapted_cond)
+                print(adapted_cond.shape)
+                adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+                print(adapted_cond.shape)
+
+                cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+            else:
+                cond_list = [cond for i in range(z.shape[-1])]  # Todo make this more efficient
+
+            # apply model by loop over crops
+            output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+            assert not isinstance(output_list[0],
+                                  tuple)  # todo cant deal with multiple model outputs check this never happens
+
+            o = torch.stack(output_list, axis=-1)
+            o = o * weighting
+            # Reverse reshape to img shape
+            o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+            # stitch crops together
+            x_recon = fold(o) / normalization
+
+        else:
+            x_recon = self.model(x_noisy, t, **cond)
+
+        if isinstance(x_recon, tuple) and not return_ids:
+            return x_recon[0]
+        else:
+            return x_recon
+
+    def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+        return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+               extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+    def _prior_bpd(self, x_start):
+        """
+        Get the prior KL term for the variational lower-bound, measured in
+        bits-per-dim.
+        This term can't be optimized, as it only depends on the encoder.
+        :param x_start: the [N x C x ...] tensor of inputs.
+        :return: a batch of [N] KL values (in bits), one per batch element.
+        """
+        batch_size = x_start.shape[0]
+        t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+        qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+        kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+        return mean_flat(kl_prior) / np.log(2.0)
+
+    def p_losses(self, x_start, cond, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_output = self.apply_model(x_noisy, t, cond)
+
+        loss_dict = {}
+        prefix = 'train' if self.training else 'val'
+
+        if self.parameterization == "x0":
+            target = x_start
+        elif self.parameterization == "eps":
+            target = noise
+        else:
+            raise NotImplementedError()
+
+        loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+        loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+
+        logvar_t = self.logvar[t].to(self.device)
+        loss = loss_simple / torch.exp(logvar_t) + logvar_t
+        # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+        if self.learn_logvar:
+            loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+            loss_dict.update({'logvar': self.logvar.data.mean()})
+
+        loss = self.l_simple_weight * loss.mean()
+
+        loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+        loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+        loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+        loss += (self.original_elbo_weight * loss_vlb)
+        loss_dict.update({f'{prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+                        return_x0=False, score_corrector=None, corrector_kwargs=None):
+        t_in = t
+        model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+        if score_corrector is not None:
+            assert self.parameterization == "eps"
+            model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+        if return_codebook_ids:
+            model_out, logits = model_out
+
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        else:
+            raise NotImplementedError()
+
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+        if quantize_denoised:
+            x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        if return_codebook_ids:
+            return model_mean, posterior_variance, posterior_log_variance, logits
+        elif return_x0:
+            return model_mean, posterior_variance, posterior_log_variance, x_recon
+        else:
+            return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+                 return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+                 temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+        b, *_, device = *x.shape, x.device
+        outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+                                       return_codebook_ids=return_codebook_ids,
+                                       quantize_denoised=quantize_denoised,
+                                       return_x0=return_x0,
+                                       score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+        if return_codebook_ids:
+            raise DeprecationWarning("Support dropped.")
+            model_mean, _, model_log_variance, logits = outputs
+        elif return_x0:
+            model_mean, _, model_log_variance, x0 = outputs
+        else:
+            model_mean, _, model_log_variance = outputs
+
+        noise = noise_like(x.shape, device, repeat_noise) * temperature
+        if noise_dropout > 0.:
+            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+        if return_codebook_ids:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+        if return_x0:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+        else:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+                              img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+                              score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+                              log_every_t=None):
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        timesteps = self.num_timesteps
+        if batch_size is not None:
+            b = batch_size if batch_size is not None else shape[0]
+            shape = [batch_size] + list(shape)
+        else:
+            b = batch_size = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=self.device)
+        else:
+            img = x_T
+        intermediates = []
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+                        total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+        if type(temperature) == float:
+            temperature = [temperature] * timesteps
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img, x0_partial = self.p_sample(img, cond, ts,
+                                            clip_denoised=self.clip_denoised,
+                                            quantize_denoised=quantize_denoised, return_x0=True,
+                                            temperature=temperature[i], noise_dropout=noise_dropout,
+                                            score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+            if mask is not None:
+                assert x0 is not None
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(x0_partial)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+        return img, intermediates
+
+    @torch.no_grad()
+    def p_sample_loop(self, cond, shape, return_intermediates=False,
+                      x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+                      mask=None, x0=None, img_callback=None, start_T=None,
+                      log_every_t=None):
+
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        device = self.betas.device
+        b = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=device)
+        else:
+            img = x_T
+
+        intermediates = [img]
+        if timesteps is None:
+            timesteps = self.num_timesteps
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+
+        if mask is not None:
+            assert x0 is not None
+            assert x0.shape[2:3] == mask.shape[2:3]  # spatial size has to match
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img = self.p_sample(img, cond, ts,
+                                clip_denoised=self.clip_denoised,
+                                quantize_denoised=quantize_denoised)
+            if mask is not None:
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(img)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+               verbose=True, timesteps=None, quantize_denoised=False,
+               mask=None, x0=None, shape=None,**kwargs):
+        if shape is None:
+            shape = (batch_size, self.channels, self.image_size, self.image_size)
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+        return self.p_sample_loop(cond,
+                                  shape,
+                                  return_intermediates=return_intermediates, x_T=x_T,
+                                  verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+                                  mask=mask, x0=x0)
+
+    @torch.no_grad()
+    def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+        if ddim:
+            ddim_sampler = DDIMSampler(self)
+            shape = (self.channels, self.image_size, self.image_size)
+            samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+                                                        shape,cond,verbose=False,**kwargs)
+
+        else:
+            samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+                                                 return_intermediates=True,**kwargs)
+
+        return samples, intermediates
+
+
+    @torch.no_grad()
+    def log_images(self, batch, N=8, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+                   quantize_denoised=True, inpaint=True, plot_denoise_rows=False, plot_progressive_rows=True,
+                   plot_diffusion_rows=True, **kwargs):
+
+        use_ddim = ddim_steps is not None
+
+        log = dict()
+        z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+                                           return_first_stage_outputs=True,
+                                           force_c_encode=True,
+                                           return_original_cond=True,
+                                           bs=N)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        log["inputs"] = x
+        log["reconstruction"] = xrec
+        if self.model.conditioning_key is not None:
+            if hasattr(self.cond_stage_model, "decode"):
+                xc = self.cond_stage_model.decode(c)
+                log["conditioning"] = xc
+            elif self.cond_stage_key in ["caption"]:
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+                log["conditioning"] = xc
+            elif self.cond_stage_key == 'class_label':
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+                log['conditioning'] = xc
+            elif isimage(xc):
+                log["conditioning"] = xc
+            if ismap(xc):
+                log["original_conditioning"] = self.to_rgb(xc)
+
+        if plot_diffusion_rows:
+            # get diffusion row
+            diffusion_row = list()
+            z_start = z[:n_row]
+            for t in range(self.num_timesteps):
+                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                    t = t.to(self.device).long()
+                    noise = torch.randn_like(z_start)
+                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+                    diffusion_row.append(self.decode_first_stage(z_noisy))
+
+            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
+            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+            log["diffusion_row"] = diffusion_grid
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                         ddim_steps=ddim_steps,eta=ddim_eta)
+                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+            x_samples = self.decode_first_stage(samples)
+            log["samples"] = x_samples
+            if plot_denoise_rows:
+                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+                log["denoise_row"] = denoise_grid
+
+            if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+                    self.first_stage_model, IdentityFirstStage):
+                # also display when quantizing x0 while sampling
+                with self.ema_scope("Plotting Quantized Denoised"):
+                    samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                             ddim_steps=ddim_steps,eta=ddim_eta,
+                                                             quantize_denoised=True)
+                    # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+                    #                                      quantize_denoised=True)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_x0_quantized"] = x_samples
+
+            if inpaint:
+                # make a simple center square
+                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                mask = torch.ones(N, h, w).to(self.device)
+                # zeros will be filled in
+                mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+                mask = mask[:, None, ...]
+                with self.ema_scope("Plotting Inpaint"):
+
+                    samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_inpainting"] = x_samples
+                log["mask"] = mask
+
+                # outpaint
+                with self.ema_scope("Plotting Outpaint"):
+                    samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_outpainting"] = x_samples
+
+        if plot_progressive_rows:
+            with self.ema_scope("Plotting Progressives"):
+                img, progressives = self.progressive_denoising(c,
+                                                               shape=(self.channels, self.image_size, self.image_size),
+                                                               batch_size=N)
+            prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+            log["progressive_row"] = prog_row
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.cond_stage_trainable:
+            print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+            params = params + list(self.cond_stage_model.parameters())
+        if self.learn_logvar:
+            print('Diffusion model optimizing logvar')
+            params.append(self.logvar)
+        opt = torch.optim.AdamW(params, lr=lr)
+        if self.use_scheduler:
+            assert 'target' in self.scheduler_config
+            scheduler = instantiate_from_config(self.scheduler_config)
+
+            print("Setting up LambdaLR scheduler...")
+            scheduler = [
+                {
+                    'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+                    'interval': 'step',
+                    'frequency': 1
+                }]
+            return [opt], scheduler
+        return opt
+
+    @torch.no_grad()
+    def to_rgb(self, x):
+        x = x.float()
+        if not hasattr(self, "colorize"):
+            self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+        x = nn.functional.conv2d(x, weight=self.colorize)
+        x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+        return x
+
+
+class DiffusionWrapper(pl.LightningModule):
+    def __init__(self, diff_model_config, conditioning_key):
+        super().__init__()
+        self.diffusion_model = instantiate_from_config(diff_model_config)
+        self.conditioning_key = conditioning_key
+        assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+    def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+        if self.conditioning_key is None:
+            out = self.diffusion_model(x, t)
+        elif self.conditioning_key == 'concat':
+            xc = torch.cat([x] + c_concat, dim=1)
+            out = self.diffusion_model(xc, t)
+        elif self.conditioning_key == 'crossattn':
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(x, t, context=cc)
+        elif self.conditioning_key == 'hybrid':
+            xc = torch.cat([x] + c_concat, dim=1)
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(xc, t, context=cc)
+        elif self.conditioning_key == 'adm':
+            cc = c_crossattn[0]
+            out = self.diffusion_model(x, t, y=cc)
+        else:
+            raise NotImplementedError()
+
+        return out
+
+
+class Layout2ImgDiffusion(LatentDiffusion):
+    # TODO: move all layout-specific hacks to this class
+    def __init__(self, cond_stage_key, *args, **kwargs):
+        assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+    def log_images(self, batch, N=8, *args, **kwargs):
+        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+        key = 'train' if self.training else 'validation'
+        dset = self.trainer.datamodule.datasets[key]
+        mapper = dset.conditional_builders[self.cond_stage_key]
+
+        bbox_imgs = []
+        map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+        for tknzd_bbox in batch[self.cond_stage_key][:N]:
+            bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+            bbox_imgs.append(bboximg)
+
+        cond_img = torch.stack(bbox_imgs, dim=0)
+        logs['bbox_image'] = cond_img
+        return logs

stable_diffusion/ldm/models/diffusion/ddpm_edit.py

@@ -0,0 +1,1459 @@
+"""
+wild mixture of
+https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
+https://github.com/CompVis/taming-transformers
+-- merci
+"""
+
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+__conditioning_keys__ = {'concat': 'c_concat',
+                         'crossattn': 'c_crossattn',
+                         'adm': 'y'}
+
+
+def disabled_train(self, mode=True):
+    """Overwrite model.train with this function to make sure train/eval mode
+    does not change anymore."""
+    return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+    return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPM(pl.LightningModule):
+    # classic DDPM with Gaussian diffusion, in image space
+    def __init__(self,
+                 unet_config,
+                 timesteps=1000,
+                 beta_schedule="linear",
+                 loss_type="l2",
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 load_only_unet=False,
+                 monitor="val/loss",
+                 use_ema=True,
+                 first_stage_key="image",
+                 image_size=256,
+                 channels=3,
+                 log_every_t=100,
+                 clip_denoised=True,
+                 linear_start=1e-4,
+                 linear_end=2e-2,
+                 cosine_s=8e-3,
+                 given_betas=None,
+                 original_elbo_weight=0.,
+                 v_posterior=0.,  # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+                 l_simple_weight=1.,
+                 conditioning_key=None,
+                 parameterization="eps",  # all assuming fixed variance schedules
+                 scheduler_config=None,
+                 use_positional_encodings=False,
+                 learn_logvar=False,
+                 logvar_init=0.,
+                 load_ema=True,
+                 ):
+        super().__init__()
+        assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+        self.parameterization = parameterization
+        print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+        self.cond_stage_model = None
+        self.clip_denoised = clip_denoised
+        self.log_every_t = log_every_t
+        self.first_stage_key = first_stage_key
+        self.image_size = image_size  # try conv?
+        self.channels = channels
+        self.use_positional_encodings = use_positional_encodings
+        self.model = DiffusionWrapper(unet_config, conditioning_key)
+        count_params(self.model, verbose=True)
+        self.use_ema = use_ema
+
+        self.use_scheduler = scheduler_config is not None
+        if self.use_scheduler:
+            self.scheduler_config = scheduler_config
+
+        self.v_posterior = v_posterior
+        self.original_elbo_weight = original_elbo_weight
+        self.l_simple_weight = l_simple_weight
+
+        if monitor is not None:
+            self.monitor = monitor
+
+        if self.use_ema and load_ema:
+            self.model_ema = LitEma(self.model)
+            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+            # If initialing from EMA-only checkpoint, create EMA model after loading.
+            if self.use_ema and not load_ema:
+                self.model_ema = LitEma(self.model)
+                print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+                               linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+        self.loss_type = loss_type
+
+        self.learn_logvar = learn_logvar
+        self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+        if self.learn_logvar:
+            self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+    def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        if exists(given_betas):
+            betas = given_betas
+        else:
+            betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+                                       cosine_s=cosine_s)
+        alphas = 1. - betas
+        alphas_cumprod = np.cumprod(alphas, axis=0)
+        alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+        timesteps, = betas.shape
+        self.num_timesteps = int(timesteps)
+        self.linear_start = linear_start
+        self.linear_end = linear_end
+        assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+        to_torch = partial(torch.tensor, dtype=torch.float32)
+
+        self.register_buffer('betas', to_torch(betas))
+        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+        self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+        # calculations for diffusion q(x_t | x_{t-1}) and others
+        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+        # calculations for posterior q(x_{t-1} | x_t, x_0)
+        posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+                    1. - alphas_cumprod) + self.v_posterior * betas
+        # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+        self.register_buffer('posterior_variance', to_torch(posterior_variance))
+        # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+        self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+        self.register_buffer('posterior_mean_coef1', to_torch(
+            betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+        self.register_buffer('posterior_mean_coef2', to_torch(
+            (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+        if self.parameterization == "eps":
+            lvlb_weights = self.betas ** 2 / (
+                        2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+        elif self.parameterization == "x0":
+            lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+        else:
+            raise NotImplementedError("mu not supported")
+        # TODO how to choose this term
+        lvlb_weights[0] = lvlb_weights[1]
+        self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+        assert not torch.isnan(self.lvlb_weights).all()
+
+    @contextmanager
+    def ema_scope(self, context=None):
+        if self.use_ema:
+            self.model_ema.store(self.model.parameters())
+            self.model_ema.copy_to(self.model)
+            if context is not None:
+                print(f"{context}: Switched to EMA weights")
+        try:
+            yield None
+        finally:
+            if self.use_ema:
+                self.model_ema.restore(self.model.parameters())
+                if context is not None:
+                    print(f"{context}: Restored training weights")
+
+    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+        sd = torch.load(path, map_location="cpu")
+        if "state_dict" in list(sd.keys()):
+            sd = sd["state_dict"]
+        keys = list(sd.keys())
+
+        # Our model adds additional channels to the first layer to condition on an input image.
+        # For the first layer, copy existing channel weights and initialize new channel weights to zero.
+        input_keys = [
+            "model.diffusion_model.input_blocks.0.0.weight",
+            "model_ema.diffusion_modelinput_blocks00weight",
+        ]
+
+        self_sd = self.state_dict()
+        for input_key in input_keys:
+            if input_key not in sd or input_key not in self_sd:
+                continue
+
+            input_weight = self_sd[input_key]
+
+            if input_weight.size() != sd[input_key].size():
+                print(f"Manual init: {input_key}")
+                input_weight.zero_()
+                input_weight[:, :4, :, :].copy_(sd[input_key])
+                ignore_keys.append(input_key)
+
+        for k in keys:
+            for ik in ignore_keys:
+                if k.startswith(ik):
+                    print("Deleting key {} from state_dict.".format(k))
+                    del sd[k]
+        missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+            sd, strict=False)
+        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+        if len(missing) > 0:
+            print(f"Missing Keys: {missing}")
+        if len(unexpected) > 0:
+            print(f"Unexpected Keys: {unexpected}")
+
+    def q_mean_variance(self, x_start, t):
+        """
+        Get the distribution q(x_t | x_0).
+        :param x_start: the [N x C x ...] tensor of noiseless inputs.
+        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+        :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+        """
+        mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+        variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+        log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+        return mean, variance, log_variance
+
+    def predict_start_from_noise(self, x_t, t, noise):
+        return (
+                extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+                extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+        )
+
+    def q_posterior(self, x_start, x_t, t):
+        posterior_mean = (
+                extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+                extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+        )
+        posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+        posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+        return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+    def p_mean_variance(self, x, t, clip_denoised: bool):
+        model_out = self.model(x, t)
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+        b, *_, device = *x.shape, x.device
+        model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+        noise = noise_like(x.shape, device, repeat_noise)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+        return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def p_sample_loop(self, shape, return_intermediates=False):
+        device = self.betas.device
+        b = shape[0]
+        img = torch.randn(shape, device=device)
+        intermediates = [img]
+        for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+            img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+                                clip_denoised=self.clip_denoised)
+            if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+                intermediates.append(img)
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, batch_size=16, return_intermediates=False):
+        image_size = self.image_size
+        channels = self.channels
+        return self.p_sample_loop((batch_size, channels, image_size, image_size),
+                                  return_intermediates=return_intermediates)
+
+    def q_sample(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+    def get_loss(self, pred, target, mean=True):
+        if self.loss_type == 'l1':
+            loss = (target - pred).abs()
+            if mean:
+                loss = loss.mean()
+        elif self.loss_type == 'l2':
+            if mean:
+                loss = torch.nn.functional.mse_loss(target, pred)
+            else:
+                loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+        else:
+            raise NotImplementedError("unknown loss type '{loss_type}'")
+
+        return loss
+
+    def p_losses(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_out = self.model(x_noisy, t)
+
+        loss_dict = {}
+        if self.parameterization == "eps":
+            target = noise
+        elif self.parameterization == "x0":
+            target = x_start
+        else:
+            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+        loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+        log_prefix = 'train' if self.training else 'val'
+
+        loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+        loss_simple = loss.mean() * self.l_simple_weight
+
+        loss_vlb = (self.lvlb_weights[t] * loss).mean()
+        loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+        loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+        loss_dict.update({f'{log_prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def forward(self, x, *args, **kwargs):
+        # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+        # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        return self.p_losses(x, t, *args, **kwargs)
+
+    def get_input(self, batch, k):
+        return batch[k]
+
+    def shared_step(self, batch):
+        x = self.get_input(batch, self.first_stage_key)
+        loss, loss_dict = self(x)
+        return loss, loss_dict
+
+    def training_step(self, batch, batch_idx):
+        loss, loss_dict = self.shared_step(batch)
+
+        self.log_dict(loss_dict, prog_bar=True,
+                      logger=True, on_step=True, on_epoch=True)
+
+        self.log("global_step", self.global_step,
+                 prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        if self.use_scheduler:
+            lr = self.optimizers().param_groups[0]['lr']
+            self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        return loss
+
+    @torch.no_grad()
+    def validation_step(self, batch, batch_idx):
+        _, loss_dict_no_ema = self.shared_step(batch)
+        with self.ema_scope():
+            _, loss_dict_ema = self.shared_step(batch)
+            loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+        self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+        self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+    def on_train_batch_end(self, *args, **kwargs):
+        if self.use_ema:
+            self.model_ema(self.model)
+
+    def _get_rows_from_list(self, samples):
+        n_imgs_per_row = len(samples)
+        denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    @torch.no_grad()
+    def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+        log = dict()
+        x = self.get_input(batch, self.first_stage_key)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        x = x.to(self.device)[:N]
+        log["inputs"] = x
+
+        # get diffusion row
+        diffusion_row = list()
+        x_start = x[:n_row]
+
+        for t in range(self.num_timesteps):
+            if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                t = t.to(self.device).long()
+                noise = torch.randn_like(x_start)
+                x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+                diffusion_row.append(x_noisy)
+
+        log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+            log["samples"] = samples
+            log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.learn_logvar:
+            params = params + [self.logvar]
+        opt = torch.optim.AdamW(params, lr=lr)
+        return opt
+
+
+class LatentDiffusion(DDPM):
+    """main class"""
+    def __init__(self,
+                 first_stage_config,
+                 cond_stage_config,
+                 num_timesteps_cond=None,
+                 cond_stage_key="image",
+                 cond_stage_trainable=False,
+                 concat_mode=True,
+                 cond_stage_forward=None,
+                 conditioning_key=None,
+                 scale_factor=1.0,
+                 scale_by_std=False,
+                 load_ema=True,
+                 *args, **kwargs):
+        self.num_timesteps_cond = default(num_timesteps_cond, 1)
+        self.scale_by_std = scale_by_std
+        assert self.num_timesteps_cond <= kwargs['timesteps']
+        # for backwards compatibility after implementation of DiffusionWrapper
+        if conditioning_key is None:
+            conditioning_key = 'concat' if concat_mode else 'crossattn'
+        if cond_stage_config == '__is_unconditional__':
+            conditioning_key = None
+        ckpt_path = kwargs.pop("ckpt_path", None)
+        ignore_keys = kwargs.pop("ignore_keys", [])
+        super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs)
+        self.concat_mode = concat_mode
+        self.cond_stage_trainable = cond_stage_trainable
+        self.cond_stage_key = cond_stage_key
+        try:
+            self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+        except:
+            self.num_downs = 0
+        if not scale_by_std:
+            self.scale_factor = scale_factor
+        else:
+            self.register_buffer('scale_factor', torch.tensor(scale_factor))
+        self.instantiate_first_stage(first_stage_config)
+        self.instantiate_cond_stage(cond_stage_config)
+        self.cond_stage_forward = cond_stage_forward
+        self.clip_denoised = False
+        self.bbox_tokenizer = None
+
+        self.restarted_from_ckpt = False
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys)
+            self.restarted_from_ckpt = True
+
+            if self.use_ema and not load_ema:
+                self.model_ema = LitEma(self.model)
+                print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+    def make_cond_schedule(self, ):
+        self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+        ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+        self.cond_ids[:self.num_timesteps_cond] = ids
+
+    @rank_zero_only
+    @torch.no_grad()
+    def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+        # only for very first batch
+        if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+            assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+            # set rescale weight to 1./std of encodings
+            print("### USING STD-RESCALING ###")
+            x = super().get_input(batch, self.first_stage_key)
+            x = x.to(self.device)
+            encoder_posterior = self.encode_first_stage(x)
+            z = self.get_first_stage_encoding(encoder_posterior).detach()
+            del self.scale_factor
+            self.register_buffer('scale_factor', 1. / z.flatten().std())
+            print(f"setting self.scale_factor to {self.scale_factor}")
+            print("### USING STD-RESCALING ###")
+
+    def register_schedule(self,
+                          given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+        self.shorten_cond_schedule = self.num_timesteps_cond > 1
+        if self.shorten_cond_schedule:
+            self.make_cond_schedule()
+
+    def instantiate_first_stage(self, config):
+        model = instantiate_from_config(config)
+        self.first_stage_model = model.eval()
+        self.first_stage_model.train = disabled_train
+        for param in self.first_stage_model.parameters():
+            param.requires_grad = False
+
+    def instantiate_cond_stage(self, config):
+        if not self.cond_stage_trainable:
+            if config == "__is_first_stage__":
+                print("Using first stage also as cond stage.")
+                self.cond_stage_model = self.first_stage_model
+            elif config == "__is_unconditional__":
+                print(f"Training {self.__class__.__name__} as an unconditional model.")
+                self.cond_stage_model = None
+                # self.be_unconditional = True
+            else:
+                model = instantiate_from_config(config)
+                self.cond_stage_model = model.eval()
+                self.cond_stage_model.train = disabled_train
+                for param in self.cond_stage_model.parameters():
+                    param.requires_grad = False
+        else:
+            assert config != '__is_first_stage__'
+            assert config != '__is_unconditional__'
+            model = instantiate_from_config(config)
+            self.cond_stage_model = model
+
+    def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+        denoise_row = []
+        for zd in tqdm(samples, desc=desc):
+            denoise_row.append(self.decode_first_stage(zd.to(self.device),
+                                                            force_not_quantize=force_no_decoder_quantization))
+        n_imgs_per_row = len(denoise_row)
+        denoise_row = torch.stack(denoise_row)  # n_log_step, n_row, C, H, W
+        denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    def get_first_stage_encoding(self, encoder_posterior):
+        if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+            z = encoder_posterior.sample()
+        elif isinstance(encoder_posterior, torch.Tensor):
+            z = encoder_posterior
+        else:
+            raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+        return self.scale_factor * z
+
+    def get_learned_conditioning(self, c):
+        if self.cond_stage_forward is None:
+            if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+                c = self.cond_stage_model.encode(c)
+                if isinstance(c, DiagonalGaussianDistribution):
+                    c = c.mode()
+            else:
+                c = self.cond_stage_model(c)
+        else:
+            assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+            c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+        return c
+
+    def meshgrid(self, h, w):
+        y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+        x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+        arr = torch.cat([y, x], dim=-1)
+        return arr
+
+    def delta_border(self, h, w):
+        """
+        :param h: height
+        :param w: width
+        :return: normalized distance to image border,
+         wtith min distance = 0 at border and max dist = 0.5 at image center
+        """
+        lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+        arr = self.meshgrid(h, w) / lower_right_corner
+        dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+        dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+        edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+        return edge_dist
+
+    def get_weighting(self, h, w, Ly, Lx, device):
+        weighting = self.delta_border(h, w)
+        weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+                               self.split_input_params["clip_max_weight"], )
+        weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+        if self.split_input_params["tie_braker"]:
+            L_weighting = self.delta_border(Ly, Lx)
+            L_weighting = torch.clip(L_weighting,
+                                     self.split_input_params["clip_min_tie_weight"],
+                                     self.split_input_params["clip_max_tie_weight"])
+
+            L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+            weighting = weighting * L_weighting
+        return weighting
+
+    def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1):  # todo load once not every time, shorten code
+        """
+        :param x: img of size (bs, c, h, w)
+        :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+        """
+        bs, nc, h, w = x.shape
+
+        # number of crops in image
+        Ly = (h - kernel_size[0]) // stride[0] + 1
+        Lx = (w - kernel_size[1]) // stride[1] + 1
+
+        if uf == 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+            weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h, w)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+        elif uf > 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+                                dilation=1, padding=0,
+                                stride=(stride[0] * uf, stride[1] * uf))
+            fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h * uf, w * uf)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+        elif df > 1 and uf == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+                                dilation=1, padding=0,
+                                stride=(stride[0] // df, stride[1] // df))
+            fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h // df, w // df)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+        else:
+            raise NotImplementedError
+
+        return fold, unfold, normalization, weighting
+
+    @torch.no_grad()
+    def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+                  cond_key=None, return_original_cond=False, bs=None, uncond=0.05):
+        x = super().get_input(batch, k)
+        if bs is not None:
+            x = x[:bs]
+        x = x.to(self.device)
+        encoder_posterior = self.encode_first_stage(x)
+        z = self.get_first_stage_encoding(encoder_posterior).detach()
+        cond_key = cond_key or self.cond_stage_key
+        xc = super().get_input(batch, cond_key)
+        if bs is not None:
+            xc["c_crossattn"] = xc["c_crossattn"][:bs]
+            xc["c_concat"] = xc["c_concat"][:bs]
+        cond = {}
+
+        # To support classifier-free guidance, randomly drop out only text conditioning 5%, only image conditioning 5%, and both 5%.
+        random = torch.rand(x.size(0), device=x.device)
+        prompt_mask = rearrange(random < 2 * uncond, "n -> n 1 1")
+        input_mask = 1 - rearrange((random >= uncond).float() * (random < 3 * uncond).float(), "n -> n 1 1 1")
+
+        null_prompt = self.get_learned_conditioning([""])
+        cond["c_crossattn"] = [torch.where(prompt_mask, null_prompt, self.get_learned_conditioning(xc["c_crossattn"]).detach())]
+        cond["c_concat"] = [input_mask * self.encode_first_stage((xc["c_concat"].to(self.device))).mode().detach()]
+
+        out = [z, cond]
+        if return_first_stage_outputs:
+            xrec = self.decode_first_stage(z)
+            out.extend([x, xrec])
+        if return_original_cond:
+            out.append(xc)
+        return out
+
+    @torch.no_grad()
+    def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    # same as above but without decorator
+    def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    @torch.no_grad()
+    def encode_first_stage(self, x):
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                df = self.split_input_params["vqf"]
+                self.split_input_params['original_image_size'] = x.shape[-2:]
+                bs, nc, h, w = x.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+                z = unfold(x)  # (bn, nc * prod(**ks), L)
+                # Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+                               for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)
+                o = o * weighting
+
+                # Reverse reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization
+                return decoded
+
+            else:
+                return self.first_stage_model.encode(x)
+        else:
+            return self.first_stage_model.encode(x)
+
+    def shared_step(self, batch, **kwargs):
+        x, c = self.get_input(batch, self.first_stage_key)
+        loss = self(x, c)
+        return loss
+
+    def forward(self, x, c, *args, **kwargs):
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        if self.model.conditioning_key is not None:
+            assert c is not None
+            if self.cond_stage_trainable:
+                c = self.get_learned_conditioning(c)
+            if self.shorten_cond_schedule:  # TODO: drop this option
+                tc = self.cond_ids[t].to(self.device)
+                c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+        return self.p_losses(x, c, t, *args, **kwargs)
+
+    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
+        def rescale_bbox(bbox):
+            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+            return x0, y0, w, h
+
+        return [rescale_bbox(b) for b in bboxes]
+
+    def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+        if isinstance(cond, dict):
+            # hybrid case, cond is exptected to be a dict
+            pass
+        else:
+            if not isinstance(cond, list):
+                cond = [cond]
+            key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+            cond = {key: cond}
+
+        if hasattr(self, "split_input_params"):
+            assert len(cond) == 1  # todo can only deal with one conditioning atm
+            assert not return_ids
+            ks = self.split_input_params["ks"]  # eg. (128, 128)
+            stride = self.split_input_params["stride"]  # eg. (64, 64)
+
+            h, w = x_noisy.shape[-2:]
+
+            fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+            z = unfold(x_noisy)  # (bn, nc * prod(**ks), L)
+            # Reshape to img shape
+            z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+            z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+            if self.cond_stage_key in ["image", "LR_image", "segmentation",
+                                       'bbox_img'] and self.model.conditioning_key:  # todo check for completeness
+                c_key = next(iter(cond.keys()))  # get key
+                c = next(iter(cond.values()))  # get value
+                assert (len(c) == 1)  # todo extend to list with more than one elem
+                c = c[0]  # get element
+
+                c = unfold(c)
+                c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+            elif self.cond_stage_key == 'coordinates_bbox':
+                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+                # assuming padding of unfold is always 0 and its dilation is always 1
+                n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+                full_img_h, full_img_w = self.split_input_params['original_image_size']
+                # as we are operating on latents, we need the factor from the original image size to the
+                # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+                num_downs = self.first_stage_model.encoder.num_resolutions - 1
+                rescale_latent = 2 ** (num_downs)
+
+                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # need to rescale the tl patch coordinates to be in between (0,1)
+                tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+                                         rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+                                        for patch_nr in range(z.shape[-1])]
+
+                # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+                patch_limits = [(x_tl, y_tl,
+                                 rescale_latent * ks[0] / full_img_w,
+                                 rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+                # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+                # tokenize crop coordinates for the bounding boxes of the respective patches
+                patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+                                      for bbox in patch_limits]  # list of length l with tensors of shape (1, 2)
+                print(patch_limits_tknzd[0].shape)
+                # cut tknzd crop position from conditioning
+                assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+                cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+                print(cut_cond.shape)
+
+                adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+                adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+                print(adapted_cond.shape)
+                adapted_cond = self.get_learned_conditioning(adapted_cond)
+                print(adapted_cond.shape)
+                adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+                print(adapted_cond.shape)
+
+                cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+            else:
+                cond_list = [cond for i in range(z.shape[-1])]  # Todo make this more efficient
+
+            # apply model by loop over crops
+            output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+            assert not isinstance(output_list[0],
+                                  tuple)  # todo cant deal with multiple model outputs check this never happens
+
+            o = torch.stack(output_list, axis=-1)
+            o = o * weighting
+            # Reverse reshape to img shape
+            o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+            # stitch crops together
+            x_recon = fold(o) / normalization
+
+        else:
+            x_recon = self.model(x_noisy, t, **cond)
+
+        if isinstance(x_recon, tuple) and not return_ids:
+            return x_recon[0]
+        else:
+            return x_recon
+
+    def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+        return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+               extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+    def _prior_bpd(self, x_start):
+        """
+        Get the prior KL term for the variational lower-bound, measured in
+        bits-per-dim.
+        This term can't be optimized, as it only depends on the encoder.
+        :param x_start: the [N x C x ...] tensor of inputs.
+        :return: a batch of [N] KL values (in bits), one per batch element.
+        """
+        batch_size = x_start.shape[0]
+        t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+        qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+        kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+        return mean_flat(kl_prior) / np.log(2.0)
+
+    def p_losses(self, x_start, cond, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_output = self.apply_model(x_noisy, t, cond)
+
+        loss_dict = {}
+        prefix = 'train' if self.training else 'val'
+
+        if self.parameterization == "x0":
+            target = x_start
+        elif self.parameterization == "eps":
+            target = noise
+        else:
+            raise NotImplementedError()
+
+        loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+        loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+        self.logvar = self.logvar.to(self.device)
+        logvar_t = self.logvar[t].to(self.device)
+        loss = loss_simple / torch.exp(logvar_t) + logvar_t
+        # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+        if self.learn_logvar:
+            loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+            loss_dict.update({'logvar': self.logvar.data.mean()})
+
+        loss = self.l_simple_weight * loss.mean()
+
+        loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+        loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+        loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+        loss += (self.original_elbo_weight * loss_vlb)
+        loss_dict.update({f'{prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+                        return_x0=False, score_corrector=None, corrector_kwargs=None):
+        t_in = t
+        model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+        if score_corrector is not None:
+            assert self.parameterization == "eps"
+            model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+        if return_codebook_ids:
+            model_out, logits = model_out
+
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        else:
+            raise NotImplementedError()
+
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+        if quantize_denoised:
+            x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        if return_codebook_ids:
+            return model_mean, posterior_variance, posterior_log_variance, logits
+        elif return_x0:
+            return model_mean, posterior_variance, posterior_log_variance, x_recon
+        else:
+            return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+                 return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+                 temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+        b, *_, device = *x.shape, x.device
+        outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+                                       return_codebook_ids=return_codebook_ids,
+                                       quantize_denoised=quantize_denoised,
+                                       return_x0=return_x0,
+                                       score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+        if return_codebook_ids:
+            raise DeprecationWarning("Support dropped.")
+            model_mean, _, model_log_variance, logits = outputs
+        elif return_x0:
+            model_mean, _, model_log_variance, x0 = outputs
+        else:
+            model_mean, _, model_log_variance = outputs
+
+        noise = noise_like(x.shape, device, repeat_noise) * temperature
+        if noise_dropout > 0.:
+            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+        if return_codebook_ids:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+        if return_x0:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+        else:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+                              img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+                              score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+                              log_every_t=None):
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        timesteps = self.num_timesteps
+        if batch_size is not None:
+            b = batch_size if batch_size is not None else shape[0]
+            shape = [batch_size] + list(shape)
+        else:
+            b = batch_size = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=self.device)
+        else:
+            img = x_T
+        intermediates = []
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+                        total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+        if type(temperature) == float:
+            temperature = [temperature] * timesteps
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img, x0_partial = self.p_sample(img, cond, ts,
+                                            clip_denoised=self.clip_denoised,
+                                            quantize_denoised=quantize_denoised, return_x0=True,
+                                            temperature=temperature[i], noise_dropout=noise_dropout,
+                                            score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+            if mask is not None:
+                assert x0 is not None
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(x0_partial)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+        return img, intermediates
+
+    @torch.no_grad()
+    def p_sample_loop(self, cond, shape, return_intermediates=False,
+                      x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+                      mask=None, x0=None, img_callback=None, start_T=None,
+                      log_every_t=None):
+
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        device = self.betas.device
+        b = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=device)
+        else:
+            img = x_T
+
+        intermediates = [img]
+        if timesteps is None:
+            timesteps = self.num_timesteps
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+
+        if mask is not None:
+            assert x0 is not None
+            assert x0.shape[2:3] == mask.shape[2:3]  # spatial size has to match
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img = self.p_sample(img, cond, ts,
+                                clip_denoised=self.clip_denoised,
+                                quantize_denoised=quantize_denoised)
+            if mask is not None:
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(img)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+               verbose=True, timesteps=None, quantize_denoised=False,
+               mask=None, x0=None, shape=None,**kwargs):
+        if shape is None:
+            shape = (batch_size, self.channels, self.image_size, self.image_size)
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+        return self.p_sample_loop(cond,
+                                  shape,
+                                  return_intermediates=return_intermediates, x_T=x_T,
+                                  verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+                                  mask=mask, x0=x0)
+
+    @torch.no_grad()
+    def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+        if ddim:
+            ddim_sampler = DDIMSampler(self)
+            shape = (self.channels, self.image_size, self.image_size)
+            samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+                                                        shape,cond,verbose=False,**kwargs)
+
+        else:
+            samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+                                                 return_intermediates=True,**kwargs)
+
+        return samples, intermediates
+
+
+    @torch.no_grad()
+    def log_images(self, batch, N=4, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+                   quantize_denoised=True, inpaint=False, plot_denoise_rows=False, plot_progressive_rows=False,
+                   plot_diffusion_rows=False, **kwargs):
+
+        use_ddim = False
+
+        log = dict()
+        z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+                                           return_first_stage_outputs=True,
+                                           force_c_encode=True,
+                                           return_original_cond=True,
+                                           bs=N, uncond=0)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        log["inputs"] = x
+        log["reals"] = xc["c_concat"]
+        log["reconstruction"] = xrec
+        if self.model.conditioning_key is not None:
+            if hasattr(self.cond_stage_model, "decode"):
+                xc = self.cond_stage_model.decode(c)
+                log["conditioning"] = xc
+            elif self.cond_stage_key in ["caption"]:
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+                log["conditioning"] = xc
+            elif self.cond_stage_key == 'class_label':
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+                log['conditioning'] = xc
+            elif isimage(xc):
+                log["conditioning"] = xc
+            if ismap(xc):
+                log["original_conditioning"] = self.to_rgb(xc)
+
+        if plot_diffusion_rows:
+            # get diffusion row
+            diffusion_row = list()
+            z_start = z[:n_row]
+            for t in range(self.num_timesteps):
+                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                    t = t.to(self.device).long()
+                    noise = torch.randn_like(z_start)
+                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+                    diffusion_row.append(self.decode_first_stage(z_noisy))
+
+            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
+            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+            log["diffusion_row"] = diffusion_grid
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                         ddim_steps=ddim_steps,eta=ddim_eta)
+                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+            x_samples = self.decode_first_stage(samples)
+            log["samples"] = x_samples
+            if plot_denoise_rows:
+                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+                log["denoise_row"] = denoise_grid
+
+            if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+                    self.first_stage_model, IdentityFirstStage):
+                # also display when quantizing x0 while sampling
+                with self.ema_scope("Plotting Quantized Denoised"):
+                    samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                             ddim_steps=ddim_steps,eta=ddim_eta,
+                                                             quantize_denoised=True)
+                    # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+                    #                                      quantize_denoised=True)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_x0_quantized"] = x_samples
+
+            if inpaint:
+                # make a simple center square
+                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                mask = torch.ones(N, h, w).to(self.device)
+                # zeros will be filled in
+                mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+                mask = mask[:, None, ...]
+                with self.ema_scope("Plotting Inpaint"):
+
+                    samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_inpainting"] = x_samples
+                log["mask"] = mask
+
+                # outpaint
+                with self.ema_scope("Plotting Outpaint"):
+                    samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_outpainting"] = x_samples
+
+        if plot_progressive_rows:
+            with self.ema_scope("Plotting Progressives"):
+                img, progressives = self.progressive_denoising(c,
+                                                               shape=(self.channels, self.image_size, self.image_size),
+                                                               batch_size=N)
+            prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+            log["progressive_row"] = prog_row
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.cond_stage_trainable:
+            print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+            params = params + list(self.cond_stage_model.parameters())
+        if self.learn_logvar:
+            print('Diffusion model optimizing logvar')
+            params.append(self.logvar)
+        opt = torch.optim.AdamW(params, lr=lr)
+        if self.use_scheduler:
+            assert 'target' in self.scheduler_config
+            scheduler = instantiate_from_config(self.scheduler_config)
+
+            print("Setting up LambdaLR scheduler...")
+            scheduler = [
+                {
+                    'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+                    'interval': 'step',
+                    'frequency': 1
+                }]
+            return [opt], scheduler
+        return opt
+
+    @torch.no_grad()
+    def to_rgb(self, x):
+        x = x.float()
+        if not hasattr(self, "colorize"):
+            self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+        x = nn.functional.conv2d(x, weight=self.colorize)
+        x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+        return x
+
+
+class DiffusionWrapper(pl.LightningModule):
+    def __init__(self, diff_model_config, conditioning_key):
+        super().__init__()
+        self.diffusion_model = instantiate_from_config(diff_model_config)
+        self.conditioning_key = conditioning_key
+        assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+    def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+        if self.conditioning_key is None:
+            out = self.diffusion_model(x, t)
+        elif self.conditioning_key == 'concat':
+            xc = torch.cat([x] + c_concat, dim=1)
+            out = self.diffusion_model(xc, t)
+        elif self.conditioning_key == 'crossattn':
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(x, t, context=cc)
+        elif self.conditioning_key == 'hybrid':
+            xc = torch.cat([x] + c_concat, dim=1)
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(xc, t, context=cc)
+        elif self.conditioning_key == 'adm':
+            cc = c_crossattn[0]
+            out = self.diffusion_model(x, t, y=cc)
+        else:
+            raise NotImplementedError()
+
+        return out
+
+
+class Layout2ImgDiffusion(LatentDiffusion):
+    # TODO: move all layout-specific hacks to this class
+    def __init__(self, cond_stage_key, *args, **kwargs):
+        assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+    def log_images(self, batch, N=8, *args, **kwargs):
+        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+        key = 'train' if self.training else 'validation'
+        dset = self.trainer.datamodule.datasets[key]
+        mapper = dset.conditional_builders[self.cond_stage_key]
+
+        bbox_imgs = []
+        map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+        for tknzd_bbox in batch[self.cond_stage_key][:N]:
+            bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+            bbox_imgs.append(bboximg)
+
+        cond_img = torch.stack(bbox_imgs, dim=0)
+        logs['bbox_image'] = cond_img
+        return logs

stable_diffusion/ldm/models/diffusion/ddpm_edit_disc.py

@@ -0,0 +1,1669 @@
+"""
+wild mixture of
+https://github.com/lucidrains/denoising-diffusion-pytorch/blob/7706bdfc6f527f58d33f84b7b522e61e6e3164b3/denoising_diffusion_pytorch/denoising_diffusion_pytorch.py
+https://github.com/openai/improved-diffusion/blob/e94489283bb876ac1477d5dd7709bbbd2d9902ce/improved_diffusion/gaussian_diffusion.py
+https://github.com/CompVis/taming-transformers
+-- merci
+"""
+
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+import os
+import numpy as np
+import torchvision
+import pytorch_lightning as pl
+import json
+from PIL import Image
+import pickle
+import torch.distributed as dist
+
+import torch
+import torch.nn as nn
+import numpy as np
+import pytorch_lightning as pl
+from torch.optim.lr_scheduler import LambdaLR
+from einops import rearrange, repeat
+from contextlib import contextmanager
+from functools import partial
+from tqdm import tqdm
+from torchvision.utils import make_grid
+from pytorch_lightning.utilities.distributed import rank_zero_only
+
+from ldm.util import log_txt_as_img, exists, default, ismap, isimage, mean_flat, count_params, instantiate_from_config
+from ldm.modules.ema import LitEma
+from ldm.modules.distributions.distributions import normal_kl, DiagonalGaussianDistribution
+from ldm.models.autoencoder import VQModelInterface, IdentityFirstStage, AutoencoderKL
+from ldm.modules.diffusionmodules.util import make_beta_schedule, extract_into_tensor, noise_like
+from ldm.models.diffusion.ddim import DDIMSampler
+
+
+__conditioning_keys__ = {'concat': 'c_concat',
+                         'crossattn': 'c_crossattn',
+                         'adm': 'y'}
+
+def get_world_size():
+    if not dist.is_available():
+        return 1
+    if not dist.is_initialized():
+        return 1
+    return dist.get_world_size()
+
+def all_gather(data):
+    """
+    Run all_gather on arbitrary picklable data (not necessarily tensors)
+    Args:
+        data: any picklable object
+    Returns:
+        list[data]: list of data gathered from each rank
+    """
+    world_size = get_world_size()
+    if world_size == 1:
+        return [data]
+
+    # serialized to a Tensor
+    origin_size = None
+    if not isinstance(data, torch.Tensor):
+        buffer = pickle.dumps(data)
+        storage = torch.ByteStorage.from_buffer(buffer)
+        tensor = torch.ByteTensor(storage).to("cuda")
+    else:
+        origin_size = data.size()
+        tensor = data.reshape(-1)
+
+    tensor_type = tensor.dtype
+
+    # obtain Tensor size of each rank
+    local_size = torch.LongTensor([tensor.numel()]).to("cuda")
+    size_list = [torch.LongTensor([0]).to("cuda") for _ in range(world_size)]
+    dist.all_gather(size_list, local_size)
+    size_list = [int(size.item()) for size in size_list]
+    max_size = max(size_list)
+
+    # receiving Tensor from all ranks
+    # we pad the tensor because torch all_gather does not support
+    # gathering tensors of different shapes
+    tensor_list = []
+    for _ in size_list:
+        tensor_list.append(torch.FloatTensor(size=(max_size,)).cuda().to(tensor_type))
+    if local_size != max_size:
+        padding = torch.FloatTensor(size=(max_size - local_size,)).cuda().to(tensor_type)
+        tensor = torch.cat((tensor, padding), dim=0)
+    dist.all_gather(tensor_list, tensor)
+
+    data_list = []
+    for size, tensor in zip(size_list, tensor_list):
+        if origin_size is None:
+            buffer = tensor.cpu().numpy().tobytes()[:size]
+            data_list.append(pickle.loads(buffer))
+        else:
+            buffer = tensor[:size]
+            data_list.append(buffer)
+
+    if origin_size is not None:
+        new_shape = [-1] + list(origin_size[1:])
+        resized_list = []
+        for data in data_list:
+            # suppose the difference of tensor size exist in first dimension
+            data = data.reshape(new_shape)
+            resized_list.append(data)
+
+        return resized_list
+    else:
+        return data_list
+
+def disabled_train(self, mode=True):
+    """Overwrite model.train with this function to make sure train/eval mode
+    does not change anymore."""
+    return self
+
+
+def uniform_on_device(r1, r2, shape, device):
+    return (r1 - r2) * torch.rand(*shape, device=device) + r2
+
+
+class DDPM(pl.LightningModule):
+    # classic DDPM with Gaussian diffusion, in image space
+    def __init__(self,
+                 unet_config,
+                 timesteps=1000,
+                 beta_schedule="linear",
+                 loss_type="l2",
+                 ckpt_path=None,
+                 ignore_keys=[],
+                 load_only_unet=False,
+                 monitor="val/loss",
+                 use_ema=True,
+                 first_stage_key="image",
+                 image_size=256,
+                 channels=3,
+                 log_every_t=100,
+                 clip_denoised=True,
+                 linear_start=1e-4,
+                 linear_end=2e-2,
+                 cosine_s=8e-3,
+                 given_betas=None,
+                 original_elbo_weight=0.,
+                 v_posterior=0.,  # weight for choosing posterior variance as sigma = (1-v) * beta_tilde + v * beta
+                 l_simple_weight=1.,
+                 conditioning_key=None,
+                 parameterization="eps",  # all assuming fixed variance schedules
+                 scheduler_config=None,
+                 use_positional_encodings=False,
+                 learn_logvar=False,
+                 logvar_init=0.,
+                 load_ema=True,
+                 ):
+        super().__init__()
+        assert parameterization in ["eps", "x0"], 'currently only supporting "eps" and "x0"'
+        self.parameterization = parameterization
+        print(f"{self.__class__.__name__}: Running in {self.parameterization}-prediction mode")
+        self.cond_stage_model = None
+        self.clip_denoised = clip_denoised
+        self.log_every_t = log_every_t
+        self.first_stage_key = first_stage_key
+        self.image_size = image_size  # try conv?
+        self.channels = channels
+        self.use_positional_encodings = use_positional_encodings
+        self.model = DiffusionWrapper(unet_config, conditioning_key)
+        count_params(self.model, verbose=True)
+        self.use_ema = use_ema
+
+        self.use_scheduler = scheduler_config is not None
+        if self.use_scheduler:
+            self.scheduler_config = scheduler_config
+
+        self.v_posterior = v_posterior
+        self.original_elbo_weight = original_elbo_weight
+        self.l_simple_weight = l_simple_weight
+
+        if monitor is not None:
+            self.monitor = monitor
+
+        if self.use_ema and load_ema:
+            self.model_ema = LitEma(self.model)
+            print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys=ignore_keys, only_model=load_only_unet)
+
+            # If initialing from EMA-only checkpoint, create EMA model after loading.
+            if self.use_ema and not load_ema:
+                self.model_ema = LitEma(self.model)
+                print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+        self.register_schedule(given_betas=given_betas, beta_schedule=beta_schedule, timesteps=timesteps,
+                               linear_start=linear_start, linear_end=linear_end, cosine_s=cosine_s)
+
+        self.loss_type = loss_type
+
+        self.learn_logvar = learn_logvar
+        self.logvar = torch.full(fill_value=logvar_init, size=(self.num_timesteps,))
+        if self.learn_logvar:
+            self.logvar = nn.Parameter(self.logvar, requires_grad=True)
+
+
+    def register_schedule(self, given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        if exists(given_betas):
+            betas = given_betas
+        else:
+            betas = make_beta_schedule(beta_schedule, timesteps, linear_start=linear_start, linear_end=linear_end,
+                                       cosine_s=cosine_s)
+        alphas = 1. - betas
+        alphas_cumprod = np.cumprod(alphas, axis=0)
+        alphas_cumprod_prev = np.append(1., alphas_cumprod[:-1])
+
+        timesteps, = betas.shape
+        self.num_timesteps = int(timesteps)
+        self.linear_start = linear_start
+        self.linear_end = linear_end
+        assert alphas_cumprod.shape[0] == self.num_timesteps, 'alphas have to be defined for each timestep'
+
+        to_torch = partial(torch.tensor, dtype=torch.float32)
+
+        self.register_buffer('betas', to_torch(betas))
+        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+        self.register_buffer('alphas_cumprod_prev', to_torch(alphas_cumprod_prev))
+
+        # calculations for diffusion q(x_t | x_{t-1}) and others
+        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod)))
+        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod)))
+        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod)))
+        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod)))
+        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod - 1)))
+
+        # calculations for posterior q(x_{t-1} | x_t, x_0)
+        posterior_variance = (1 - self.v_posterior) * betas * (1. - alphas_cumprod_prev) / (
+                    1. - alphas_cumprod) + self.v_posterior * betas
+        # above: equal to 1. / (1. / (1. - alpha_cumprod_tm1) + alpha_t / beta_t)
+        self.register_buffer('posterior_variance', to_torch(posterior_variance))
+        # below: log calculation clipped because the posterior variance is 0 at the beginning of the diffusion chain
+        self.register_buffer('posterior_log_variance_clipped', to_torch(np.log(np.maximum(posterior_variance, 1e-20))))
+        self.register_buffer('posterior_mean_coef1', to_torch(
+            betas * np.sqrt(alphas_cumprod_prev) / (1. - alphas_cumprod)))
+        self.register_buffer('posterior_mean_coef2', to_torch(
+            (1. - alphas_cumprod_prev) * np.sqrt(alphas) / (1. - alphas_cumprod)))
+
+        if self.parameterization == "eps":
+            lvlb_weights = self.betas ** 2 / (
+                        2 * self.posterior_variance * to_torch(alphas) * (1 - self.alphas_cumprod))
+        elif self.parameterization == "x0":
+            lvlb_weights = 0.5 * np.sqrt(torch.Tensor(alphas_cumprod)) / (2. * 1 - torch.Tensor(alphas_cumprod))
+        else:
+            raise NotImplementedError("mu not supported")
+        # TODO how to choose this term
+        lvlb_weights[0] = lvlb_weights[1]
+        self.register_buffer('lvlb_weights', lvlb_weights, persistent=False)
+        assert not torch.isnan(self.lvlb_weights).all()
+
+    @contextmanager
+    def ema_scope(self, context=None):
+        if self.use_ema:
+            self.model_ema.store(self.model.parameters())
+            self.model_ema.copy_to(self.model)
+            if context is not None:
+                print(f"{context}: Switched to EMA weights")
+        try:
+            yield None
+        finally:
+            if self.use_ema:
+                self.model_ema.restore(self.model.parameters())
+                if context is not None:
+                    print(f"{context}: Restored training weights")
+
+    def init_from_ckpt(self, path, ignore_keys=list(), only_model=False):
+        sd = torch.load(path, map_location="cpu")
+        if "state_dict" in list(sd.keys()):
+            sd = sd["state_dict"]
+        keys = list(sd.keys())
+
+        # Our model adds additional channels to the first layer to condition on an input image.
+        # For the first layer, copy existing channel weights and initialize new channel weights to zero.
+        input_keys = [
+            "model.diffusion_model.input_blocks.0.0.weight",
+            "model_ema.diffusion_modelinput_blocks00weight",
+        ]
+
+        self_sd = self.state_dict()
+        for input_key in input_keys:
+            if input_key not in sd or input_key not in self_sd:
+                continue
+
+            input_weight = self_sd[input_key]
+
+            if input_weight.size() != sd[input_key].size():
+                print(f"Manual init: {input_key}")
+                input_weight.zero_()
+                input_weight[:, :4, :, :].copy_(sd[input_key])
+                ignore_keys.append(input_key)
+
+        for k in keys:
+            for ik in ignore_keys:
+                if k.startswith(ik):
+                    print("Deleting key {} from state_dict.".format(k))
+                    del sd[k]
+        missing, unexpected = self.load_state_dict(sd, strict=False) if not only_model else self.model.load_state_dict(
+            sd, strict=False)
+        print(f"Restored from {path} with {len(missing)} missing and {len(unexpected)} unexpected keys")
+        if len(missing) > 0:
+            print(f"Missing Keys: {missing}")
+        if len(unexpected) > 0:
+            print(f"Unexpected Keys: {unexpected}")
+
+    def q_mean_variance(self, x_start, t):
+        """
+        Get the distribution q(x_t | x_0).
+        :param x_start: the [N x C x ...] tensor of noiseless inputs.
+        :param t: the number of diffusion steps (minus 1). Here, 0 means one step.
+        :return: A tuple (mean, variance, log_variance), all of x_start's shape.
+        """
+        mean = (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start)
+        variance = extract_into_tensor(1.0 - self.alphas_cumprod, t, x_start.shape)
+        log_variance = extract_into_tensor(self.log_one_minus_alphas_cumprod, t, x_start.shape)
+        return mean, variance, log_variance
+
+    def predict_start_from_noise(self, x_t, t, noise):
+        return (
+                extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t -
+                extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape) * noise
+        )
+
+    def q_posterior(self, x_start, x_t, t):
+        posterior_mean = (
+                extract_into_tensor(self.posterior_mean_coef1, t, x_t.shape) * x_start +
+                extract_into_tensor(self.posterior_mean_coef2, t, x_t.shape) * x_t
+        )
+        posterior_variance = extract_into_tensor(self.posterior_variance, t, x_t.shape)
+        posterior_log_variance_clipped = extract_into_tensor(self.posterior_log_variance_clipped, t, x_t.shape)
+        return posterior_mean, posterior_variance, posterior_log_variance_clipped
+
+    def p_mean_variance(self, x, t, clip_denoised: bool):
+        model_out = self.model(x, t)
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, t, clip_denoised=True, repeat_noise=False):
+        b, *_, device = *x.shape, x.device
+        model_mean, _, model_log_variance = self.p_mean_variance(x=x, t=t, clip_denoised=clip_denoised)
+        noise = noise_like(x.shape, device, repeat_noise)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+        return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def p_sample_loop(self, shape, return_intermediates=False):
+        device = self.betas.device
+        b = shape[0]
+        img = torch.randn(shape, device=device)
+        intermediates = [img]
+        for i in tqdm(reversed(range(0, self.num_timesteps)), desc='Sampling t', total=self.num_timesteps):
+            img = self.p_sample(img, torch.full((b,), i, device=device, dtype=torch.long),
+                                clip_denoised=self.clip_denoised)
+            if i % self.log_every_t == 0 or i == self.num_timesteps - 1:
+                intermediates.append(img)
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, batch_size=16, return_intermediates=False):
+        image_size = self.image_size
+        channels = self.channels
+        return self.p_sample_loop((batch_size, channels, image_size, image_size),
+                                  return_intermediates=return_intermediates)
+
+    def q_sample(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
+                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+
+    def get_loss(self, pred, target, mean=True):
+        if self.loss_type == 'l1':
+            loss = (target - pred).abs()
+            if mean:
+                loss = loss.mean()
+        elif self.loss_type == 'l2':
+            if mean:
+                loss = torch.nn.functional.mse_loss(target, pred)
+            else:
+                loss = torch.nn.functional.mse_loss(target, pred, reduction='none')
+        else:
+            raise NotImplementedError("unknown loss type '{loss_type}'")
+
+        return loss
+
+    def p_losses(self, x_start, t, noise=None):
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+        model_out = self.model(x_noisy, t)
+
+        loss_dict = {}
+        if self.parameterization == "eps":
+            target = noise
+        elif self.parameterization == "x0":
+            target = x_start
+        else:
+            raise NotImplementedError(f"Paramterization {self.parameterization} not yet supported")
+
+        loss = self.get_loss(model_out, target, mean=False).mean(dim=[1, 2, 3])
+
+        log_prefix = 'train' if self.training else 'val'
+
+        loss_dict.update({f'{log_prefix}/loss_simple': loss.mean()})
+        loss_simple = loss.mean() * self.l_simple_weight
+
+        loss_vlb = (self.lvlb_weights[t] * loss).mean()
+        loss_dict.update({f'{log_prefix}/loss_vlb': loss_vlb})
+
+        loss = loss_simple + self.original_elbo_weight * loss_vlb
+
+        loss_dict.update({f'{log_prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def forward(self, x, *args, **kwargs):
+        print('\n\n I made it here: forward of DDPM \n\n')
+        # b, c, h, w, device, img_size, = *x.shape, x.device, self.image_size
+        # assert h == img_size and w == img_size, f'height and width of image must be {img_size}'
+        t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        return self.p_losses(x, t, *args, **kwargs)
+
+    def get_input(self, batch, k):
+        return batch[k]
+
+    def shared_step(self, batch, discriminate=False):
+        if discriminate:
+            new_batch = {'edited': None, 'edit': {'c_concat': None, 'c_crossattn': None}}
+            for i in batch['edited'].shape[0]:
+                new_batch['edited'] = batch['edited'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+                new_batch['edit']['c_concat'] = batch['edit']['c_concat'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+                new_batch['edit']['c_crossattn'] = batch['edit']['c_crossattn'][i]
+                x = self.get_input(new_batch, self.first_stage_key)
+                loss, loss_dict = self(x)
+        else:
+            x = self.get_input(batch, self.first_stage_key)
+            loss, loss_dict = self(x)
+        return loss, loss_dict
+
+    def training_step(self, batch, batch_idx):
+        loss, loss_dict = self.shared_step(batch)
+
+        self.log_dict(loss_dict, prog_bar=True,
+                      logger=True, on_step=True, on_epoch=True)
+
+        self.log("global_step", self.global_step,
+                 prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        if self.use_scheduler:
+            lr = self.optimizers().param_groups[0]['lr']
+            self.log('lr_abs', lr, prog_bar=True, logger=True, on_step=True, on_epoch=False)
+
+        return loss
+
+    # def log_local(self, save_dir, split, images, prompts,
+    #               global_step, current_epoch, batch_idx):
+    #     root = os.path.join(save_dir, "images", split)
+    #     names = {"reals": "before", "inputs": "after", "reconstruction": "before-vq", "samples": "after-gen"}
+    #     # print(root)
+    #     for k in images:
+    #         grid = torchvision.utils.make_grid(images[k], nrow=8)
+    #         if self.rescale:
+    #             grid = (grid + 1.0) / 2.0  # -1,1 -> 0,1; c,h,w
+    #         grid = grid.transpose(0, 1).transpose(1, 2).squeeze(-1)
+    #         grid = grid.numpy()
+    #         grid = (grid * 255).astype(np.uint8)
+    #         filename = "gs-{:06}_e-{:06}_b-{:06}_{}.png".format(
+    #             global_step,
+    #             current_epoch,
+    #             batch_idx,
+    #             names[k])
+    #         path = os.path.join(root, filename)
+    #         os.makedirs(os.path.split(path)[0], exist_ok=True)
+    #         # print(path)
+    #         Image.fromarray(grid).save(path)
+
+    #     filename = "gs-{:06}_e-{:06}_b-{:06}_prompt.json".format(
+    #         global_step,
+    #         current_epoch,
+    #         batch_idx)
+    #     path = os.path.join(root, filename)
+    #     with open(path, "w") as f:
+    #         for p in prompts:
+    #             f.write(f"{json.dumps(p)}\n")
+
+    # def log_img(self, batch, batch_idx, split="val"):
+    #     check_idx = batch_idx if self.log_on_batch_idx else self.global_step
+    #     if (self.check_frequency(check_idx) and  # batch_idx % self.batch_freq == 0
+    #             hasattr(self, "log_images") and
+    #             callable(self.log_images) and
+    #             self.max_images > 0) or (split == "val" and batch_idx == 0):
+    #         logger = type(self.logger)
+
+    #         is_train = self.training
+    #         if is_train:
+    #             self.eval()
+
+    #         with torch.no_grad():
+    #             images = self.log_images(batch, split=split, **self.log_images_kwargs)
+
+    #         prompts = batch["edit"]["c_crossattn"][:self.max_images]
+    #         prompts = [p for ps in all_gather(prompts) for p in ps]
+
+    #         for k in images:
+    #             N = min(images[k].shape[0], self.max_images)
+    #             images[k] = images[k][:N]
+    #             images[k] = torch.cat(all_gather(images[k][:N]))
+    #             if isinstance(images[k], torch.Tensor):
+    #                 images[k] = images[k].detach().cpu()
+    #                 if self.clamp:
+    #                     images[k] = torch.clamp(images[k], -1., 1.)
+
+    #         self.log_local(self.logger.save_dir, split, images, prompts,
+    #                        self.global_step, self.current_epoch, batch_idx)
+
+    #         logger_log_images = self.logger_log_images.get(logger, lambda *args, **kwargs: None)
+    #         logger_log_images(self, images, self.global_step, split)
+
+    #         if is_train:
+    #             self.train()
+
+
+    @torch.no_grad()
+    def validation_step(self, batch, batch_idx, discriminate=False):
+        self.discriminate = discriminate
+        def calculate_accuracy(losses):
+            correct_count = 0
+            for loss in losses:
+                if loss[0] < min(loss[1:]):
+                    correct_count += 1
+            return correct_count, len(losses)  # Return counts for aggregation
+        
+        # self.log_img(batch, batch_idx, split="val")
+        losses = self.shared_step(batch, discriminate=discriminate)
+        if discriminate:
+            correct_count, total_count = calculate_accuracy(losses)
+            return {'correct_count': correct_count, 'total_count': total_count}
+        else:
+            _, loss_dict_no_ema = self.shared_step(batch)
+            with self.ema_scope():
+                _, loss_dict_ema = self.shared_step(batch)
+                loss_dict_ema = {key + '_ema': loss_dict_ema[key] for key in loss_dict_ema}
+            self.log_dict(loss_dict_no_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+            self.log_dict(loss_dict_ema, prog_bar=False, logger=True, on_step=False, on_epoch=True)
+
+    def validation_epoch_end(self, outputs):
+        if self.discriminate:
+            correct_count = sum(x['correct_count'] for x in outputs)
+            total_count = sum(x['total_count'] for x in outputs)
+            overall_accuracy = (correct_count / total_count) * 100
+            print(f"Overall accuracy: {overall_accuracy:.2f}%")
+            import pdb; pdb.set_trace()
+            self.log('overall_accuracy', overall_accuracy, prog_bar=True, logger=True)
+
+    def on_train_batch_end(self, *args, **kwargs):
+        if self.use_ema:
+            self.model_ema(self.model)
+
+    def _get_rows_from_list(self, samples):
+        n_imgs_per_row = len(samples)
+        denoise_grid = rearrange(samples, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    @torch.no_grad()
+    def log_images(self, batch, N=8, n_row=2, sample=True, return_keys=None, **kwargs):
+        log = dict()
+        x = self.get_input(batch, self.first_stage_key)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        x = x.to(self.device)[:N]
+        log["inputs"] = x
+
+        # get diffusion row
+        diffusion_row = list()
+        x_start = x[:n_row]
+
+        for t in range(self.num_timesteps):
+            if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                t = t.to(self.device).long()
+                noise = torch.randn_like(x_start)
+                x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+                diffusion_row.append(x_noisy)
+
+        log["diffusion_row"] = self._get_rows_from_list(diffusion_row)
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, denoise_row = self.sample(batch_size=N, return_intermediates=True)
+
+            log["samples"] = samples
+            log["denoise_row"] = self._get_rows_from_list(denoise_row)
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.learn_logvar:
+            params = params + [self.logvar]
+        opt = torch.optim.AdamW(params, lr=lr)
+        return opt
+
+
+class LatentDiffusion(DDPM):
+    """main class"""
+    def __init__(self,
+                 first_stage_config,
+                 cond_stage_config,
+                 num_timesteps_cond=None,
+                 cond_stage_key="image",
+                 cond_stage_trainable=False,
+                 concat_mode=True,
+                 cond_stage_forward=None,
+                 conditioning_key=None,
+                 scale_factor=1.0,
+                 scale_by_std=False,
+                 load_ema=True,
+                 *args, **kwargs):
+        self.num_timesteps_cond = default(num_timesteps_cond, 1)
+        self.scale_by_std = scale_by_std
+        assert self.num_timesteps_cond <= kwargs['timesteps']
+        # for backwards compatibility after implementation of DiffusionWrapper
+        if conditioning_key is None:
+            conditioning_key = 'concat' if concat_mode else 'crossattn'
+        if cond_stage_config == '__is_unconditional__':
+            conditioning_key = None
+        ckpt_path = kwargs.pop("ckpt_path", None)
+        ignore_keys = kwargs.pop("ignore_keys", [])
+        super().__init__(conditioning_key=conditioning_key, *args, load_ema=load_ema, **kwargs)
+        self.concat_mode = concat_mode
+        self.cond_stage_trainable = cond_stage_trainable
+        self.cond_stage_key = cond_stage_key
+        try:
+            self.num_downs = len(first_stage_config.params.ddconfig.ch_mult) - 1
+        except:
+            self.num_downs = 0
+        if not scale_by_std:
+            self.scale_factor = scale_factor
+        else:
+            self.register_buffer('scale_factor', torch.tensor(scale_factor))
+        self.instantiate_first_stage(first_stage_config)
+        self.instantiate_cond_stage(cond_stage_config)
+        self.cond_stage_forward = cond_stage_forward
+        self.clip_denoised = False
+        self.bbox_tokenizer = None
+
+        self.restarted_from_ckpt = False
+        if ckpt_path is not None:
+            self.init_from_ckpt(ckpt_path, ignore_keys)
+            self.restarted_from_ckpt = True
+
+            if self.use_ema and not load_ema:
+                self.model_ema = LitEma(self.model)
+                print(f"Keeping EMAs of {len(list(self.model_ema.buffers()))}.")
+
+    def make_cond_schedule(self, ):
+        self.cond_ids = torch.full(size=(self.num_timesteps,), fill_value=self.num_timesteps - 1, dtype=torch.long)
+        ids = torch.round(torch.linspace(0, self.num_timesteps - 1, self.num_timesteps_cond)).long()
+        self.cond_ids[:self.num_timesteps_cond] = ids
+
+    @rank_zero_only
+    @torch.no_grad()
+    def on_train_batch_start(self, batch, batch_idx, dataloader_idx):
+        # only for very first batch
+        if self.scale_by_std and self.current_epoch == 0 and self.global_step == 0 and batch_idx == 0 and not self.restarted_from_ckpt:
+            assert self.scale_factor == 1., 'rather not use custom rescaling and std-rescaling simultaneously'
+            # set rescale weight to 1./std of encodings
+            print("### USING STD-RESCALING ###")
+            x = super().get_input(batch, self.first_stage_key)
+            x = x.to(self.device)
+            encoder_posterior = self.encode_first_stage(x)
+            z = self.get_first_stage_encoding(encoder_posterior).detach()
+            del self.scale_factor
+            self.register_buffer('scale_factor', 1. / z.flatten().std())
+            print(f"setting self.scale_factor to {self.scale_factor}")
+            print("### USING STD-RESCALING ###")
+
+    def register_schedule(self,
+                          given_betas=None, beta_schedule="linear", timesteps=1000,
+                          linear_start=1e-4, linear_end=2e-2, cosine_s=8e-3):
+        super().register_schedule(given_betas, beta_schedule, timesteps, linear_start, linear_end, cosine_s)
+
+        self.shorten_cond_schedule = self.num_timesteps_cond > 1
+        if self.shorten_cond_schedule:
+            self.make_cond_schedule()
+
+    def instantiate_first_stage(self, config):
+        model = instantiate_from_config(config)
+        self.first_stage_model = model.eval()
+        self.first_stage_model.train = disabled_train
+        for param in self.first_stage_model.parameters():
+            param.requires_grad = False
+
+    def instantiate_cond_stage(self, config):
+        if not self.cond_stage_trainable:
+            if config == "__is_first_stage__":
+                print("Using first stage also as cond stage.")
+                self.cond_stage_model = self.first_stage_model
+            elif config == "__is_unconditional__":
+                print(f"Training {self.__class__.__name__} as an unconditional model.")
+                self.cond_stage_model = None
+                # self.be_unconditional = True
+            else:
+                model = instantiate_from_config(config)
+                self.cond_stage_model = model.eval()
+                self.cond_stage_model.train = disabled_train
+                for param in self.cond_stage_model.parameters():
+                    param.requires_grad = False
+        else:
+            assert config != '__is_first_stage__'
+            assert config != '__is_unconditional__'
+            model = instantiate_from_config(config)
+            self.cond_stage_model = model
+
+    def _get_denoise_row_from_list(self, samples, desc='', force_no_decoder_quantization=False):
+        denoise_row = []
+        for zd in tqdm(samples, desc=desc):
+            denoise_row.append(self.decode_first_stage(zd.to(self.device),
+                                                            force_not_quantize=force_no_decoder_quantization))
+        n_imgs_per_row = len(denoise_row)
+        denoise_row = torch.stack(denoise_row)  # n_log_step, n_row, C, H, W
+        denoise_grid = rearrange(denoise_row, 'n b c h w -> b n c h w')
+        denoise_grid = rearrange(denoise_grid, 'b n c h w -> (b n) c h w')
+        denoise_grid = make_grid(denoise_grid, nrow=n_imgs_per_row)
+        return denoise_grid
+
+    def get_first_stage_encoding(self, encoder_posterior):
+        if isinstance(encoder_posterior, DiagonalGaussianDistribution):
+            z = encoder_posterior.sample()
+        elif isinstance(encoder_posterior, torch.Tensor):
+            z = encoder_posterior
+        else:
+            raise NotImplementedError(f"encoder_posterior of type '{type(encoder_posterior)}' not yet implemented")
+        return self.scale_factor * z
+
+    def get_learned_conditioning(self, c):
+        if self.cond_stage_forward is None:
+            if hasattr(self.cond_stage_model, 'encode') and callable(self.cond_stage_model.encode):
+                c = self.cond_stage_model.encode(c)
+                if isinstance(c, DiagonalGaussianDistribution):
+                    c = c.mode()
+            else:
+                c = self.cond_stage_model(c)
+        else:
+            assert hasattr(self.cond_stage_model, self.cond_stage_forward)
+            c = getattr(self.cond_stage_model, self.cond_stage_forward)(c)
+        return c
+
+    def meshgrid(self, h, w):
+        y = torch.arange(0, h).view(h, 1, 1).repeat(1, w, 1)
+        x = torch.arange(0, w).view(1, w, 1).repeat(h, 1, 1)
+
+        arr = torch.cat([y, x], dim=-1)
+        return arr
+
+    def delta_border(self, h, w):
+        """
+        :param h: height
+        :param w: width
+        :return: normalized distance to image border,
+         wtith min distance = 0 at border and max dist = 0.5 at image center
+        """
+        lower_right_corner = torch.tensor([h - 1, w - 1]).view(1, 1, 2)
+        arr = self.meshgrid(h, w) / lower_right_corner
+        dist_left_up = torch.min(arr, dim=-1, keepdims=True)[0]
+        dist_right_down = torch.min(1 - arr, dim=-1, keepdims=True)[0]
+        edge_dist = torch.min(torch.cat([dist_left_up, dist_right_down], dim=-1), dim=-1)[0]
+        return edge_dist
+
+    def get_weighting(self, h, w, Ly, Lx, device):
+        weighting = self.delta_border(h, w)
+        weighting = torch.clip(weighting, self.split_input_params["clip_min_weight"],
+                               self.split_input_params["clip_max_weight"], )
+        weighting = weighting.view(1, h * w, 1).repeat(1, 1, Ly * Lx).to(device)
+
+        if self.split_input_params["tie_braker"]:
+            L_weighting = self.delta_border(Ly, Lx)
+            L_weighting = torch.clip(L_weighting,
+                                     self.split_input_params["clip_min_tie_weight"],
+                                     self.split_input_params["clip_max_tie_weight"])
+
+            L_weighting = L_weighting.view(1, 1, Ly * Lx).to(device)
+            weighting = weighting * L_weighting
+        return weighting
+
+    def get_fold_unfold(self, x, kernel_size, stride, uf=1, df=1):  # todo load once not every time, shorten code
+        """
+        :param x: img of size (bs, c, h, w)
+        :return: n img crops of size (n, bs, c, kernel_size[0], kernel_size[1])
+        """
+        bs, nc, h, w = x.shape
+
+        # number of crops in image
+        Ly = (h - kernel_size[0]) // stride[0] + 1
+        Lx = (w - kernel_size[1]) // stride[1] + 1
+
+        if uf == 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold = torch.nn.Fold(output_size=x.shape[2:], **fold_params)
+
+            weighting = self.get_weighting(kernel_size[0], kernel_size[1], Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h, w)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0], kernel_size[1], Ly * Lx))
+
+        elif uf > 1 and df == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] * uf, kernel_size[0] * uf),
+                                dilation=1, padding=0,
+                                stride=(stride[0] * uf, stride[1] * uf))
+            fold = torch.nn.Fold(output_size=(x.shape[2] * uf, x.shape[3] * uf), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] * uf, kernel_size[1] * uf, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h * uf, w * uf)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] * uf, kernel_size[1] * uf, Ly * Lx))
+
+        elif df > 1 and uf == 1:
+            fold_params = dict(kernel_size=kernel_size, dilation=1, padding=0, stride=stride)
+            unfold = torch.nn.Unfold(**fold_params)
+
+            fold_params2 = dict(kernel_size=(kernel_size[0] // df, kernel_size[0] // df),
+                                dilation=1, padding=0,
+                                stride=(stride[0] // df, stride[1] // df))
+            fold = torch.nn.Fold(output_size=(x.shape[2] // df, x.shape[3] // df), **fold_params2)
+
+            weighting = self.get_weighting(kernel_size[0] // df, kernel_size[1] // df, Ly, Lx, x.device).to(x.dtype)
+            normalization = fold(weighting).view(1, 1, h // df, w // df)  # normalizes the overlap
+            weighting = weighting.view((1, 1, kernel_size[0] // df, kernel_size[1] // df, Ly * Lx))
+
+        else:
+            raise NotImplementedError
+
+        return fold, unfold, normalization, weighting
+
+    @torch.no_grad()
+    def get_input(self, batch, k, return_first_stage_outputs=False, force_c_encode=False,
+                  cond_key=None, return_original_cond=False, bs=None, uncond=0.05):
+        x = super().get_input(batch, k)
+        if bs is not None:
+            x = x[:bs]
+        x = x.to(self.device)
+        encoder_posterior = self.encode_first_stage(x)
+        z = self.get_first_stage_encoding(encoder_posterior).detach()
+        cond_key = cond_key or self.cond_stage_key
+        xc = super().get_input(batch, cond_key)
+        if bs is not None:
+            xc["c_crossattn"] = xc["c_crossattn"][:bs]
+            xc["c_concat"] = xc["c_concat"][:bs]
+        cond = {}
+
+        # To support classifier-free guidance, randomly drop out only text conditioning 5%, only image conditioning 5%, and both 5%.
+        random = torch.rand(x.size(0), device=x.device)
+        prompt_mask = rearrange(random < 2 * uncond, "n -> n 1 1")
+        input_mask = 1 - rearrange((random >= uncond).float() * (random < 3 * uncond).float(), "n -> n 1 1 1")
+
+        null_prompt = self.get_learned_conditioning([""])
+        cond["c_crossattn"] = [torch.where(prompt_mask, null_prompt, self.get_learned_conditioning(xc["c_crossattn"]).detach())]
+        cond["c_concat"] = [input_mask * self.encode_first_stage((xc["c_concat"].to(self.device))).mode().detach()]
+
+        out = [z, cond]
+        if return_first_stage_outputs:
+            xrec = self.decode_first_stage(z)
+            out.extend([x, xrec])
+        if return_original_cond:
+            out.append(xc)
+        return out
+
+    @torch.no_grad()
+    def decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    # same as above but without decorator
+    def differentiable_decode_first_stage(self, z, predict_cids=False, force_not_quantize=False):
+        if predict_cids:
+            if z.dim() == 4:
+                z = torch.argmax(z.exp(), dim=1).long()
+            z = self.first_stage_model.quantize.get_codebook_entry(z, shape=None)
+            z = rearrange(z, 'b h w c -> b c h w').contiguous()
+
+        z = 1. / self.scale_factor * z
+
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                uf = self.split_input_params["vqf"]
+                bs, nc, h, w = z.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(z, ks, stride, uf=uf)
+
+                z = unfold(z)  # (bn, nc * prod(**ks), L)
+                # 1. Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                # 2. apply model loop over last dim
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i],
+                                                                 force_not_quantize=predict_cids or force_not_quantize)
+                                   for i in range(z.shape[-1])]
+                else:
+
+                    output_list = [self.first_stage_model.decode(z[:, :, :, :, i])
+                                   for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)  # # (bn, nc, ks[0], ks[1], L)
+                o = o * weighting
+                # Reverse 1. reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization  # norm is shape (1, 1, h, w)
+                return decoded
+            else:
+                if isinstance(self.first_stage_model, VQModelInterface):
+                    return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+                else:
+                    return self.first_stage_model.decode(z)
+
+        else:
+            if isinstance(self.first_stage_model, VQModelInterface):
+                return self.first_stage_model.decode(z, force_not_quantize=predict_cids or force_not_quantize)
+            else:
+                return self.first_stage_model.decode(z)
+
+    @torch.no_grad()
+    def encode_first_stage(self, x):
+        if hasattr(self, "split_input_params"):
+            if self.split_input_params["patch_distributed_vq"]:
+                ks = self.split_input_params["ks"]  # eg. (128, 128)
+                stride = self.split_input_params["stride"]  # eg. (64, 64)
+                df = self.split_input_params["vqf"]
+                self.split_input_params['original_image_size'] = x.shape[-2:]
+                bs, nc, h, w = x.shape
+                if ks[0] > h or ks[1] > w:
+                    ks = (min(ks[0], h), min(ks[1], w))
+                    print("reducing Kernel")
+
+                if stride[0] > h or stride[1] > w:
+                    stride = (min(stride[0], h), min(stride[1], w))
+                    print("reducing stride")
+
+                fold, unfold, normalization, weighting = self.get_fold_unfold(x, ks, stride, df=df)
+                z = unfold(x)  # (bn, nc * prod(**ks), L)
+                # Reshape to img shape
+                z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                output_list = [self.first_stage_model.encode(z[:, :, :, :, i])
+                               for i in range(z.shape[-1])]
+
+                o = torch.stack(output_list, axis=-1)
+                o = o * weighting
+
+                # Reverse reshape to img shape
+                o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+                # stitch crops together
+                decoded = fold(o)
+                decoded = decoded / normalization
+                return decoded
+
+            else:
+                return self.first_stage_model.encode(x)
+        else:
+            return self.first_stage_model.encode(x)
+
+    def shared_step(self, batch, discriminate=False, **kwargs):
+        if discriminate:
+            new_batch = {'edited': None, 'edit': {'c_concat': None, 'c_crossattn': None}}
+            losses = []
+            for i in range(batch['edited'].shape[0]):
+                new_batch['edited'] = batch['edited'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+                new_batch['edit']['c_concat'] = batch['edit']['c_concat'][i].unsqueeze(0).repeat((10, 1, 1, 1))
+                losses_ = []
+                for k in range(len(batch['edit']['c_crossattn'])):
+                    new_batch['edit']['c_crossattn'] = batch['edit']['c_crossattn'][k][i]
+                    x, c = self.get_input(new_batch, self.first_stage_key, uncond=0.0)
+                    loss = self(x, c, discriminate=discriminate)
+                    loss = loss[1]['val/loss_simple']
+                    losses_.append(loss)
+                losses.append(losses_)
+            return losses
+        else:
+            x, c = self.get_input(batch, self.first_stage_key)
+            loss = self(x, c)
+            return loss
+
+    def forward(self, x, c, discriminate=False, *args, **kwargs):
+        if discriminate:
+            t = torch.linspace(10, self.num_timesteps-10, steps=x.shape[0], device=self.device).long()
+        else:
+            t = torch.randint(0, self.num_timesteps, (x.shape[0],), device=self.device).long()
+        if self.model.conditioning_key is not None:
+            assert c is not None
+            if self.cond_stage_trainable:
+                c = self.get_learned_conditioning(c)
+            if self.shorten_cond_schedule:  # TODO: drop this option
+                tc = self.cond_ids[t].to(self.device)
+                c = self.q_sample(x_start=c, t=tc, noise=torch.randn_like(c.float()))
+        return self.p_losses(x, c, t, discriminate=True, *args, **kwargs)
+
+    def _rescale_annotations(self, bboxes, crop_coordinates):  # TODO: move to dataset
+        def rescale_bbox(bbox):
+            x0 = clamp((bbox[0] - crop_coordinates[0]) / crop_coordinates[2])
+            y0 = clamp((bbox[1] - crop_coordinates[1]) / crop_coordinates[3])
+            w = min(bbox[2] / crop_coordinates[2], 1 - x0)
+            h = min(bbox[3] / crop_coordinates[3], 1 - y0)
+            return x0, y0, w, h
+
+        return [rescale_bbox(b) for b in bboxes]
+
+    def apply_model(self, x_noisy, t, cond, return_ids=False):
+
+        if isinstance(cond, dict):
+            # hybrid case, cond is exptected to be a dict
+            pass
+        else:
+            if not isinstance(cond, list):
+                cond = [cond]
+            key = 'c_concat' if self.model.conditioning_key == 'concat' else 'c_crossattn'
+            cond = {key: cond}
+
+        if hasattr(self, "split_input_params"):
+            assert len(cond) == 1  # todo can only deal with one conditioning atm
+            assert not return_ids
+            ks = self.split_input_params["ks"]  # eg. (128, 128)
+            stride = self.split_input_params["stride"]  # eg. (64, 64)
+
+            h, w = x_noisy.shape[-2:]
+
+            fold, unfold, normalization, weighting = self.get_fold_unfold(x_noisy, ks, stride)
+
+            z = unfold(x_noisy)  # (bn, nc * prod(**ks), L)
+            # Reshape to img shape
+            z = z.view((z.shape[0], -1, ks[0], ks[1], z.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+            z_list = [z[:, :, :, :, i] for i in range(z.shape[-1])]
+
+            if self.cond_stage_key in ["image", "LR_image", "segmentation",
+                                       'bbox_img'] and self.model.conditioning_key:  # todo check for completeness
+                c_key = next(iter(cond.keys()))  # get key
+                c = next(iter(cond.values()))  # get value
+                assert (len(c) == 1)  # todo extend to list with more than one elem
+                c = c[0]  # get element
+
+                c = unfold(c)
+                c = c.view((c.shape[0], -1, ks[0], ks[1], c.shape[-1]))  # (bn, nc, ks[0], ks[1], L )
+
+                cond_list = [{c_key: [c[:, :, :, :, i]]} for i in range(c.shape[-1])]
+
+            elif self.cond_stage_key == 'coordinates_bbox':
+                assert 'original_image_size' in self.split_input_params, 'BoudingBoxRescaling is missing original_image_size'
+
+                # assuming padding of unfold is always 0 and its dilation is always 1
+                n_patches_per_row = int((w - ks[0]) / stride[0] + 1)
+                full_img_h, full_img_w = self.split_input_params['original_image_size']
+                # as we are operating on latents, we need the factor from the original image size to the
+                # spatial latent size to properly rescale the crops for regenerating the bbox annotations
+                num_downs = self.first_stage_model.encoder.num_resolutions - 1
+                rescale_latent = 2 ** (num_downs)
+
+                # get top left postions of patches as conforming for the bbbox tokenizer, therefore we
+                # need to rescale the tl patch coordinates to be in between (0,1)
+                tl_patch_coordinates = [(rescale_latent * stride[0] * (patch_nr % n_patches_per_row) / full_img_w,
+                                         rescale_latent * stride[1] * (patch_nr // n_patches_per_row) / full_img_h)
+                                        for patch_nr in range(z.shape[-1])]
+
+                # patch_limits are tl_coord, width and height coordinates as (x_tl, y_tl, h, w)
+                patch_limits = [(x_tl, y_tl,
+                                 rescale_latent * ks[0] / full_img_w,
+                                 rescale_latent * ks[1] / full_img_h) for x_tl, y_tl in tl_patch_coordinates]
+                # patch_values = [(np.arange(x_tl,min(x_tl+ks, 1.)),np.arange(y_tl,min(y_tl+ks, 1.))) for x_tl, y_tl in tl_patch_coordinates]
+
+                # tokenize crop coordinates for the bounding boxes of the respective patches
+                patch_limits_tknzd = [torch.LongTensor(self.bbox_tokenizer._crop_encoder(bbox))[None].to(self.device)
+                                      for bbox in patch_limits]  # list of length l with tensors of shape (1, 2)
+                print(patch_limits_tknzd[0].shape)
+                # cut tknzd crop position from conditioning
+                assert isinstance(cond, dict), 'cond must be dict to be fed into model'
+                cut_cond = cond['c_crossattn'][0][..., :-2].to(self.device)
+                print(cut_cond.shape)
+
+                adapted_cond = torch.stack([torch.cat([cut_cond, p], dim=1) for p in patch_limits_tknzd])
+                adapted_cond = rearrange(adapted_cond, 'l b n -> (l b) n')
+                print(adapted_cond.shape)
+                adapted_cond = self.get_learned_conditioning(adapted_cond)
+                print(adapted_cond.shape)
+                adapted_cond = rearrange(adapted_cond, '(l b) n d -> l b n d', l=z.shape[-1])
+                print(adapted_cond.shape)
+
+                cond_list = [{'c_crossattn': [e]} for e in adapted_cond]
+
+            else:
+                cond_list = [cond for i in range(z.shape[-1])]  # Todo make this more efficient
+
+            # apply model by loop over crops
+            output_list = [self.model(z_list[i], t, **cond_list[i]) for i in range(z.shape[-1])]
+            assert not isinstance(output_list[0],
+                                  tuple)  # todo cant deal with multiple model outputs check this never happens
+
+            o = torch.stack(output_list, axis=-1)
+            o = o * weighting
+            # Reverse reshape to img shape
+            o = o.view((o.shape[0], -1, o.shape[-1]))  # (bn, nc * ks[0] * ks[1], L)
+            # stitch crops together
+            x_recon = fold(o) / normalization
+
+        else:
+            x_recon = self.model(x_noisy, t, **cond)
+
+        if isinstance(x_recon, tuple) and not return_ids:
+            return x_recon[0]
+        else:
+            return x_recon
+
+    def _predict_eps_from_xstart(self, x_t, t, pred_xstart):
+        return (extract_into_tensor(self.sqrt_recip_alphas_cumprod, t, x_t.shape) * x_t - pred_xstart) / \
+               extract_into_tensor(self.sqrt_recipm1_alphas_cumprod, t, x_t.shape)
+
+    def _prior_bpd(self, x_start):
+        """
+        Get the prior KL term for the variational lower-bound, measured in
+        bits-per-dim.
+        This term can't be optimized, as it only depends on the encoder.
+        :param x_start: the [N x C x ...] tensor of inputs.
+        :return: a batch of [N] KL values (in bits), one per batch element.
+        """
+        batch_size = x_start.shape[0]
+        t = torch.tensor([self.num_timesteps - 1] * batch_size, device=x_start.device)
+        qt_mean, _, qt_log_variance = self.q_mean_variance(x_start, t)
+        kl_prior = normal_kl(mean1=qt_mean, logvar1=qt_log_variance, mean2=0.0, logvar2=0.0)
+        return mean_flat(kl_prior) / np.log(2.0)
+
+    def p_losses(self, x_start, cond, t, discriminate=False, noise=None):
+        if discriminate:
+            # set seed
+            torch.manual_seed(0)
+        noise = default(noise, lambda: torch.randn_like(x_start))
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+
+        #Override for debugging TODO: delete
+        # import pickle
+        # with open(os.path.expanduser("~/diffusion-itm/first_noise.pkl"), "rb") as f:
+        #     noise = pickle.load(f)
+        #     noise = noise.to(self.device).unsqueeze(0).repeat(x_start.shape[0], 1, 1, 1)
+        x_noisy = self.q_sample(x_start=x_start, t=t, noise=noise)
+
+        model_output = self.apply_model(x_noisy, t, cond)
+
+        loss_dict = {}
+        prefix = 'train' if self.training else 'val'
+
+        if self.parameterization == "x0":
+            target = x_start
+        elif self.parameterization == "eps":
+            target = noise
+        else:
+            raise NotImplementedError()
+
+        loss_simple = self.get_loss(model_output, target, mean=False).mean([1, 2, 3])
+        # loss_dict.update({f'{prefix}/loss_simple_list': loss_simple})
+        loss_dict.update({f'{prefix}/loss_simple': loss_simple.mean()})
+
+        logvar_t = self.logvar.to(self.device)[t]
+        loss = loss_simple / torch.exp(logvar_t) + logvar_t
+        # loss = loss_simple / torch.exp(self.logvar) + self.logvar
+        if self.learn_logvar:
+            loss_dict.update({f'{prefix}/loss_gamma': loss.mean()})
+            loss_dict.update({'logvar': self.logvar.data.mean()})
+
+        loss = self.l_simple_weight * loss.mean()
+
+        loss_vlb = self.get_loss(model_output, target, mean=False).mean(dim=(1, 2, 3))
+        loss_vlb = (self.lvlb_weights[t] * loss_vlb).mean()
+        loss_dict.update({f'{prefix}/loss_vlb': loss_vlb})
+        loss += (self.original_elbo_weight * loss_vlb)
+        loss_dict.update({f'{prefix}/loss': loss})
+
+        return loss, loss_dict
+
+    def p_mean_variance(self, x, c, t, clip_denoised: bool, return_codebook_ids=False, quantize_denoised=False,
+                        return_x0=False, score_corrector=None, corrector_kwargs=None):
+        t_in = t
+        model_out = self.apply_model(x, t_in, c, return_ids=return_codebook_ids)
+
+        if score_corrector is not None:
+            assert self.parameterization == "eps"
+            model_out = score_corrector.modify_score(self, model_out, x, t, c, **corrector_kwargs)
+
+        if return_codebook_ids:
+            model_out, logits = model_out
+
+        if self.parameterization == "eps":
+            x_recon = self.predict_start_from_noise(x, t=t, noise=model_out)
+        elif self.parameterization == "x0":
+            x_recon = model_out
+        else:
+            raise NotImplementedError()
+
+        if clip_denoised:
+            x_recon.clamp_(-1., 1.)
+        if quantize_denoised:
+            x_recon, _, [_, _, indices] = self.first_stage_model.quantize(x_recon)
+        model_mean, posterior_variance, posterior_log_variance = self.q_posterior(x_start=x_recon, x_t=x, t=t)
+        if return_codebook_ids:
+            return model_mean, posterior_variance, posterior_log_variance, logits
+        elif return_x0:
+            return model_mean, posterior_variance, posterior_log_variance, x_recon
+        else:
+            return model_mean, posterior_variance, posterior_log_variance
+
+    @torch.no_grad()
+    def p_sample(self, x, c, t, clip_denoised=False, repeat_noise=False,
+                 return_codebook_ids=False, quantize_denoised=False, return_x0=False,
+                 temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None):
+        b, *_, device = *x.shape, x.device
+        outputs = self.p_mean_variance(x=x, c=c, t=t, clip_denoised=clip_denoised,
+                                       return_codebook_ids=return_codebook_ids,
+                                       quantize_denoised=quantize_denoised,
+                                       return_x0=return_x0,
+                                       score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+        if return_codebook_ids:
+            raise DeprecationWarning("Support dropped.")
+            model_mean, _, model_log_variance, logits = outputs
+        elif return_x0:
+            model_mean, _, model_log_variance, x0 = outputs
+        else:
+            model_mean, _, model_log_variance = outputs
+
+        noise = noise_like(x.shape, device, repeat_noise) * temperature
+        if noise_dropout > 0.:
+            noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+        # no noise when t == 0
+        nonzero_mask = (1 - (t == 0).float()).reshape(b, *((1,) * (len(x.shape) - 1)))
+
+        if return_codebook_ids:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, logits.argmax(dim=1)
+        if return_x0:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise, x0
+        else:
+            return model_mean + nonzero_mask * (0.5 * model_log_variance).exp() * noise
+
+    @torch.no_grad()
+    def progressive_denoising(self, cond, shape, verbose=True, callback=None, quantize_denoised=False,
+                              img_callback=None, mask=None, x0=None, temperature=1., noise_dropout=0.,
+                              score_corrector=None, corrector_kwargs=None, batch_size=None, x_T=None, start_T=None,
+                              log_every_t=None):
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        timesteps = self.num_timesteps
+        if batch_size is not None:
+            b = batch_size if batch_size is not None else shape[0]
+            shape = [batch_size] + list(shape)
+        else:
+            b = batch_size = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=self.device)
+        else:
+            img = x_T
+        intermediates = []
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Progressive Generation',
+                        total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+        if type(temperature) == float:
+            temperature = [temperature] * timesteps
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=self.device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img, x0_partial = self.p_sample(img, cond, ts,
+                                            clip_denoised=self.clip_denoised,
+                                            quantize_denoised=quantize_denoised, return_x0=True,
+                                            temperature=temperature[i], noise_dropout=noise_dropout,
+                                            score_corrector=score_corrector, corrector_kwargs=corrector_kwargs)
+            if mask is not None:
+                assert x0 is not None
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(x0_partial)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+        return img, intermediates
+
+    @torch.no_grad()
+    def p_sample_loop(self, cond, shape, return_intermediates=False,
+                      x_T=None, verbose=True, callback=None, timesteps=None, quantize_denoised=False,
+                      mask=None, x0=None, img_callback=None, start_T=None,
+                      log_every_t=None):
+
+        if not log_every_t:
+            log_every_t = self.log_every_t
+        device = self.betas.device
+        b = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=device)
+        else:
+            img = x_T
+
+        intermediates = [img]
+        if timesteps is None:
+            timesteps = self.num_timesteps
+
+        if start_T is not None:
+            timesteps = min(timesteps, start_T)
+        iterator = tqdm(reversed(range(0, timesteps)), desc='Sampling t', total=timesteps) if verbose else reversed(
+            range(0, timesteps))
+
+        if mask is not None:
+            assert x0 is not None
+            assert x0.shape[2:3] == mask.shape[2:3]  # spatial size has to match
+
+        for i in iterator:
+            ts = torch.full((b,), i, device=device, dtype=torch.long)
+            if self.shorten_cond_schedule:
+                assert self.model.conditioning_key != 'hybrid'
+                tc = self.cond_ids[ts].to(cond.device)
+                cond = self.q_sample(x_start=cond, t=tc, noise=torch.randn_like(cond))
+
+            img = self.p_sample(img, cond, ts,
+                                clip_denoised=self.clip_denoised,
+                                quantize_denoised=quantize_denoised)
+            if mask is not None:
+                img_orig = self.q_sample(x0, ts)
+                img = img_orig * mask + (1. - mask) * img
+
+            if i % log_every_t == 0 or i == timesteps - 1:
+                intermediates.append(img)
+            if callback: callback(i)
+            if img_callback: img_callback(img, i)
+
+        if return_intermediates:
+            return img, intermediates
+        return img
+
+    @torch.no_grad()
+    def sample(self, cond, batch_size=16, return_intermediates=False, x_T=None,
+               verbose=True, timesteps=None, quantize_denoised=False,
+               mask=None, x0=None, shape=None,**kwargs):
+        if shape is None:
+            shape = (batch_size, self.channels, self.image_size, self.image_size)
+        if cond is not None:
+            if isinstance(cond, dict):
+                cond = {key: cond[key][:batch_size] if not isinstance(cond[key], list) else
+                list(map(lambda x: x[:batch_size], cond[key])) for key in cond}
+            else:
+                cond = [c[:batch_size] for c in cond] if isinstance(cond, list) else cond[:batch_size]
+        return self.p_sample_loop(cond,
+                                  shape,
+                                  return_intermediates=return_intermediates, x_T=x_T,
+                                  verbose=verbose, timesteps=timesteps, quantize_denoised=quantize_denoised,
+                                  mask=mask, x0=x0)
+
+    @torch.no_grad()
+    def sample_log(self,cond,batch_size,ddim, ddim_steps,**kwargs):
+
+        if ddim:
+            ddim_sampler = DDIMSampler(self)
+            shape = (self.channels, self.image_size, self.image_size)
+            samples, intermediates =ddim_sampler.sample(ddim_steps,batch_size,
+                                                        shape,cond,verbose=False,**kwargs)
+
+        else:
+            samples, intermediates = self.sample(cond=cond, batch_size=batch_size,
+                                                 return_intermediates=True,**kwargs)
+
+        return samples, intermediates
+
+
+    @torch.no_grad()
+    def log_images(self, batch, N=4, n_row=4, sample=True, ddim_steps=200, ddim_eta=1., return_keys=None,
+                   quantize_denoised=True, inpaint=False, plot_denoise_rows=False, plot_progressive_rows=False,
+                   plot_diffusion_rows=False, **kwargs):
+
+        use_ddim = False
+
+        log = dict()
+        z, c, x, xrec, xc = self.get_input(batch, self.first_stage_key,
+                                           return_first_stage_outputs=True,
+                                           force_c_encode=True,
+                                           return_original_cond=True,
+                                           bs=N, uncond=0)
+        N = min(x.shape[0], N)
+        n_row = min(x.shape[0], n_row)
+        log["inputs"] = x
+        log["reals"] = xc["c_concat"]
+        log["reconstruction"] = xrec
+        if self.model.conditioning_key is not None:
+            if hasattr(self.cond_stage_model, "decode"):
+                xc = self.cond_stage_model.decode(c)
+                log["conditioning"] = xc
+            elif self.cond_stage_key in ["caption"]:
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["caption"])
+                log["conditioning"] = xc
+            elif self.cond_stage_key == 'class_label':
+                xc = log_txt_as_img((x.shape[2], x.shape[3]), batch["human_label"])
+                log['conditioning'] = xc
+            elif isimage(xc):
+                log["conditioning"] = xc
+            if ismap(xc):
+                log["original_conditioning"] = self.to_rgb(xc)
+
+        if plot_diffusion_rows:
+            # get diffusion row
+            diffusion_row = list()
+            z_start = z[:n_row]
+            for t in range(self.num_timesteps):
+                if t % self.log_every_t == 0 or t == self.num_timesteps - 1:
+                    t = repeat(torch.tensor([t]), '1 -> b', b=n_row)
+                    t = t.to(self.device).long()
+                    noise = torch.randn_like(z_start)
+                    z_noisy = self.q_sample(x_start=z_start, t=t, noise=noise)
+                    diffusion_row.append(self.decode_first_stage(z_noisy))
+
+            diffusion_row = torch.stack(diffusion_row)  # n_log_step, n_row, C, H, W
+            diffusion_grid = rearrange(diffusion_row, 'n b c h w -> b n c h w')
+            diffusion_grid = rearrange(diffusion_grid, 'b n c h w -> (b n) c h w')
+            diffusion_grid = make_grid(diffusion_grid, nrow=diffusion_row.shape[0])
+            log["diffusion_row"] = diffusion_grid
+
+        if sample:
+            # get denoise row
+            with self.ema_scope("Plotting"):
+                samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                         ddim_steps=ddim_steps,eta=ddim_eta)
+                # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True)
+            x_samples = self.decode_first_stage(samples)
+            log["samples"] = x_samples
+            if plot_denoise_rows:
+                denoise_grid = self._get_denoise_row_from_list(z_denoise_row)
+                log["denoise_row"] = denoise_grid
+
+            if quantize_denoised and not isinstance(self.first_stage_model, AutoencoderKL) and not isinstance(
+                    self.first_stage_model, IdentityFirstStage):
+                # also display when quantizing x0 while sampling
+                with self.ema_scope("Plotting Quantized Denoised"):
+                    samples, z_denoise_row = self.sample_log(cond=c,batch_size=N,ddim=use_ddim,
+                                                             ddim_steps=ddim_steps,eta=ddim_eta,
+                                                             quantize_denoised=True)
+                    # samples, z_denoise_row = self.sample(cond=c, batch_size=N, return_intermediates=True,
+                    #                                      quantize_denoised=True)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_x0_quantized"] = x_samples
+
+            if inpaint:
+                # make a simple center square
+                b, h, w = z.shape[0], z.shape[2], z.shape[3]
+                mask = torch.ones(N, h, w).to(self.device)
+                # zeros will be filled in
+                mask[:, h // 4:3 * h // 4, w // 4:3 * w // 4] = 0.
+                mask = mask[:, None, ...]
+                with self.ema_scope("Plotting Inpaint"):
+
+                    samples, _ = self.sample_log(cond=c,batch_size=N,ddim=use_ddim, eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_inpainting"] = x_samples
+                log["mask"] = mask
+
+                # outpaint
+                with self.ema_scope("Plotting Outpaint"):
+                    samples, _ = self.sample_log(cond=c, batch_size=N, ddim=use_ddim,eta=ddim_eta,
+                                                ddim_steps=ddim_steps, x0=z[:N], mask=mask)
+                x_samples = self.decode_first_stage(samples.to(self.device))
+                log["samples_outpainting"] = x_samples
+
+        if plot_progressive_rows:
+            with self.ema_scope("Plotting Progressives"):
+                img, progressives = self.progressive_denoising(c,
+                                                               shape=(self.channels, self.image_size, self.image_size),
+                                                               batch_size=N)
+            prog_row = self._get_denoise_row_from_list(progressives, desc="Progressive Generation")
+            log["progressive_row"] = prog_row
+
+        if return_keys:
+            if np.intersect1d(list(log.keys()), return_keys).shape[0] == 0:
+                return log
+            else:
+                return {key: log[key] for key in return_keys}
+        return log
+
+    def configure_optimizers(self):
+        lr = self.learning_rate
+        params = list(self.model.parameters())
+        if self.cond_stage_trainable:
+            print(f"{self.__class__.__name__}: Also optimizing conditioner params!")
+            params = params + list(self.cond_stage_model.parameters())
+        if self.learn_logvar:
+            print('Diffusion model optimizing logvar')
+            params.append(self.logvar)
+        opt = torch.optim.AdamW(params, lr=lr)
+        if self.use_scheduler:
+            assert 'target' in self.scheduler_config
+            scheduler = instantiate_from_config(self.scheduler_config)
+
+            print("Setting up LambdaLR scheduler...")
+            scheduler = [
+                {
+                    'scheduler': LambdaLR(opt, lr_lambda=scheduler.schedule),
+                    'interval': 'step',
+                    'frequency': 1
+                }]
+            return [opt], scheduler
+        return opt
+
+    @torch.no_grad()
+    def to_rgb(self, x):
+        x = x.float()
+        if not hasattr(self, "colorize"):
+            self.colorize = torch.randn(3, x.shape[1], 1, 1).to(x)
+        x = nn.functional.conv2d(x, weight=self.colorize)
+        x = 2. * (x - x.min()) / (x.max() - x.min()) - 1.
+        return x
+
+
+class DiffusionWrapper(pl.LightningModule):
+    def __init__(self, diff_model_config, conditioning_key):
+        super().__init__()
+        self.diffusion_model = instantiate_from_config(diff_model_config)
+        self.conditioning_key = conditioning_key
+        assert self.conditioning_key in [None, 'concat', 'crossattn', 'hybrid', 'adm']
+
+    def forward(self, x, t, c_concat: list = None, c_crossattn: list = None):
+        if self.conditioning_key is None:
+            out = self.diffusion_model(x, t)
+        elif self.conditioning_key == 'concat':
+            xc = torch.cat([x] + c_concat, dim=1)
+            out = self.diffusion_model(xc, t)
+        elif self.conditioning_key == 'crossattn':
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(x, t, context=cc)
+        elif self.conditioning_key == 'hybrid':
+            xc = torch.cat([x] + c_concat, dim=1)
+            cc = torch.cat(c_crossattn, 1)
+            out = self.diffusion_model(xc, t, context=cc)
+        elif self.conditioning_key == 'adm':
+            cc = c_crossattn[0]
+            out = self.diffusion_model(x, t, y=cc)
+        else:
+            raise NotImplementedError()
+
+        return out
+
+
+class Layout2ImgDiffusion(LatentDiffusion):
+    # TODO: move all layout-specific hacks to this class
+    def __init__(self, cond_stage_key, *args, **kwargs):
+        assert cond_stage_key == 'coordinates_bbox', 'Layout2ImgDiffusion only for cond_stage_key="coordinates_bbox"'
+        super().__init__(cond_stage_key=cond_stage_key, *args, **kwargs)
+
+    def log_images(self, batch, N=8, *args, **kwargs):
+        logs = super().log_images(batch=batch, N=N, *args, **kwargs)
+
+        key = 'train' if self.training else 'validation'
+        dset = self.trainer.datamodule.datasets[key]
+        mapper = dset.conditional_builders[self.cond_stage_key]
+
+        bbox_imgs = []
+        map_fn = lambda catno: dset.get_textual_label(dset.get_category_id(catno))
+        for tknzd_bbox in batch[self.cond_stage_key][:N]:
+            bboximg = mapper.plot(tknzd_bbox.detach().cpu(), map_fn, (256, 256))
+            bbox_imgs.append(bboximg)
+
+        cond_img = torch.stack(bbox_imgs, dim=0)
+        logs['bbox_image'] = cond_img
+        return logs

stable_diffusion/ldm/models/diffusion/dpm_solver/__init__.py

@@ -0,0 +1 @@
+from .sampler import DPMSolverSampler

stable_diffusion/ldm/models/diffusion/dpm_solver/dpm_solver.py

@@ -0,0 +1,1184 @@
+import torch
+import torch.nn.functional as F
+import math
+
+
+class NoiseScheduleVP:
+    def __init__(
+            self,
+            schedule='discrete',
+            betas=None,
+            alphas_cumprod=None,
+            continuous_beta_0=0.1,
+            continuous_beta_1=20.,
+        ):
+        """Create a wrapper class for the forward SDE (VP type).
+
+        ***
+        Update: We support discrete-time diffusion models by implementing a picewise linear interpolation for log_alpha_t.
+                We recommend to use schedule='discrete' for the discrete-time diffusion models, especially for high-resolution images.
+        ***
+
+        The forward SDE ensures that the condition distribution q_{t|0}(x_t | x_0) = N ( alpha_t * x_0, sigma_t^2 * I ).
+        We further define lambda_t = log(alpha_t) - log(sigma_t), which is the half-logSNR (described in the DPM-Solver paper).
+        Therefore, we implement the functions for computing alpha_t, sigma_t and lambda_t. For t in [0, T], we have:
+
+            log_alpha_t = self.marginal_log_mean_coeff(t)
+            sigma_t = self.marginal_std(t)
+            lambda_t = self.marginal_lambda(t)
+
+        Moreover, as lambda(t) is an invertible function, we also support its inverse function:
+
+            t = self.inverse_lambda(lambda_t)
+
+        ===============================================================
+
+        We support both discrete-time DPMs (trained on n = 0, 1, ..., N-1) and continuous-time DPMs (trained on t in [t_0, T]).
+
+        1. For discrete-time DPMs:
+
+            For discrete-time DPMs trained on n = 0, 1, ..., N-1, we convert the discrete steps to continuous time steps by:
+                t_i = (i + 1) / N
+            e.g. for N = 1000, we have t_0 = 1e-3 and T = t_{N-1} = 1.
+            We solve the corresponding diffusion ODE from time T = 1 to time t_0 = 1e-3.
+
+            Args:
+                betas: A `torch.Tensor`. The beta array for the discrete-time DPM. (See the original DDPM paper for details)
+                alphas_cumprod: A `torch.Tensor`. The cumprod alphas for the discrete-time DPM. (See the original DDPM paper for details)
+
+            Note that we always have alphas_cumprod = cumprod(betas). Therefore, we only need to set one of `betas` and `alphas_cumprod`.
+
+            **Important**:  Please pay special attention for the args for `alphas_cumprod`:
+                The `alphas_cumprod` is the \hat{alpha_n} arrays in the notations of DDPM. Specifically, DDPMs assume that
+                    q_{t_n | 0}(x_{t_n} | x_0) = N ( \sqrt{\hat{alpha_n}} * x_0, (1 - \hat{alpha_n}) * I ).
+                Therefore, the notation \hat{alpha_n} is different from the notation alpha_t in DPM-Solver. In fact, we have
+                    alpha_{t_n} = \sqrt{\hat{alpha_n}},
+                and
+                    log(alpha_{t_n}) = 0.5 * log(\hat{alpha_n}).
+
+
+        2. For continuous-time DPMs:
+
+            We support two types of VPSDEs: linear (DDPM) and cosine (improved-DDPM). The hyperparameters for the noise
+            schedule are the default settings in DDPM and improved-DDPM:
+
+            Args:
+                beta_min: A `float` number. The smallest beta for the linear schedule.
+                beta_max: A `float` number. The largest beta for the linear schedule.
+                cosine_s: A `float` number. The hyperparameter in the cosine schedule.
+                cosine_beta_max: A `float` number. The hyperparameter in the cosine schedule.
+                T: A `float` number. The ending time of the forward process.
+
+        ===============================================================
+
+        Args:
+            schedule: A `str`. The noise schedule of the forward SDE. 'discrete' for discrete-time DPMs,
+                    'linear' or 'cosine' for continuous-time DPMs.
+        Returns:
+            A wrapper object of the forward SDE (VP type).
+        
+        ===============================================================
+
+        Example:
+
+        # For discrete-time DPMs, given betas (the beta array for n = 0, 1, ..., N - 1):
+        >>> ns = NoiseScheduleVP('discrete', betas=betas)
+
+        # For discrete-time DPMs, given alphas_cumprod (the \hat{alpha_n} array for n = 0, 1, ..., N - 1):
+        >>> ns = NoiseScheduleVP('discrete', alphas_cumprod=alphas_cumprod)
+
+        # For continuous-time DPMs (VPSDE), linear schedule:
+        >>> ns = NoiseScheduleVP('linear', continuous_beta_0=0.1, continuous_beta_1=20.)
+
+        """
+
+        if schedule not in ['discrete', 'linear', 'cosine']:
+            raise ValueError("Unsupported noise schedule {}. The schedule needs to be 'discrete' or 'linear' or 'cosine'".format(schedule))
+
+        self.schedule = schedule
+        if schedule == 'discrete':
+            if betas is not None:
+                log_alphas = 0.5 * torch.log(1 - betas).cumsum(dim=0)
+            else:
+                assert alphas_cumprod is not None
+                log_alphas = 0.5 * torch.log(alphas_cumprod)
+            self.total_N = len(log_alphas)
+            self.T = 1.
+            self.t_array = torch.linspace(0., 1., self.total_N + 1)[1:].reshape((1, -1))
+            self.log_alpha_array = log_alphas.reshape((1, -1,))
+        else:
+            self.total_N = 1000
+            self.beta_0 = continuous_beta_0
+            self.beta_1 = continuous_beta_1
+            self.cosine_s = 0.008
+            self.cosine_beta_max = 999.
+            self.cosine_t_max = math.atan(self.cosine_beta_max * (1. + self.cosine_s) / math.pi) * 2. * (1. + self.cosine_s) / math.pi - self.cosine_s
+            self.cosine_log_alpha_0 = math.log(math.cos(self.cosine_s / (1. + self.cosine_s) * math.pi / 2.))
+            self.schedule = schedule
+            if schedule == 'cosine':
+                # For the cosine schedule, T = 1 will have numerical issues. So we manually set the ending time T.
+                # Note that T = 0.9946 may be not the optimal setting. However, we find it works well.
+                self.T = 0.9946
+            else:
+                self.T = 1.
+
+    def marginal_log_mean_coeff(self, t):
+        """
+        Compute log(alpha_t) of a given continuous-time label t in [0, T].
+        """
+        if self.schedule == 'discrete':
+            return interpolate_fn(t.reshape((-1, 1)), self.t_array.to(t.device), self.log_alpha_array.to(t.device)).reshape((-1))
+        elif self.schedule == 'linear':
+            return -0.25 * t ** 2 * (self.beta_1 - self.beta_0) - 0.5 * t * self.beta_0
+        elif self.schedule == 'cosine':
+            log_alpha_fn = lambda s: torch.log(torch.cos((s + self.cosine_s) / (1. + self.cosine_s) * math.pi / 2.))
+            log_alpha_t =  log_alpha_fn(t) - self.cosine_log_alpha_0
+            return log_alpha_t
+
+    def marginal_alpha(self, t):
+        """
+        Compute alpha_t of a given continuous-time label t in [0, T].
+        """
+        return torch.exp(self.marginal_log_mean_coeff(t))
+
+    def marginal_std(self, t):
+        """
+        Compute sigma_t of a given continuous-time label t in [0, T].
+        """
+        return torch.sqrt(1. - torch.exp(2. * self.marginal_log_mean_coeff(t)))
+
+    def marginal_lambda(self, t):
+        """
+        Compute lambda_t = log(alpha_t) - log(sigma_t) of a given continuous-time label t in [0, T].
+        """
+        log_mean_coeff = self.marginal_log_mean_coeff(t)
+        log_std = 0.5 * torch.log(1. - torch.exp(2. * log_mean_coeff))
+        return log_mean_coeff - log_std
+
+    def inverse_lambda(self, lamb):
+        """
+        Compute the continuous-time label t in [0, T] of a given half-logSNR lambda_t.
+        """
+        if self.schedule == 'linear':
+            tmp = 2. * (self.beta_1 - self.beta_0) * torch.logaddexp(-2. * lamb, torch.zeros((1,)).to(lamb))
+            Delta = self.beta_0**2 + tmp
+            return tmp / (torch.sqrt(Delta) + self.beta_0) / (self.beta_1 - self.beta_0)
+        elif self.schedule == 'discrete':
+            log_alpha = -0.5 * torch.logaddexp(torch.zeros((1,)).to(lamb.device), -2. * lamb)
+            t = interpolate_fn(log_alpha.reshape((-1, 1)), torch.flip(self.log_alpha_array.to(lamb.device), [1]), torch.flip(self.t_array.to(lamb.device), [1]))
+            return t.reshape((-1,))
+        else:
+            log_alpha = -0.5 * torch.logaddexp(-2. * lamb, torch.zeros((1,)).to(lamb))
+            t_fn = lambda log_alpha_t: torch.arccos(torch.exp(log_alpha_t + self.cosine_log_alpha_0)) * 2. * (1. + self.cosine_s) / math.pi - self.cosine_s
+            t = t_fn(log_alpha)
+            return t
+
+
+def model_wrapper(
+    model,
+    noise_schedule,
+    model_type="noise",
+    model_kwargs={},
+    guidance_type="uncond",
+    condition=None,
+    unconditional_condition=None,
+    guidance_scale=1.,
+    classifier_fn=None,
+    classifier_kwargs={},
+):
+    """Create a wrapper function for the noise prediction model.
+
+    DPM-Solver needs to solve the continuous-time diffusion ODEs. For DPMs trained on discrete-time labels, we need to
+    firstly wrap the model function to a noise prediction model that accepts the continuous time as the input.
+
+    We support four types of the diffusion model by setting `model_type`:
+
+        1. "noise": noise prediction model. (Trained by predicting noise).
+
+        2. "x_start": data prediction model. (Trained by predicting the data x_0 at time 0).
+
+        3. "v": velocity prediction model. (Trained by predicting the velocity).
+            The "v" prediction is derivation detailed in Appendix D of [1], and is used in Imagen-Video [2].
+
+            [1] Salimans, Tim, and Jonathan Ho. "Progressive distillation for fast sampling of diffusion models."
+                arXiv preprint arXiv:2202.00512 (2022).
+            [2] Ho, Jonathan, et al. "Imagen Video: High Definition Video Generation with Diffusion Models."
+                arXiv preprint arXiv:2210.02303 (2022).
+    
+        4. "score": marginal score function. (Trained by denoising score matching).
+            Note that the score function and the noise prediction model follows a simple relationship:
+            ```
+                noise(x_t, t) = -sigma_t * score(x_t, t)
+            ```
+
+    We support three types of guided sampling by DPMs by setting `guidance_type`:
+        1. "uncond": unconditional sampling by DPMs.
+            The input `model` has the following format:
+            ``
+                model(x, t_input, **model_kwargs) -> noise | x_start | v | score
+            ``
+
+        2. "classifier": classifier guidance sampling [3] by DPMs and another classifier.
+            The input `model` has the following format:
+            ``
+                model(x, t_input, **model_kwargs) -> noise | x_start | v | score
+            `` 
+
+            The input `classifier_fn` has the following format:
+            ``
+                classifier_fn(x, t_input, cond, **classifier_kwargs) -> logits(x, t_input, cond)
+            ``
+
+            [3] P. Dhariwal and A. Q. Nichol, "Diffusion models beat GANs on image synthesis,"
+                in Advances in Neural Information Processing Systems, vol. 34, 2021, pp. 8780-8794.
+
+        3. "classifier-free": classifier-free guidance sampling by conditional DPMs.
+            The input `model` has the following format:
+            ``
+                model(x, t_input, cond, **model_kwargs) -> noise | x_start | v | score
+            `` 
+            And if cond == `unconditional_condition`, the model output is the unconditional DPM output.
+
+            [4] Ho, Jonathan, and Tim Salimans. "Classifier-free diffusion guidance."
+                arXiv preprint arXiv:2207.12598 (2022).
+        
+
+    The `t_input` is the time label of the model, which may be discrete-time labels (i.e. 0 to 999)
+    or continuous-time labels (i.e. epsilon to T).
+
+    We wrap the model function to accept only `x` and `t_continuous` as inputs, and outputs the predicted noise:
+    ``
+        def model_fn(x, t_continuous) -> noise:
+            t_input = get_model_input_time(t_continuous)
+            return noise_pred(model, x, t_input, **model_kwargs)         
+    ``
+    where `t_continuous` is the continuous time labels (i.e. epsilon to T). And we use `model_fn` for DPM-Solver.
+
+    ===============================================================
+
+    Args:
+        model: A diffusion model with the corresponding format described above.
+        noise_schedule: A noise schedule object, such as NoiseScheduleVP.
+        model_type: A `str`. The parameterization type of the diffusion model.
+                    "noise" or "x_start" or "v" or "score".
+        model_kwargs: A `dict`. A dict for the other inputs of the model function.
+        guidance_type: A `str`. The type of the guidance for sampling.
+                    "uncond" or "classifier" or "classifier-free".
+        condition: A pytorch tensor. The condition for the guided sampling.
+                    Only used for "classifier" or "classifier-free" guidance type.
+        unconditional_condition: A pytorch tensor. The condition for the unconditional sampling.
+                    Only used for "classifier-free" guidance type.
+        guidance_scale: A `float`. The scale for the guided sampling.
+        classifier_fn: A classifier function. Only used for the classifier guidance.
+        classifier_kwargs: A `dict`. A dict for the other inputs of the classifier function.
+    Returns:
+        A noise prediction model that accepts the noised data and the continuous time as the inputs.
+    """
+
+    def get_model_input_time(t_continuous):
+        """
+        Convert the continuous-time `t_continuous` (in [epsilon, T]) to the model input time.
+        For discrete-time DPMs, we convert `t_continuous` in [1 / N, 1] to `t_input` in [0, 1000 * (N - 1) / N].
+        For continuous-time DPMs, we just use `t_continuous`.
+        """
+        if noise_schedule.schedule == 'discrete':
+            return (t_continuous - 1. / noise_schedule.total_N) * 1000.
+        else:
+            return t_continuous
+
+    def noise_pred_fn(x, t_continuous, cond=None):
+        if t_continuous.reshape((-1,)).shape[0] == 1:
+            t_continuous = t_continuous.expand((x.shape[0]))
+        t_input = get_model_input_time(t_continuous)
+        if cond is None:
+            output = model(x, t_input, **model_kwargs)
+        else:
+            output = model(x, t_input, cond, **model_kwargs)
+        if model_type == "noise":
+            return output
+        elif model_type == "x_start":
+            alpha_t, sigma_t = noise_schedule.marginal_alpha(t_continuous), noise_schedule.marginal_std(t_continuous)
+            dims = x.dim()
+            return (x - expand_dims(alpha_t, dims) * output) / expand_dims(sigma_t, dims)
+        elif model_type == "v":
+            alpha_t, sigma_t = noise_schedule.marginal_alpha(t_continuous), noise_schedule.marginal_std(t_continuous)
+            dims = x.dim()
+            return expand_dims(alpha_t, dims) * output + expand_dims(sigma_t, dims) * x
+        elif model_type == "score":
+            sigma_t = noise_schedule.marginal_std(t_continuous)
+            dims = x.dim()
+            return -expand_dims(sigma_t, dims) * output
+
+    def cond_grad_fn(x, t_input):
+        """
+        Compute the gradient of the classifier, i.e. nabla_{x} log p_t(cond | x_t).
+        """
+        with torch.enable_grad():
+            x_in = x.detach().requires_grad_(True)
+            log_prob = classifier_fn(x_in, t_input, condition, **classifier_kwargs)
+            return torch.autograd.grad(log_prob.sum(), x_in)[0]
+
+    def model_fn(x, t_continuous):
+        """
+        The noise predicition model function that is used for DPM-Solver.
+        """
+        if t_continuous.reshape((-1,)).shape[0] == 1:
+            t_continuous = t_continuous.expand((x.shape[0]))
+        if guidance_type == "uncond":
+            return noise_pred_fn(x, t_continuous)
+        elif guidance_type == "classifier":
+            assert classifier_fn is not None
+            t_input = get_model_input_time(t_continuous)
+            cond_grad = cond_grad_fn(x, t_input)
+            sigma_t = noise_schedule.marginal_std(t_continuous)
+            noise = noise_pred_fn(x, t_continuous)
+            return noise - guidance_scale * expand_dims(sigma_t, dims=cond_grad.dim()) * cond_grad
+        elif guidance_type == "classifier-free":
+            if guidance_scale == 1. or unconditional_condition is None:
+                return noise_pred_fn(x, t_continuous, cond=condition)
+            else:
+                x_in = torch.cat([x] * 2)
+                t_in = torch.cat([t_continuous] * 2)
+                c_in = torch.cat([unconditional_condition, condition])
+                noise_uncond, noise = noise_pred_fn(x_in, t_in, cond=c_in).chunk(2)
+                return noise_uncond + guidance_scale * (noise - noise_uncond)
+
+    assert model_type in ["noise", "x_start", "v"]
+    assert guidance_type in ["uncond", "classifier", "classifier-free"]
+    return model_fn
+
+
+class DPM_Solver:
+    def __init__(self, model_fn, noise_schedule, predict_x0=False, thresholding=False, max_val=1.):
+        """Construct a DPM-Solver. 
+
+        We support both the noise prediction model ("predicting epsilon") and the data prediction model ("predicting x0").
+        If `predict_x0` is False, we use the solver for the noise prediction model (DPM-Solver).
+        If `predict_x0` is True, we use the solver for the data prediction model (DPM-Solver++).
+            In such case, we further support the "dynamic thresholding" in [1] when `thresholding` is True.
+            The "dynamic thresholding" can greatly improve the sample quality for pixel-space DPMs with large guidance scales.
+
+        Args:
+            model_fn: A noise prediction model function which accepts the continuous-time input (t in [epsilon, T]):
+                ``
+                def model_fn(x, t_continuous):
+                    return noise
+                ``
+            noise_schedule: A noise schedule object, such as NoiseScheduleVP.
+            predict_x0: A `bool`. If true, use the data prediction model; else, use the noise prediction model.
+            thresholding: A `bool`. Valid when `predict_x0` is True. Whether to use the "dynamic thresholding" in [1].
+            max_val: A `float`. Valid when both `predict_x0` and `thresholding` are True. The max value for thresholding.
+        
+        [1] Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily Denton, Seyed Kamyar Seyed Ghasemipour, Burcu Karagol Ayan, S Sara Mahdavi, Rapha Gontijo Lopes, et al. Photorealistic text-to-image diffusion models with deep language understanding. arXiv preprint arXiv:2205.11487, 2022b.
+        """
+        self.model = model_fn
+        self.noise_schedule = noise_schedule
+        self.predict_x0 = predict_x0
+        self.thresholding = thresholding
+        self.max_val = max_val
+
+    def noise_prediction_fn(self, x, t):
+        """
+        Return the noise prediction model.
+        """
+        return self.model(x, t)
+
+    def data_prediction_fn(self, x, t):
+        """
+        Return the data prediction model (with thresholding).
+        """
+        noise = self.noise_prediction_fn(x, t)
+        dims = x.dim()
+        alpha_t, sigma_t = self.noise_schedule.marginal_alpha(t), self.noise_schedule.marginal_std(t)
+        x0 = (x - expand_dims(sigma_t, dims) * noise) / expand_dims(alpha_t, dims)
+        if self.thresholding:
+            p = 0.995   # A hyperparameter in the paper of "Imagen" [1].
+            s = torch.quantile(torch.abs(x0).reshape((x0.shape[0], -1)), p, dim=1)
+            s = expand_dims(torch.maximum(s, self.max_val * torch.ones_like(s).to(s.device)), dims)
+            x0 = torch.clamp(x0, -s, s) / s
+        return x0
+
+    def model_fn(self, x, t):
+        """
+        Convert the model to the noise prediction model or the data prediction model. 
+        """
+        if self.predict_x0:
+            return self.data_prediction_fn(x, t)
+        else:
+            return self.noise_prediction_fn(x, t)
+
+    def get_time_steps(self, skip_type, t_T, t_0, N, device):
+        """Compute the intermediate time steps for sampling.
+
+        Args:
+            skip_type: A `str`. The type for the spacing of the time steps. We support three types:
+                - 'logSNR': uniform logSNR for the time steps.
+                - 'time_uniform': uniform time for the time steps. (**Recommended for high-resolutional data**.)
+                - 'time_quadratic': quadratic time for the time steps. (Used in DDIM for low-resolutional data.)
+            t_T: A `float`. The starting time of the sampling (default is T).
+            t_0: A `float`. The ending time of the sampling (default is epsilon).
+            N: A `int`. The total number of the spacing of the time steps.
+            device: A torch device.
+        Returns:
+            A pytorch tensor of the time steps, with the shape (N + 1,).
+        """
+        if skip_type == 'logSNR':
+            lambda_T = self.noise_schedule.marginal_lambda(torch.tensor(t_T).to(device))
+            lambda_0 = self.noise_schedule.marginal_lambda(torch.tensor(t_0).to(device))
+            logSNR_steps = torch.linspace(lambda_T.cpu().item(), lambda_0.cpu().item(), N + 1).to(device)
+            return self.noise_schedule.inverse_lambda(logSNR_steps)
+        elif skip_type == 'time_uniform':
+            return torch.linspace(t_T, t_0, N + 1).to(device)
+        elif skip_type == 'time_quadratic':
+            t_order = 2
+            t = torch.linspace(t_T**(1. / t_order), t_0**(1. / t_order), N + 1).pow(t_order).to(device)
+            return t
+        else:
+            raise ValueError("Unsupported skip_type {}, need to be 'logSNR' or 'time_uniform' or 'time_quadratic'".format(skip_type))
+
+    def get_orders_and_timesteps_for_singlestep_solver(self, steps, order, skip_type, t_T, t_0, device):
+        """
+        Get the order of each step for sampling by the singlestep DPM-Solver.
+
+        We combine both DPM-Solver-1,2,3 to use all the function evaluations, which is named as "DPM-Solver-fast".
+        Given a fixed number of function evaluations by `steps`, the sampling procedure by DPM-Solver-fast is:
+            - If order == 1:
+                We take `steps` of DPM-Solver-1 (i.e. DDIM).
+            - If order == 2:
+                - Denote K = (steps // 2). We take K or (K + 1) intermediate time steps for sampling.
+                - If steps % 2 == 0, we use K steps of DPM-Solver-2.
+                - If steps % 2 == 1, we use K steps of DPM-Solver-2 and 1 step of DPM-Solver-1.
+            - If order == 3:
+                - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling.
+                - If steps % 3 == 0, we use (K - 2) steps of DPM-Solver-3, and 1 step of DPM-Solver-2 and 1 step of DPM-Solver-1.
+                - If steps % 3 == 1, we use (K - 1) steps of DPM-Solver-3 and 1 step of DPM-Solver-1.
+                - If steps % 3 == 2, we use (K - 1) steps of DPM-Solver-3 and 1 step of DPM-Solver-2.
+
+        ============================================
+        Args:
+            order: A `int`. The max order for the solver (2 or 3).
+            steps: A `int`. The total number of function evaluations (NFE).
+            skip_type: A `str`. The type for the spacing of the time steps. We support three types:
+                - 'logSNR': uniform logSNR for the time steps.
+                - 'time_uniform': uniform time for the time steps. (**Recommended for high-resolutional data**.)
+                - 'time_quadratic': quadratic time for the time steps. (Used in DDIM for low-resolutional data.)
+            t_T: A `float`. The starting time of the sampling (default is T).
+            t_0: A `float`. The ending time of the sampling (default is epsilon).
+            device: A torch device.
+        Returns:
+            orders: A list of the solver order of each step.
+        """
+        if order == 3:
+            K = steps // 3 + 1
+            if steps % 3 == 0:
+                orders = [3,] * (K - 2) + [2, 1]
+            elif steps % 3 == 1:
+                orders = [3,] * (K - 1) + [1]
+            else:
+                orders = [3,] * (K - 1) + [2]
+        elif order == 2:
+            if steps % 2 == 0:
+                K = steps // 2
+                orders = [2,] * K
+            else:
+                K = steps // 2 + 1
+                orders = [2,] * (K - 1) + [1]
+        elif order == 1:
+            K = 1
+            orders = [1,] * steps
+        else:
+            raise ValueError("'order' must be '1' or '2' or '3'.")
+        if skip_type == 'logSNR':
+            # To reproduce the results in DPM-Solver paper
+            timesteps_outer = self.get_time_steps(skip_type, t_T, t_0, K, device)
+        else:
+            timesteps_outer = self.get_time_steps(skip_type, t_T, t_0, steps, device)[torch.cumsum(torch.tensor([0,] + orders)).to(device)]
+        return timesteps_outer, orders
+
+    def denoise_to_zero_fn(self, x, s):
+        """
+        Denoise at the final step, which is equivalent to solve the ODE from lambda_s to infty by first-order discretization. 
+        """
+        return self.data_prediction_fn(x, s)
+
+    def dpm_solver_first_update(self, x, s, t, model_s=None, return_intermediate=False):
+        """
+        DPM-Solver-1 (equivalent to DDIM) from time `s` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            model_s: A pytorch tensor. The model function evaluated at time `s`.
+                If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it.
+            return_intermediate: A `bool`. If true, also return the model value at time `s`.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        ns = self.noise_schedule
+        dims = x.dim()
+        lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t)
+        h = lambda_t - lambda_s
+        log_alpha_s, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(t)
+        sigma_s, sigma_t = ns.marginal_std(s), ns.marginal_std(t)
+        alpha_t = torch.exp(log_alpha_t)
+
+        if self.predict_x0:
+            phi_1 = torch.expm1(-h)
+            if model_s is None:
+                model_s = self.model_fn(x, s)
+            x_t = (
+                expand_dims(sigma_t / sigma_s, dims) * x
+                - expand_dims(alpha_t * phi_1, dims) * model_s
+            )
+            if return_intermediate:
+                return x_t, {'model_s': model_s}
+            else:
+                return x_t
+        else:
+            phi_1 = torch.expm1(h)
+            if model_s is None:
+                model_s = self.model_fn(x, s)
+            x_t = (
+                expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+                - expand_dims(sigma_t * phi_1, dims) * model_s
+            )
+            if return_intermediate:
+                return x_t, {'model_s': model_s}
+            else:
+                return x_t
+
+    def singlestep_dpm_solver_second_update(self, x, s, t, r1=0.5, model_s=None, return_intermediate=False, solver_type='dpm_solver'):
+        """
+        Singlestep solver DPM-Solver-2 from time `s` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            r1: A `float`. The hyperparameter of the second-order solver.
+            model_s: A pytorch tensor. The model function evaluated at time `s`.
+                If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it.
+            return_intermediate: A `bool`. If true, also return the model value at time `s` and `s1` (the intermediate time).
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        if solver_type not in ['dpm_solver', 'taylor']:
+            raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type))
+        if r1 is None:
+            r1 = 0.5
+        ns = self.noise_schedule
+        dims = x.dim()
+        lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t)
+        h = lambda_t - lambda_s
+        lambda_s1 = lambda_s + r1 * h
+        s1 = ns.inverse_lambda(lambda_s1)
+        log_alpha_s, log_alpha_s1, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(s1), ns.marginal_log_mean_coeff(t)
+        sigma_s, sigma_s1, sigma_t = ns.marginal_std(s), ns.marginal_std(s1), ns.marginal_std(t)
+        alpha_s1, alpha_t = torch.exp(log_alpha_s1), torch.exp(log_alpha_t)
+
+        if self.predict_x0:
+            phi_11 = torch.expm1(-r1 * h)
+            phi_1 = torch.expm1(-h)
+
+            if model_s is None:
+                model_s = self.model_fn(x, s)
+            x_s1 = (
+                expand_dims(sigma_s1 / sigma_s, dims) * x
+                - expand_dims(alpha_s1 * phi_11, dims) * model_s
+            )
+            model_s1 = self.model_fn(x_s1, s1)
+            if solver_type == 'dpm_solver':
+                x_t = (
+                    expand_dims(sigma_t / sigma_s, dims) * x
+                    - expand_dims(alpha_t * phi_1, dims) * model_s
+                    - (0.5 / r1) * expand_dims(alpha_t * phi_1, dims) * (model_s1 - model_s)
+                )
+            elif solver_type == 'taylor':
+                x_t = (
+                    expand_dims(sigma_t / sigma_s, dims) * x
+                    - expand_dims(alpha_t * phi_1, dims) * model_s
+                    + (1. / r1) * expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * (model_s1 - model_s)
+                )
+        else:
+            phi_11 = torch.expm1(r1 * h)
+            phi_1 = torch.expm1(h)
+
+            if model_s is None:
+                model_s = self.model_fn(x, s)
+            x_s1 = (
+                expand_dims(torch.exp(log_alpha_s1 - log_alpha_s), dims) * x
+                - expand_dims(sigma_s1 * phi_11, dims) * model_s
+            )
+            model_s1 = self.model_fn(x_s1, s1)
+            if solver_type == 'dpm_solver':
+                x_t = (
+                    expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+                    - expand_dims(sigma_t * phi_1, dims) * model_s
+                    - (0.5 / r1) * expand_dims(sigma_t * phi_1, dims) * (model_s1 - model_s)
+                )
+            elif solver_type == 'taylor':
+                x_t = (
+                    expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+                    - expand_dims(sigma_t * phi_1, dims) * model_s
+                    - (1. / r1) * expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * (model_s1 - model_s)
+                )
+        if return_intermediate:
+            return x_t, {'model_s': model_s, 'model_s1': model_s1}
+        else:
+            return x_t
+
+    def singlestep_dpm_solver_third_update(self, x, s, t, r1=1./3., r2=2./3., model_s=None, model_s1=None, return_intermediate=False, solver_type='dpm_solver'):
+        """
+        Singlestep solver DPM-Solver-3 from time `s` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            r1: A `float`. The hyperparameter of the third-order solver.
+            r2: A `float`. The hyperparameter of the third-order solver.
+            model_s: A pytorch tensor. The model function evaluated at time `s`.
+                If `model_s` is None, we evaluate the model by `x` and `s`; otherwise we directly use it.
+            model_s1: A pytorch tensor. The model function evaluated at time `s1` (the intermediate time given by `r1`).
+                If `model_s1` is None, we evaluate the model at `s1`; otherwise we directly use it.
+            return_intermediate: A `bool`. If true, also return the model value at time `s`, `s1` and `s2` (the intermediate times).
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        if solver_type not in ['dpm_solver', 'taylor']:
+            raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type))
+        if r1 is None:
+            r1 = 1. / 3.
+        if r2 is None:
+            r2 = 2. / 3.
+        ns = self.noise_schedule
+        dims = x.dim()
+        lambda_s, lambda_t = ns.marginal_lambda(s), ns.marginal_lambda(t)
+        h = lambda_t - lambda_s
+        lambda_s1 = lambda_s + r1 * h
+        lambda_s2 = lambda_s + r2 * h
+        s1 = ns.inverse_lambda(lambda_s1)
+        s2 = ns.inverse_lambda(lambda_s2)
+        log_alpha_s, log_alpha_s1, log_alpha_s2, log_alpha_t = ns.marginal_log_mean_coeff(s), ns.marginal_log_mean_coeff(s1), ns.marginal_log_mean_coeff(s2), ns.marginal_log_mean_coeff(t)
+        sigma_s, sigma_s1, sigma_s2, sigma_t = ns.marginal_std(s), ns.marginal_std(s1), ns.marginal_std(s2), ns.marginal_std(t)
+        alpha_s1, alpha_s2, alpha_t = torch.exp(log_alpha_s1), torch.exp(log_alpha_s2), torch.exp(log_alpha_t)
+
+        if self.predict_x0:
+            phi_11 = torch.expm1(-r1 * h)
+            phi_12 = torch.expm1(-r2 * h)
+            phi_1 = torch.expm1(-h)
+            phi_22 = torch.expm1(-r2 * h) / (r2 * h) + 1.
+            phi_2 = phi_1 / h + 1.
+            phi_3 = phi_2 / h - 0.5
+
+            if model_s is None:
+                model_s = self.model_fn(x, s)
+            if model_s1 is None:
+                x_s1 = (
+                    expand_dims(sigma_s1 / sigma_s, dims) * x
+                    - expand_dims(alpha_s1 * phi_11, dims) * model_s
+                )
+                model_s1 = self.model_fn(x_s1, s1)
+            x_s2 = (
+                expand_dims(sigma_s2 / sigma_s, dims) * x
+                - expand_dims(alpha_s2 * phi_12, dims) * model_s
+                + r2 / r1 * expand_dims(alpha_s2 * phi_22, dims) * (model_s1 - model_s)
+            )
+            model_s2 = self.model_fn(x_s2, s2)
+            if solver_type == 'dpm_solver':
+                x_t = (
+                    expand_dims(sigma_t / sigma_s, dims) * x
+                    - expand_dims(alpha_t * phi_1, dims) * model_s
+                    + (1. / r2) * expand_dims(alpha_t * phi_2, dims) * (model_s2 - model_s)
+                )
+            elif solver_type == 'taylor':
+                D1_0 = (1. / r1) * (model_s1 - model_s)
+                D1_1 = (1. / r2) * (model_s2 - model_s)
+                D1 = (r2 * D1_0 - r1 * D1_1) / (r2 - r1)
+                D2 = 2. * (D1_1 - D1_0) / (r2 - r1)
+                x_t = (
+                    expand_dims(sigma_t / sigma_s, dims) * x
+                    - expand_dims(alpha_t * phi_1, dims) * model_s
+                    + expand_dims(alpha_t * phi_2, dims) * D1
+                    - expand_dims(alpha_t * phi_3, dims) * D2
+                )
+        else:
+            phi_11 = torch.expm1(r1 * h)
+            phi_12 = torch.expm1(r2 * h)
+            phi_1 = torch.expm1(h)
+            phi_22 = torch.expm1(r2 * h) / (r2 * h) - 1.
+            phi_2 = phi_1 / h - 1.
+            phi_3 = phi_2 / h - 0.5
+
+            if model_s is None:
+                model_s = self.model_fn(x, s)
+            if model_s1 is None:
+                x_s1 = (
+                    expand_dims(torch.exp(log_alpha_s1 - log_alpha_s), dims) * x
+                    - expand_dims(sigma_s1 * phi_11, dims) * model_s
+                )
+                model_s1 = self.model_fn(x_s1, s1)
+            x_s2 = (
+                expand_dims(torch.exp(log_alpha_s2 - log_alpha_s), dims) * x
+                - expand_dims(sigma_s2 * phi_12, dims) * model_s
+                - r2 / r1 * expand_dims(sigma_s2 * phi_22, dims) * (model_s1 - model_s)
+            )
+            model_s2 = self.model_fn(x_s2, s2)
+            if solver_type == 'dpm_solver':
+                x_t = (
+                    expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+                    - expand_dims(sigma_t * phi_1, dims) * model_s
+                    - (1. / r2) * expand_dims(sigma_t * phi_2, dims) * (model_s2 - model_s)
+                )
+            elif solver_type == 'taylor':
+                D1_0 = (1. / r1) * (model_s1 - model_s)
+                D1_1 = (1. / r2) * (model_s2 - model_s)
+                D1 = (r2 * D1_0 - r1 * D1_1) / (r2 - r1)
+                D2 = 2. * (D1_1 - D1_0) / (r2 - r1)
+                x_t = (
+                    expand_dims(torch.exp(log_alpha_t - log_alpha_s), dims) * x
+                    - expand_dims(sigma_t * phi_1, dims) * model_s
+                    - expand_dims(sigma_t * phi_2, dims) * D1
+                    - expand_dims(sigma_t * phi_3, dims) * D2
+                )
+
+        if return_intermediate:
+            return x_t, {'model_s': model_s, 'model_s1': model_s1, 'model_s2': model_s2}
+        else:
+            return x_t
+
+    def multistep_dpm_solver_second_update(self, x, model_prev_list, t_prev_list, t, solver_type="dpm_solver"):
+        """
+        Multistep solver DPM-Solver-2 from time `t_prev_list[-1]` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            model_prev_list: A list of pytorch tensor. The previous computed model values.
+            t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],)
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        if solver_type not in ['dpm_solver', 'taylor']:
+            raise ValueError("'solver_type' must be either 'dpm_solver' or 'taylor', got {}".format(solver_type))
+        ns = self.noise_schedule
+        dims = x.dim()
+        model_prev_1, model_prev_0 = model_prev_list
+        t_prev_1, t_prev_0 = t_prev_list
+        lambda_prev_1, lambda_prev_0, lambda_t = ns.marginal_lambda(t_prev_1), ns.marginal_lambda(t_prev_0), ns.marginal_lambda(t)
+        log_alpha_prev_0, log_alpha_t = ns.marginal_log_mean_coeff(t_prev_0), ns.marginal_log_mean_coeff(t)
+        sigma_prev_0, sigma_t = ns.marginal_std(t_prev_0), ns.marginal_std(t)
+        alpha_t = torch.exp(log_alpha_t)
+
+        h_0 = lambda_prev_0 - lambda_prev_1
+        h = lambda_t - lambda_prev_0
+        r0 = h_0 / h
+        D1_0 = expand_dims(1. / r0, dims) * (model_prev_0 - model_prev_1)
+        if self.predict_x0:
+            if solver_type == 'dpm_solver':
+                x_t = (
+                    expand_dims(sigma_t / sigma_prev_0, dims) * x
+                    - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0
+                    - 0.5 * expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * D1_0
+                )
+            elif solver_type == 'taylor':
+                x_t = (
+                    expand_dims(sigma_t / sigma_prev_0, dims) * x
+                    - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0
+                    + expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * D1_0
+                )
+        else:
+            if solver_type == 'dpm_solver':
+                x_t = (
+                    expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
+                    - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0
+                    - 0.5 * expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * D1_0
+                )
+            elif solver_type == 'taylor':
+                x_t = (
+                    expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
+                    - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0
+                    - expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * D1_0
+                )
+        return x_t
+
+    def multistep_dpm_solver_third_update(self, x, model_prev_list, t_prev_list, t, solver_type='dpm_solver'):
+        """
+        Multistep solver DPM-Solver-3 from time `t_prev_list[-1]` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            model_prev_list: A list of pytorch tensor. The previous computed model values.
+            t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],)
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        ns = self.noise_schedule
+        dims = x.dim()
+        model_prev_2, model_prev_1, model_prev_0 = model_prev_list
+        t_prev_2, t_prev_1, t_prev_0 = t_prev_list
+        lambda_prev_2, lambda_prev_1, lambda_prev_0, lambda_t = ns.marginal_lambda(t_prev_2), ns.marginal_lambda(t_prev_1), ns.marginal_lambda(t_prev_0), ns.marginal_lambda(t)
+        log_alpha_prev_0, log_alpha_t = ns.marginal_log_mean_coeff(t_prev_0), ns.marginal_log_mean_coeff(t)
+        sigma_prev_0, sigma_t = ns.marginal_std(t_prev_0), ns.marginal_std(t)
+        alpha_t = torch.exp(log_alpha_t)
+
+        h_1 = lambda_prev_1 - lambda_prev_2
+        h_0 = lambda_prev_0 - lambda_prev_1
+        h = lambda_t - lambda_prev_0
+        r0, r1 = h_0 / h, h_1 / h
+        D1_0 = expand_dims(1. / r0, dims) * (model_prev_0 - model_prev_1)
+        D1_1 = expand_dims(1. / r1, dims) * (model_prev_1 - model_prev_2)
+        D1 = D1_0 + expand_dims(r0 / (r0 + r1), dims) * (D1_0 - D1_1)
+        D2 = expand_dims(1. / (r0 + r1), dims) * (D1_0 - D1_1)
+        if self.predict_x0:
+            x_t = (
+                expand_dims(sigma_t / sigma_prev_0, dims) * x
+                - expand_dims(alpha_t * (torch.exp(-h) - 1.), dims) * model_prev_0
+                + expand_dims(alpha_t * ((torch.exp(-h) - 1.) / h + 1.), dims) * D1
+                - expand_dims(alpha_t * ((torch.exp(-h) - 1. + h) / h**2 - 0.5), dims) * D2
+            )
+        else:
+            x_t = (
+                expand_dims(torch.exp(log_alpha_t - log_alpha_prev_0), dims) * x
+                - expand_dims(sigma_t * (torch.exp(h) - 1.), dims) * model_prev_0
+                - expand_dims(sigma_t * ((torch.exp(h) - 1.) / h - 1.), dims) * D1
+                - expand_dims(sigma_t * ((torch.exp(h) - 1. - h) / h**2 - 0.5), dims) * D2
+            )
+        return x_t
+
+    def singlestep_dpm_solver_update(self, x, s, t, order, return_intermediate=False, solver_type='dpm_solver', r1=None, r2=None):
+        """
+        Singlestep DPM-Solver with the order `order` from time `s` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            s: A pytorch tensor. The starting time, with the shape (x.shape[0],).
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            order: A `int`. The order of DPM-Solver. We only support order == 1 or 2 or 3.
+            return_intermediate: A `bool`. If true, also return the model value at time `s`, `s1` and `s2` (the intermediate times).
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+            r1: A `float`. The hyperparameter of the second-order or third-order solver.
+            r2: A `float`. The hyperparameter of the third-order solver.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        if order == 1:
+            return self.dpm_solver_first_update(x, s, t, return_intermediate=return_intermediate)
+        elif order == 2:
+            return self.singlestep_dpm_solver_second_update(x, s, t, return_intermediate=return_intermediate, solver_type=solver_type, r1=r1)
+        elif order == 3:
+            return self.singlestep_dpm_solver_third_update(x, s, t, return_intermediate=return_intermediate, solver_type=solver_type, r1=r1, r2=r2)
+        else:
+            raise ValueError("Solver order must be 1 or 2 or 3, got {}".format(order))
+
+    def multistep_dpm_solver_update(self, x, model_prev_list, t_prev_list, t, order, solver_type='dpm_solver'):
+        """
+        Multistep DPM-Solver with the order `order` from time `t_prev_list[-1]` to time `t`.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `s`.
+            model_prev_list: A list of pytorch tensor. The previous computed model values.
+            t_prev_list: A list of pytorch tensor. The previous times, each time has the shape (x.shape[0],)
+            t: A pytorch tensor. The ending time, with the shape (x.shape[0],).
+            order: A `int`. The order of DPM-Solver. We only support order == 1 or 2 or 3.
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+        Returns:
+            x_t: A pytorch tensor. The approximated solution at time `t`.
+        """
+        if order == 1:
+            return self.dpm_solver_first_update(x, t_prev_list[-1], t, model_s=model_prev_list[-1])
+        elif order == 2:
+            return self.multistep_dpm_solver_second_update(x, model_prev_list, t_prev_list, t, solver_type=solver_type)
+        elif order == 3:
+            return self.multistep_dpm_solver_third_update(x, model_prev_list, t_prev_list, t, solver_type=solver_type)
+        else:
+            raise ValueError("Solver order must be 1 or 2 or 3, got {}".format(order))
+
+    def dpm_solver_adaptive(self, x, order, t_T, t_0, h_init=0.05, atol=0.0078, rtol=0.05, theta=0.9, t_err=1e-5, solver_type='dpm_solver'):
+        """
+        The adaptive step size solver based on singlestep DPM-Solver.
+
+        Args:
+            x: A pytorch tensor. The initial value at time `t_T`.
+            order: A `int`. The (higher) order of the solver. We only support order == 2 or 3.
+            t_T: A `float`. The starting time of the sampling (default is T).
+            t_0: A `float`. The ending time of the sampling (default is epsilon).
+            h_init: A `float`. The initial step size (for logSNR).
+            atol: A `float`. The absolute tolerance of the solver. For image data, the default setting is 0.0078, followed [1].
+            rtol: A `float`. The relative tolerance of the solver. The default setting is 0.05.
+            theta: A `float`. The safety hyperparameter for adapting the step size. The default setting is 0.9, followed [1].
+            t_err: A `float`. The tolerance for the time. We solve the diffusion ODE until the absolute error between the 
+                current time and `t_0` is less than `t_err`. The default setting is 1e-5.
+            solver_type: either 'dpm_solver' or 'taylor'. The type for the high-order solvers.
+                The type slightly impacts the performance. We recommend to use 'dpm_solver' type.
+        Returns:
+            x_0: A pytorch tensor. The approximated solution at time `t_0`.
+
+        [1] A. Jolicoeur-Martineau, K. Li, R. Piché-Taillefer, T. Kachman, and I. Mitliagkas, "Gotta go fast when generating data with score-based models," arXiv preprint arXiv:2105.14080, 2021.
+        """
+        ns = self.noise_schedule
+        s = t_T * torch.ones((x.shape[0],)).to(x)
+        lambda_s = ns.marginal_lambda(s)
+        lambda_0 = ns.marginal_lambda(t_0 * torch.ones_like(s).to(x))
+        h = h_init * torch.ones_like(s).to(x)
+        x_prev = x
+        nfe = 0
+        if order == 2:
+            r1 = 0.5
+            lower_update = lambda x, s, t: self.dpm_solver_first_update(x, s, t, return_intermediate=True)
+            higher_update = lambda x, s, t, **kwargs: self.singlestep_dpm_solver_second_update(x, s, t, r1=r1, solver_type=solver_type, **kwargs)
+        elif order == 3:
+            r1, r2 = 1. / 3., 2. / 3.
+            lower_update = lambda x, s, t: self.singlestep_dpm_solver_second_update(x, s, t, r1=r1, return_intermediate=True, solver_type=solver_type)
+            higher_update = lambda x, s, t, **kwargs: self.singlestep_dpm_solver_third_update(x, s, t, r1=r1, r2=r2, solver_type=solver_type, **kwargs)
+        else:
+            raise ValueError("For adaptive step size solver, order must be 2 or 3, got {}".format(order))
+        while torch.abs((s - t_0)).mean() > t_err:
+            t = ns.inverse_lambda(lambda_s + h)
+            x_lower, lower_noise_kwargs = lower_update(x, s, t)
+            x_higher = higher_update(x, s, t, **lower_noise_kwargs)
+            delta = torch.max(torch.ones_like(x).to(x) * atol, rtol * torch.max(torch.abs(x_lower), torch.abs(x_prev)))
+            norm_fn = lambda v: torch.sqrt(torch.square(v.reshape((v.shape[0], -1))).mean(dim=-1, keepdim=True))
+            E = norm_fn((x_higher - x_lower) / delta).max()
+            if torch.all(E <= 1.):
+                x = x_higher
+                s = t
+                x_prev = x_lower
+                lambda_s = ns.marginal_lambda(s)
+            h = torch.min(theta * h * torch.float_power(E, -1. / order).float(), lambda_0 - lambda_s)
+            nfe += order
+        print('adaptive solver nfe', nfe)
+        return x
+
+    def sample(self, x, steps=20, t_start=None, t_end=None, order=3, skip_type='time_uniform',
+        method='singlestep', lower_order_final=True, denoise_to_zero=False, solver_type='dpm_solver',
+        atol=0.0078, rtol=0.05,
+    ):
+        """
+        Compute the sample at time `t_end` by DPM-Solver, given the initial `x` at time `t_start`.
+
+        =====================================================
+
+        We support the following algorithms for both noise prediction model and data prediction model:
+            - 'singlestep':
+                Singlestep DPM-Solver (i.e. "DPM-Solver-fast" in the paper), which combines different orders of singlestep DPM-Solver. 
+                We combine all the singlestep solvers with order <= `order` to use up all the function evaluations (steps).
+                The total number of function evaluations (NFE) == `steps`.
+                Given a fixed NFE == `steps`, the sampling procedure is:
+                    - If `order` == 1:
+                        - Denote K = steps. We use K steps of DPM-Solver-1 (i.e. DDIM).
+                    - If `order` == 2:
+                        - Denote K = (steps // 2) + (steps % 2). We take K intermediate time steps for sampling.
+                        - If steps % 2 == 0, we use K steps of singlestep DPM-Solver-2.
+                        - If steps % 2 == 1, we use (K - 1) steps of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1.
+                    - If `order` == 3:
+                        - Denote K = (steps // 3 + 1). We take K intermediate time steps for sampling.
+                        - If steps % 3 == 0, we use (K - 2) steps of singlestep DPM-Solver-3, and 1 step of singlestep DPM-Solver-2 and 1 step of DPM-Solver-1.
+                        - If steps % 3 == 1, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of DPM-Solver-1.
+                        - If steps % 3 == 2, we use (K - 1) steps of singlestep DPM-Solver-3 and 1 step of singlestep DPM-Solver-2.
+            - 'multistep':
+                Multistep DPM-Solver with the order of `order`. The total number of function evaluations (NFE) == `steps`.
+                We initialize the first `order` values by lower order multistep solvers.
+                Given a fixed NFE == `steps`, the sampling procedure is:
+                    Denote K = steps.
+                    - If `order` == 1:
+                        - We use K steps of DPM-Solver-1 (i.e. DDIM).
+                    - If `order` == 2:
+                        - We firstly use 1 step of DPM-Solver-1, then use (K - 1) step of multistep DPM-Solver-2.
+                    - If `order` == 3:
+                        - We firstly use 1 step of DPM-Solver-1, then 1 step of multistep DPM-Solver-2, then (K - 2) step of multistep DPM-Solver-3.
+            - 'singlestep_fixed':
+                Fixed order singlestep DPM-Solver (i.e. DPM-Solver-1 or singlestep DPM-Solver-2 or singlestep DPM-Solver-3).
+                We use singlestep DPM-Solver-`order` for `order`=1 or 2 or 3, with total [`steps` // `order`] * `order` NFE.
+            - 'adaptive':
+                Adaptive step size DPM-Solver (i.e. "DPM-Solver-12" and "DPM-Solver-23" in the paper).
+                We ignore `steps` and use adaptive step size DPM-Solver with a higher order of `order`.
+                You can adjust the absolute tolerance `atol` and the relative tolerance `rtol` to balance the computatation costs
+                (NFE) and the sample quality.
+                    - If `order` == 2, we use DPM-Solver-12 which combines DPM-Solver-1 and singlestep DPM-Solver-2.
+                    - If `order` == 3, we use DPM-Solver-23 which combines singlestep DPM-Solver-2 and singlestep DPM-Solver-3.
+
+        =====================================================
+
+        Some advices for choosing the algorithm:
+            - For **unconditional sampling** or **guided sampling with small guidance scale** by DPMs:
+                Use singlestep DPM-Solver ("DPM-Solver-fast" in the paper) with `order = 3`.
+                e.g.
+                    >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, predict_x0=False)
+                    >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=3,
+                            skip_type='time_uniform', method='singlestep')
+            - For **guided sampling with large guidance scale** by DPMs:
+                Use multistep DPM-Solver with `predict_x0 = True` and `order = 2`.
+                e.g.
+                    >>> dpm_solver = DPM_Solver(model_fn, noise_schedule, predict_x0=True)
+                    >>> x_sample = dpm_solver.sample(x, steps=steps, t_start=t_start, t_end=t_end, order=2,
+                            skip_type='time_uniform', method='multistep')
+
+        We support three types of `skip_type`:
+            - 'logSNR': uniform logSNR for the time steps. **Recommended for low-resolutional images**
+            - 'time_uniform': uniform time for the time steps. **Recommended for high-resolutional images**.
+            - 'time_quadratic': quadratic time for the time steps.
+
+        =====================================================
+        Args:
+            x: A pytorch tensor. The initial value at time `t_start`
+                e.g. if `t_start` == T, then `x` is a sample from the standard normal distribution.
+            steps: A `int`. The total number of function evaluations (NFE).
+            t_start: A `float`. The starting time of the sampling.
+                If `T` is None, we use self.noise_schedule.T (default is 1.0).
+            t_end: A `float`. The ending time of the sampling.
+                If `t_end` is None, we use 1. / self.noise_schedule.total_N.
+                e.g. if total_N == 1000, we have `t_end` == 1e-3.
+                For discrete-time DPMs:
+                    - We recommend `t_end` == 1. / self.noise_schedule.total_N.
+                For continuous-time DPMs:
+                    - We recommend `t_end` == 1e-3 when `steps` <= 15; and `t_end` == 1e-4 when `steps` > 15.
+            order: A `int`. The order of DPM-Solver.
+            skip_type: A `str`. The type for the spacing of the time steps. 'time_uniform' or 'logSNR' or 'time_quadratic'.
+            method: A `str`. The method for sampling. 'singlestep' or 'multistep' or 'singlestep_fixed' or 'adaptive'.
+            denoise_to_zero: A `bool`. Whether to denoise to time 0 at the final step.
+                Default is `False`. If `denoise_to_zero` is `True`, the total NFE is (`steps` + 1).
+
+                This trick is firstly proposed by DDPM (https://arxiv.org/abs/2006.11239) and
+                score_sde (https://arxiv.org/abs/2011.13456). Such trick can improve the FID
+                for diffusion models sampling by diffusion SDEs for low-resolutional images
+                (such as CIFAR-10). However, we observed that such trick does not matter for
+                high-resolutional images. As it needs an additional NFE, we do not recommend
+                it for high-resolutional images.
+            lower_order_final: A `bool`. Whether to use lower order solvers at the final steps.
+                Only valid for `method=multistep` and `steps < 15`. We empirically find that
+                this trick is a key to stabilizing the sampling by DPM-Solver with very few steps
+                (especially for steps <= 10). So we recommend to set it to be `True`.
+            solver_type: A `str`. The taylor expansion type for the solver. `dpm_solver` or `taylor`. We recommend `dpm_solver`.
+            atol: A `float`. The absolute tolerance of the adaptive step size solver. Valid when `method` == 'adaptive'.
+            rtol: A `float`. The relative tolerance of the adaptive step size solver. Valid when `method` == 'adaptive'.
+        Returns:
+            x_end: A pytorch tensor. The approximated solution at time `t_end`.
+
+        """
+        t_0 = 1. / self.noise_schedule.total_N if t_end is None else t_end
+        t_T = self.noise_schedule.T if t_start is None else t_start
+        device = x.device
+        if method == 'adaptive':
+            with torch.no_grad():
+                x = self.dpm_solver_adaptive(x, order=order, t_T=t_T, t_0=t_0, atol=atol, rtol=rtol, solver_type=solver_type)
+        elif method == 'multistep':
+            assert steps >= order
+            timesteps = self.get_time_steps(skip_type=skip_type, t_T=t_T, t_0=t_0, N=steps, device=device)
+            assert timesteps.shape[0] - 1 == steps
+            with torch.no_grad():
+                vec_t = timesteps[0].expand((x.shape[0]))
+                model_prev_list = [self.model_fn(x, vec_t)]
+                t_prev_list = [vec_t]
+                # Init the first `order` values by lower order multistep DPM-Solver.
+                for init_order in range(1, order):
+                    vec_t = timesteps[init_order].expand(x.shape[0])
+                    x = self.multistep_dpm_solver_update(x, model_prev_list, t_prev_list, vec_t, init_order, solver_type=solver_type)
+                    model_prev_list.append(self.model_fn(x, vec_t))
+                    t_prev_list.append(vec_t)
+                # Compute the remaining values by `order`-th order multistep DPM-Solver.
+                for step in range(order, steps + 1):
+                    vec_t = timesteps[step].expand(x.shape[0])
+                    if lower_order_final and steps < 15:
+                        step_order = min(order, steps + 1 - step)
+                    else:
+                        step_order = order
+                    x = self.multistep_dpm_solver_update(x, model_prev_list, t_prev_list, vec_t, step_order, solver_type=solver_type)
+                    for i in range(order - 1):
+                        t_prev_list[i] = t_prev_list[i + 1]
+                        model_prev_list[i] = model_prev_list[i + 1]
+                    t_prev_list[-1] = vec_t
+                    # We do not need to evaluate the final model value.
+                    if step < steps:
+                        model_prev_list[-1] = self.model_fn(x, vec_t)
+        elif method in ['singlestep', 'singlestep_fixed']:
+            if method == 'singlestep':
+                timesteps_outer, orders = self.get_orders_and_timesteps_for_singlestep_solver(steps=steps, order=order, skip_type=skip_type, t_T=t_T, t_0=t_0, device=device)
+            elif method == 'singlestep_fixed':
+                K = steps // order
+                orders = [order,] * K
+                timesteps_outer = self.get_time_steps(skip_type=skip_type, t_T=t_T, t_0=t_0, N=K, device=device)
+            for i, order in enumerate(orders):
+                t_T_inner, t_0_inner = timesteps_outer[i], timesteps_outer[i + 1]
+                timesteps_inner = self.get_time_steps(skip_type=skip_type, t_T=t_T_inner.item(), t_0=t_0_inner.item(), N=order, device=device)
+                lambda_inner = self.noise_schedule.marginal_lambda(timesteps_inner)
+                vec_s, vec_t = t_T_inner.tile(x.shape[0]), t_0_inner.tile(x.shape[0])
+                h = lambda_inner[-1] - lambda_inner[0]
+                r1 = None if order <= 1 else (lambda_inner[1] - lambda_inner[0]) / h
+                r2 = None if order <= 2 else (lambda_inner[2] - lambda_inner[0]) / h
+                x = self.singlestep_dpm_solver_update(x, vec_s, vec_t, order, solver_type=solver_type, r1=r1, r2=r2)
+        if denoise_to_zero:
+            x = self.denoise_to_zero_fn(x, torch.ones((x.shape[0],)).to(device) * t_0)
+        return x
+
+
+
+#############################################################
+# other utility functions
+#############################################################
+
+def interpolate_fn(x, xp, yp):
+    """
+    A piecewise linear function y = f(x), using xp and yp as keypoints.
+    We implement f(x) in a differentiable way (i.e. applicable for autograd).
+    The function f(x) is well-defined for all x-axis. (For x beyond the bounds of xp, we use the outmost points of xp to define the linear function.)
+
+    Args:
+        x: PyTorch tensor with shape [N, C], where N is the batch size, C is the number of channels (we use C = 1 for DPM-Solver).
+        xp: PyTorch tensor with shape [C, K], where K is the number of keypoints.
+        yp: PyTorch tensor with shape [C, K].
+    Returns:
+        The function values f(x), with shape [N, C].
+    """
+    N, K = x.shape[0], xp.shape[1]
+    all_x = torch.cat([x.unsqueeze(2), xp.unsqueeze(0).repeat((N, 1, 1))], dim=2)
+    sorted_all_x, x_indices = torch.sort(all_x, dim=2)
+    x_idx = torch.argmin(x_indices, dim=2)
+    cand_start_idx = x_idx - 1
+    start_idx = torch.where(
+        torch.eq(x_idx, 0),
+        torch.tensor(1, device=x.device),
+        torch.where(
+            torch.eq(x_idx, K), torch.tensor(K - 2, device=x.device), cand_start_idx,
+        ),
+    )
+    end_idx = torch.where(torch.eq(start_idx, cand_start_idx), start_idx + 2, start_idx + 1)
+    start_x = torch.gather(sorted_all_x, dim=2, index=start_idx.unsqueeze(2)).squeeze(2)
+    end_x = torch.gather(sorted_all_x, dim=2, index=end_idx.unsqueeze(2)).squeeze(2)
+    start_idx2 = torch.where(
+        torch.eq(x_idx, 0),
+        torch.tensor(0, device=x.device),
+        torch.where(
+            torch.eq(x_idx, K), torch.tensor(K - 2, device=x.device), cand_start_idx,
+        ),
+    )
+    y_positions_expanded = yp.unsqueeze(0).expand(N, -1, -1)
+    start_y = torch.gather(y_positions_expanded, dim=2, index=start_idx2.unsqueeze(2)).squeeze(2)
+    end_y = torch.gather(y_positions_expanded, dim=2, index=(start_idx2 + 1).unsqueeze(2)).squeeze(2)
+    cand = start_y + (x - start_x) * (end_y - start_y) / (end_x - start_x)
+    return cand
+
+
+def expand_dims(v, dims):
+    """
+    Expand the tensor `v` to the dim `dims`.
+
+    Args:
+        `v`: a PyTorch tensor with shape [N].
+        `dim`: a `int`.
+    Returns:
+        a PyTorch tensor with shape [N, 1, 1, ..., 1] and the total dimension is `dims`.
+    """
+    return v[(...,) + (None,)*(dims - 1)]

stable_diffusion/ldm/models/diffusion/dpm_solver/sampler.py

@@ -0,0 +1,82 @@
+"""SAMPLING ONLY."""
+
+import torch
+
+from .dpm_solver import NoiseScheduleVP, model_wrapper, DPM_Solver
+
+
+class DPMSolverSampler(object):
+    def __init__(self, model, **kwargs):
+        super().__init__()
+        self.model = model
+        to_torch = lambda x: x.clone().detach().to(torch.float32).to(model.device)
+        self.register_buffer('alphas_cumprod', to_torch(model.alphas_cumprod))
+
+    def register_buffer(self, name, attr):
+        if type(attr) == torch.Tensor:
+            if attr.device != torch.device("cuda"):
+                attr = attr.to(torch.device("cuda"))
+        setattr(self, name, attr)
+
+    @torch.no_grad()
+    def sample(self,
+               S,
+               batch_size,
+               shape,
+               conditioning=None,
+               callback=None,
+               normals_sequence=None,
+               img_callback=None,
+               quantize_x0=False,
+               eta=0.,
+               mask=None,
+               x0=None,
+               temperature=1.,
+               noise_dropout=0.,
+               score_corrector=None,
+               corrector_kwargs=None,
+               verbose=True,
+               x_T=None,
+               log_every_t=100,
+               unconditional_guidance_scale=1.,
+               unconditional_conditioning=None,
+               # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+               **kwargs
+               ):
+        if conditioning is not None:
+            if isinstance(conditioning, dict):
+                cbs = conditioning[list(conditioning.keys())[0]].shape[0]
+                if cbs != batch_size:
+                    print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+            else:
+                if conditioning.shape[0] != batch_size:
+                    print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+        # sampling
+        C, H, W = shape
+        size = (batch_size, C, H, W)
+
+        # print(f'Data shape for DPM-Solver sampling is {size}, sampling steps {S}')
+
+        device = self.model.betas.device
+        if x_T is None:
+            img = torch.randn(size, device=device)
+        else:
+            img = x_T
+
+        ns = NoiseScheduleVP('discrete', alphas_cumprod=self.alphas_cumprod)
+
+        model_fn = model_wrapper(
+            lambda x, t, c: self.model.apply_model(x, t, c),
+            ns,
+            model_type="noise",
+            guidance_type="classifier-free",
+            condition=conditioning,
+            unconditional_condition=unconditional_conditioning,
+            guidance_scale=unconditional_guidance_scale,
+        )
+
+        dpm_solver = DPM_Solver(model_fn, ns, predict_x0=True, thresholding=False)
+        x = dpm_solver.sample(img, steps=S, skip_type="time_uniform", method="multistep", order=2, lower_order_final=True)
+
+        return x.to(device), None

stable_diffusion/ldm/models/diffusion/plms.py

@@ -0,0 +1,236 @@
+"""SAMPLING ONLY."""
+
+import torch
+import numpy as np
+from tqdm import tqdm
+from functools import partial
+
+from ldm.modules.diffusionmodules.util import make_ddim_sampling_parameters, make_ddim_timesteps, noise_like
+
+
+class PLMSSampler(object):
+    def __init__(self, model, schedule="linear", **kwargs):
+        super().__init__()
+        self.model = model
+        self.ddpm_num_timesteps = model.num_timesteps
+        self.schedule = schedule
+
+    def register_buffer(self, name, attr):
+        if type(attr) == torch.Tensor:
+            if attr.device != torch.device("cuda"):
+                attr = attr.to(torch.device("cuda"))
+        setattr(self, name, attr)
+
+    def make_schedule(self, ddim_num_steps, ddim_discretize="uniform", ddim_eta=0., verbose=True):
+        if ddim_eta != 0:
+            raise ValueError('ddim_eta must be 0 for PLMS')
+        self.ddim_timesteps = make_ddim_timesteps(ddim_discr_method=ddim_discretize, num_ddim_timesteps=ddim_num_steps,
+                                                  num_ddpm_timesteps=self.ddpm_num_timesteps,verbose=verbose)
+        alphas_cumprod = self.model.alphas_cumprod
+        assert alphas_cumprod.shape[0] == self.ddpm_num_timesteps, 'alphas have to be defined for each timestep'
+        to_torch = lambda x: x.clone().detach().to(torch.float32).to(self.model.device)
+
+        self.register_buffer('betas', to_torch(self.model.betas))
+        self.register_buffer('alphas_cumprod', to_torch(alphas_cumprod))
+        self.register_buffer('alphas_cumprod_prev', to_torch(self.model.alphas_cumprod_prev))
+
+        # calculations for diffusion q(x_t | x_{t-1}) and others
+        self.register_buffer('sqrt_alphas_cumprod', to_torch(np.sqrt(alphas_cumprod.cpu())))
+        self.register_buffer('sqrt_one_minus_alphas_cumprod', to_torch(np.sqrt(1. - alphas_cumprod.cpu())))
+        self.register_buffer('log_one_minus_alphas_cumprod', to_torch(np.log(1. - alphas_cumprod.cpu())))
+        self.register_buffer('sqrt_recip_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu())))
+        self.register_buffer('sqrt_recipm1_alphas_cumprod', to_torch(np.sqrt(1. / alphas_cumprod.cpu() - 1)))
+
+        # ddim sampling parameters
+        ddim_sigmas, ddim_alphas, ddim_alphas_prev = make_ddim_sampling_parameters(alphacums=alphas_cumprod.cpu(),
+                                                                                   ddim_timesteps=self.ddim_timesteps,
+                                                                                   eta=ddim_eta,verbose=verbose)
+        self.register_buffer('ddim_sigmas', ddim_sigmas)
+        self.register_buffer('ddim_alphas', ddim_alphas)
+        self.register_buffer('ddim_alphas_prev', ddim_alphas_prev)
+        self.register_buffer('ddim_sqrt_one_minus_alphas', np.sqrt(1. - ddim_alphas))
+        sigmas_for_original_sampling_steps = ddim_eta * torch.sqrt(
+            (1 - self.alphas_cumprod_prev) / (1 - self.alphas_cumprod) * (
+                        1 - self.alphas_cumprod / self.alphas_cumprod_prev))
+        self.register_buffer('ddim_sigmas_for_original_num_steps', sigmas_for_original_sampling_steps)
+
+    @torch.no_grad()
+    def sample(self,
+               S,
+               batch_size,
+               shape,
+               conditioning=None,
+               callback=None,
+               normals_sequence=None,
+               img_callback=None,
+               quantize_x0=False,
+               eta=0.,
+               mask=None,
+               x0=None,
+               temperature=1.,
+               noise_dropout=0.,
+               score_corrector=None,
+               corrector_kwargs=None,
+               verbose=True,
+               x_T=None,
+               log_every_t=100,
+               unconditional_guidance_scale=1.,
+               unconditional_conditioning=None,
+               # this has to come in the same format as the conditioning, # e.g. as encoded tokens, ...
+               **kwargs
+               ):
+        if conditioning is not None:
+            if isinstance(conditioning, dict):
+                cbs = conditioning[list(conditioning.keys())[0]].shape[0]
+                if cbs != batch_size:
+                    print(f"Warning: Got {cbs} conditionings but batch-size is {batch_size}")
+            else:
+                if conditioning.shape[0] != batch_size:
+                    print(f"Warning: Got {conditioning.shape[0]} conditionings but batch-size is {batch_size}")
+
+        self.make_schedule(ddim_num_steps=S, ddim_eta=eta, verbose=verbose)
+        # sampling
+        C, H, W = shape
+        size = (batch_size, C, H, W)
+        print(f'Data shape for PLMS sampling is {size}')
+
+        samples, intermediates = self.plms_sampling(conditioning, size,
+                                                    callback=callback,
+                                                    img_callback=img_callback,
+                                                    quantize_denoised=quantize_x0,
+                                                    mask=mask, x0=x0,
+                                                    ddim_use_original_steps=False,
+                                                    noise_dropout=noise_dropout,
+                                                    temperature=temperature,
+                                                    score_corrector=score_corrector,
+                                                    corrector_kwargs=corrector_kwargs,
+                                                    x_T=x_T,
+                                                    log_every_t=log_every_t,
+                                                    unconditional_guidance_scale=unconditional_guidance_scale,
+                                                    unconditional_conditioning=unconditional_conditioning,
+                                                    )
+        return samples, intermediates
+
+    @torch.no_grad()
+    def plms_sampling(self, cond, shape,
+                      x_T=None, ddim_use_original_steps=False,
+                      callback=None, timesteps=None, quantize_denoised=False,
+                      mask=None, x0=None, img_callback=None, log_every_t=100,
+                      temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+                      unconditional_guidance_scale=1., unconditional_conditioning=None,):
+        device = self.model.betas.device
+        b = shape[0]
+        if x_T is None:
+            img = torch.randn(shape, device=device)
+        else:
+            img = x_T
+
+        if timesteps is None:
+            timesteps = self.ddpm_num_timesteps if ddim_use_original_steps else self.ddim_timesteps
+        elif timesteps is not None and not ddim_use_original_steps:
+            subset_end = int(min(timesteps / self.ddim_timesteps.shape[0], 1) * self.ddim_timesteps.shape[0]) - 1
+            timesteps = self.ddim_timesteps[:subset_end]
+
+        intermediates = {'x_inter': [img], 'pred_x0': [img]}
+        time_range = list(reversed(range(0,timesteps))) if ddim_use_original_steps else np.flip(timesteps)
+        total_steps = timesteps if ddim_use_original_steps else timesteps.shape[0]
+        print(f"Running PLMS Sampling with {total_steps} timesteps")
+
+        iterator = tqdm(time_range, desc='PLMS Sampler', total=total_steps)
+        old_eps = []
+
+        for i, step in enumerate(iterator):
+            index = total_steps - i - 1
+            ts = torch.full((b,), step, device=device, dtype=torch.long)
+            ts_next = torch.full((b,), time_range[min(i + 1, len(time_range) - 1)], device=device, dtype=torch.long)
+
+            if mask is not None:
+                assert x0 is not None
+                img_orig = self.model.q_sample(x0, ts)  # TODO: deterministic forward pass?
+                img = img_orig * mask + (1. - mask) * img
+
+            outs = self.p_sample_plms(img, cond, ts, index=index, use_original_steps=ddim_use_original_steps,
+                                      quantize_denoised=quantize_denoised, temperature=temperature,
+                                      noise_dropout=noise_dropout, score_corrector=score_corrector,
+                                      corrector_kwargs=corrector_kwargs,
+                                      unconditional_guidance_scale=unconditional_guidance_scale,
+                                      unconditional_conditioning=unconditional_conditioning,
+                                      old_eps=old_eps, t_next=ts_next)
+            img, pred_x0, e_t = outs
+            old_eps.append(e_t)
+            if len(old_eps) >= 4:
+                old_eps.pop(0)
+            if callback: callback(i)
+            if img_callback: img_callback(pred_x0, i)
+
+            if index % log_every_t == 0 or index == total_steps - 1:
+                intermediates['x_inter'].append(img)
+                intermediates['pred_x0'].append(pred_x0)
+
+        return img, intermediates
+
+    @torch.no_grad()
+    def p_sample_plms(self, x, c, t, index, repeat_noise=False, use_original_steps=False, quantize_denoised=False,
+                      temperature=1., noise_dropout=0., score_corrector=None, corrector_kwargs=None,
+                      unconditional_guidance_scale=1., unconditional_conditioning=None, old_eps=None, t_next=None):
+        b, *_, device = *x.shape, x.device
+
+        def get_model_output(x, t):
+            if unconditional_conditioning is None or unconditional_guidance_scale == 1.:
+                e_t = self.model.apply_model(x, t, c)
+            else:
+                x_in = torch.cat([x] * 2)
+                t_in = torch.cat([t] * 2)
+                c_in = torch.cat([unconditional_conditioning, c])
+                e_t_uncond, e_t = self.model.apply_model(x_in, t_in, c_in).chunk(2)
+                e_t = e_t_uncond + unconditional_guidance_scale * (e_t - e_t_uncond)
+
+            if score_corrector is not None:
+                assert self.model.parameterization == "eps"
+                e_t = score_corrector.modify_score(self.model, e_t, x, t, c, **corrector_kwargs)
+
+            return e_t
+
+        alphas = self.model.alphas_cumprod if use_original_steps else self.ddim_alphas
+        alphas_prev = self.model.alphas_cumprod_prev if use_original_steps else self.ddim_alphas_prev
+        sqrt_one_minus_alphas = self.model.sqrt_one_minus_alphas_cumprod if use_original_steps else self.ddim_sqrt_one_minus_alphas
+        sigmas = self.model.ddim_sigmas_for_original_num_steps if use_original_steps else self.ddim_sigmas
+
+        def get_x_prev_and_pred_x0(e_t, index):
+            # select parameters corresponding to the currently considered timestep
+            a_t = torch.full((b, 1, 1, 1), alphas[index], device=device)
+            a_prev = torch.full((b, 1, 1, 1), alphas_prev[index], device=device)
+            sigma_t = torch.full((b, 1, 1, 1), sigmas[index], device=device)
+            sqrt_one_minus_at = torch.full((b, 1, 1, 1), sqrt_one_minus_alphas[index],device=device)
+
+            # current prediction for x_0
+            pred_x0 = (x - sqrt_one_minus_at * e_t) / a_t.sqrt()
+            if quantize_denoised:
+                pred_x0, _, *_ = self.model.first_stage_model.quantize(pred_x0)
+            # direction pointing to x_t
+            dir_xt = (1. - a_prev - sigma_t**2).sqrt() * e_t
+            noise = sigma_t * noise_like(x.shape, device, repeat_noise) * temperature
+            if noise_dropout > 0.:
+                noise = torch.nn.functional.dropout(noise, p=noise_dropout)
+            x_prev = a_prev.sqrt() * pred_x0 + dir_xt + noise
+            return x_prev, pred_x0
+
+        e_t = get_model_output(x, t)
+        if len(old_eps) == 0:
+            # Pseudo Improved Euler (2nd order)
+            x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t, index)
+            e_t_next = get_model_output(x_prev, t_next)
+            e_t_prime = (e_t + e_t_next) / 2
+        elif len(old_eps) == 1:
+            # 2nd order Pseudo Linear Multistep (Adams-Bashforth)
+            e_t_prime = (3 * e_t - old_eps[-1]) / 2
+        elif len(old_eps) == 2:
+            # 3nd order Pseudo Linear Multistep (Adams-Bashforth)
+            e_t_prime = (23 * e_t - 16 * old_eps[-1] + 5 * old_eps[-2]) / 12
+        elif len(old_eps) >= 3:
+            # 4nd order Pseudo Linear Multistep (Adams-Bashforth)
+            e_t_prime = (55 * e_t - 59 * old_eps[-1] + 37 * old_eps[-2] - 9 * old_eps[-3]) / 24
+
+        x_prev, pred_x0 = get_x_prev_and_pred_x0(e_t_prime, index)
+
+        return x_prev, pred_x0, e_t

stable_diffusion/ldm/modules/attention.py

@@ -0,0 +1,275 @@
+# File modified by authors of InstructPix2Pix from original (https://github.com/CompVis/stable-diffusion).
+# See more details in LICENSE.
+
+from inspect import isfunction
+import math
+import torch
+import torch.nn.functional as F
+from torch import nn, einsum
+from einops import rearrange, repeat
+
+from ldm.modules.diffusionmodules.util import checkpoint
+
+
+def exists(val):
+    return val is not None
+
+
+def uniq(arr):
+    return{el: True for el in arr}.keys()
+
+
+def default(val, d):
+    if exists(val):
+        return val
+    return d() if isfunction(d) else d
+
+
+def max_neg_value(t):
+    return -torch.finfo(t.dtype).max
+
+
+def init_(tensor):
+    dim = tensor.shape[-1]
+    std = 1 / math.sqrt(dim)
+    tensor.uniform_(-std, std)
+    return tensor
+
+
+# feedforward
+class GEGLU(nn.Module):
+    def __init__(self, dim_in, dim_out):
+        super().__init__()
+        self.proj = nn.Linear(dim_in, dim_out * 2)
+
+    def forward(self, x):
+        x, gate = self.proj(x).chunk(2, dim=-1)
+        return x * F.gelu(gate)
+
+
+class FeedForward(nn.Module):
+    def __init__(self, dim, dim_out=None, mult=4, glu=False, dropout=0.):
+        super().__init__()
+        inner_dim = int(dim * mult)
+        dim_out = default(dim_out, dim)
+        project_in = nn.Sequential(
+            nn.Linear(dim, inner_dim),
+            nn.GELU()
+        ) if not glu else GEGLU(dim, inner_dim)
+
+        self.net = nn.Sequential(
+            project_in,
+            nn.Dropout(dropout),
+            nn.Linear(inner_dim, dim_out)
+        )
+
+    def forward(self, x):
+        return self.net(x)
+
+
+def zero_module(module):
+    """
+    Zero out the parameters of a module and return it.
+    """
+    for p in module.parameters():
+        p.detach().zero_()
+    return module
+
+
+def Normalize(in_channels):
+    return torch.nn.GroupNorm(num_groups=32, num_channels=in_channels, eps=1e-6, affine=True)
+
+
+class LinearAttention(nn.Module):
+    def __init__(self, dim, heads=4, dim_head=32):
+        super().__init__()
+        self.heads = heads
+        hidden_dim = dim_head * heads
+        self.to_qkv = nn.Conv2d(dim, hidden_dim * 3, 1, bias = False)
+        self.to_out = nn.Conv2d(hidden_dim, dim, 1)
+
+    def forward(self, x):
+        b, c, h, w = x.shape
+        qkv = self.to_qkv(x)
+        q, k, v = rearrange(qkv, 'b (qkv heads c) h w -> qkv b heads c (h w)', heads = self.heads, qkv=3)
+        k = k.softmax(dim=-1) 
+        context = torch.einsum('bhdn,bhen->bhde', k, v)
+        out = torch.einsum('bhde,bhdn->bhen', context, q)
+        out = rearrange(out, 'b heads c (h w) -> b (heads c) h w', heads=self.heads, h=h, w=w)
+        return self.to_out(out)
+
+
+class SpatialSelfAttention(nn.Module):
+    def __init__(self, in_channels):
+        super().__init__()
+        self.in_channels = in_channels
+
+        self.norm = Normalize(in_channels)
+        self.q = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.k = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.v = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.proj_out = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=1,
+                                        stride=1,
+                                        padding=0)
+
+    def forward(self, x):
+        h_ = x
+        h_ = self.norm(h_)
+        q = self.q(h_)
+        k = self.k(h_)
+        v = self.v(h_)
+
+        # compute attention
+        b,c,h,w = q.shape
+        q = rearrange(q, 'b c h w -> b (h w) c')
+        k = rearrange(k, 'b c h w -> b c (h w)')
+        w_ = torch.einsum('bij,bjk->bik', q, k)
+
+        w_ = w_ * (int(c)**(-0.5))
+        w_ = torch.nn.functional.softmax(w_, dim=2)
+
+        # attend to values
+        v = rearrange(v, 'b c h w -> b c (h w)')
+        w_ = rearrange(w_, 'b i j -> b j i')
+        h_ = torch.einsum('bij,bjk->bik', v, w_)
+        h_ = rearrange(h_, 'b c (h w) -> b c h w', h=h)
+        h_ = self.proj_out(h_)
+
+        return x+h_
+
+
+class CrossAttention(nn.Module):
+    def __init__(self, query_dim, context_dim=None, heads=8, dim_head=64, dropout=0.):
+        super().__init__()
+        inner_dim = dim_head * heads
+        context_dim = default(context_dim, query_dim)
+
+        self.scale = dim_head ** -0.5
+        self.heads = heads
+
+        self.to_q = nn.Linear(query_dim, inner_dim, bias=False)
+        self.to_k = nn.Linear(context_dim, inner_dim, bias=False)
+        self.to_v = nn.Linear(context_dim, inner_dim, bias=False)
+
+        self.to_out = nn.Sequential(
+            nn.Linear(inner_dim, query_dim),
+            nn.Dropout(dropout)
+        )
+
+        self.prompt_to_prompt = False
+
+    def forward(self, x, context=None, mask=None):
+        is_self_attn = context is None
+
+        h = self.heads
+
+        q = self.to_q(x)
+        context = default(context, x)
+        k = self.to_k(context)
+        v = self.to_v(context)
+
+        q, k, v = map(lambda t: rearrange(t, 'b n (h d) -> (b h) n d', h=h), (q, k, v))
+
+        sim = einsum('b i d, b j d -> b i j', q, k) * self.scale
+
+        if self.prompt_to_prompt and is_self_attn:
+            # Unlike the original Prompt-to-Prompt which uses cross-attention layers, we copy attention maps for self-attention layers.
+            # There must be 4 elements in the batch: {conditional, unconditional} x {prompt 1, prompt 2}
+            assert x.size(0) == 4
+            sims = sim.chunk(4)
+            sim = torch.cat((sims[0], sims[0], sims[2], sims[2]))
+
+        if exists(mask):
+            mask = rearrange(mask, 'b ... -> b (...)')
+            max_neg_value = -torch.finfo(sim.dtype).max
+            mask = repeat(mask, 'b j -> (b h) () j', h=h)
+            sim.masked_fill_(~mask, max_neg_value)
+
+        # attention, what we cannot get enough of
+        attn = sim.softmax(dim=-1)
+
+        out = einsum('b i j, b j d -> b i d', attn, v)
+        out = rearrange(out, '(b h) n d -> b n (h d)', h=h)
+        return self.to_out(out)
+
+
+class BasicTransformerBlock(nn.Module):
+    def __init__(self, dim, n_heads, d_head, dropout=0., context_dim=None, gated_ff=True, checkpoint=True):
+        super().__init__()
+        self.attn1 = CrossAttention(query_dim=dim, heads=n_heads, dim_head=d_head, dropout=dropout)  # is a self-attention
+        self.ff = FeedForward(dim, dropout=dropout, glu=gated_ff)
+        self.attn2 = CrossAttention(query_dim=dim, context_dim=context_dim,
+                                    heads=n_heads, dim_head=d_head, dropout=dropout)  # is self-attn if context is none
+        self.norm1 = nn.LayerNorm(dim)
+        self.norm2 = nn.LayerNorm(dim)
+        self.norm3 = nn.LayerNorm(dim)
+        self.checkpoint = checkpoint
+
+    def forward(self, x, context=None):
+        return checkpoint(self._forward, (x, context), self.parameters(), self.checkpoint)
+
+    def _forward(self, x, context=None):
+        x = self.attn1(self.norm1(x)) + x
+        x = self.attn2(self.norm2(x), context=context) + x
+        x = self.ff(self.norm3(x)) + x
+        return x
+
+
+class SpatialTransformer(nn.Module):
+    """
+    Transformer block for image-like data.
+    First, project the input (aka embedding)
+    and reshape to b, t, d.
+    Then apply standard transformer action.
+    Finally, reshape to image
+    """
+    def __init__(self, in_channels, n_heads, d_head,
+                 depth=1, dropout=0., context_dim=None):
+        super().__init__()
+        self.in_channels = in_channels
+        inner_dim = n_heads * d_head
+        self.norm = Normalize(in_channels)
+
+        self.proj_in = nn.Conv2d(in_channels,
+                                 inner_dim,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+
+        self.transformer_blocks = nn.ModuleList(
+            [BasicTransformerBlock(inner_dim, n_heads, d_head, dropout=dropout, context_dim=context_dim)
+                for d in range(depth)]
+        )
+
+        self.proj_out = zero_module(nn.Conv2d(inner_dim,
+                                              in_channels,
+                                              kernel_size=1,
+                                              stride=1,
+                                              padding=0))
+
+    def forward(self, x, context=None):
+        # note: if no context is given, cross-attention defaults to self-attention
+        b, c, h, w = x.shape
+        x_in = x
+        x = self.norm(x)
+        x = self.proj_in(x)
+        x = rearrange(x, 'b c h w -> b (h w) c')
+        for block in self.transformer_blocks:
+            x = block(x, context=context)
+        x = rearrange(x, 'b (h w) c -> b c h w', h=h, w=w)
+        x = self.proj_out(x)
+        return x + x_in

stable_diffusion/ldm/modules/diffusionmodules/model.py

@@ -0,0 +1,835 @@
+# pytorch_diffusion + derived encoder decoder
+import math
+import torch
+import torch.nn as nn
+import numpy as np
+from einops import rearrange
+
+from ldm.util import instantiate_from_config
+from ldm.modules.attention import LinearAttention
+
+
+def get_timestep_embedding(timesteps, embedding_dim):
+    """
+    This matches the implementation in Denoising Diffusion Probabilistic Models:
+    From Fairseq.
+    Build sinusoidal embeddings.
+    This matches the implementation in tensor2tensor, but differs slightly
+    from the description in Section 3.5 of "Attention Is All You Need".
+    """
+    assert len(timesteps.shape) == 1
+
+    half_dim = embedding_dim // 2
+    emb = math.log(10000) / (half_dim - 1)
+    emb = torch.exp(torch.arange(half_dim, dtype=torch.float32) * -emb)
+    emb = emb.to(device=timesteps.device)
+    emb = timesteps.float()[:, None] * emb[None, :]
+    emb = torch.cat([torch.sin(emb), torch.cos(emb)], dim=1)
+    if embedding_dim % 2 == 1:  # zero pad
+        emb = torch.nn.functional.pad(emb, (0,1,0,0))
+    return emb
+
+
+def nonlinearity(x):
+    # swish
+    return x*torch.sigmoid(x)
+
+
+def Normalize(in_channels, num_groups=32):
+    return torch.nn.GroupNorm(num_groups=num_groups, num_channels=in_channels, eps=1e-6, affine=True)
+
+
+class Upsample(nn.Module):
+    def __init__(self, in_channels, with_conv):
+        super().__init__()
+        self.with_conv = with_conv
+        if self.with_conv:
+            self.conv = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, x):
+        x = torch.nn.functional.interpolate(x, scale_factor=2.0, mode="nearest")
+        if self.with_conv:
+            x = self.conv(x)
+        return x
+
+
+class Downsample(nn.Module):
+    def __init__(self, in_channels, with_conv):
+        super().__init__()
+        self.with_conv = with_conv
+        if self.with_conv:
+            # no asymmetric padding in torch conv, must do it ourselves
+            self.conv = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=3,
+                                        stride=2,
+                                        padding=0)
+
+    def forward(self, x):
+        if self.with_conv:
+            pad = (0,1,0,1)
+            x = torch.nn.functional.pad(x, pad, mode="constant", value=0)
+            x = self.conv(x)
+        else:
+            x = torch.nn.functional.avg_pool2d(x, kernel_size=2, stride=2)
+        return x
+
+
+class ResnetBlock(nn.Module):
+    def __init__(self, *, in_channels, out_channels=None, conv_shortcut=False,
+                 dropout, temb_channels=512):
+        super().__init__()
+        self.in_channels = in_channels
+        out_channels = in_channels if out_channels is None else out_channels
+        self.out_channels = out_channels
+        self.use_conv_shortcut = conv_shortcut
+
+        self.norm1 = Normalize(in_channels)
+        self.conv1 = torch.nn.Conv2d(in_channels,
+                                     out_channels,
+                                     kernel_size=3,
+                                     stride=1,
+                                     padding=1)
+        if temb_channels > 0:
+            self.temb_proj = torch.nn.Linear(temb_channels,
+                                             out_channels)
+        self.norm2 = Normalize(out_channels)
+        self.dropout = torch.nn.Dropout(dropout)
+        self.conv2 = torch.nn.Conv2d(out_channels,
+                                     out_channels,
+                                     kernel_size=3,
+                                     stride=1,
+                                     padding=1)
+        if self.in_channels != self.out_channels:
+            if self.use_conv_shortcut:
+                self.conv_shortcut = torch.nn.Conv2d(in_channels,
+                                                     out_channels,
+                                                     kernel_size=3,
+                                                     stride=1,
+                                                     padding=1)
+            else:
+                self.nin_shortcut = torch.nn.Conv2d(in_channels,
+                                                    out_channels,
+                                                    kernel_size=1,
+                                                    stride=1,
+                                                    padding=0)
+
+    def forward(self, x, temb):
+        h = x
+        h = self.norm1(h)
+        h = nonlinearity(h)
+        h = self.conv1(h)
+
+        if temb is not None:
+            h = h + self.temb_proj(nonlinearity(temb))[:,:,None,None]
+
+        h = self.norm2(h)
+        h = nonlinearity(h)
+        h = self.dropout(h)
+        h = self.conv2(h)
+
+        if self.in_channels != self.out_channels:
+            if self.use_conv_shortcut:
+                x = self.conv_shortcut(x)
+            else:
+                x = self.nin_shortcut(x)
+
+        return x+h
+
+
+class LinAttnBlock(LinearAttention):
+    """to match AttnBlock usage"""
+    def __init__(self, in_channels):
+        super().__init__(dim=in_channels, heads=1, dim_head=in_channels)
+
+
+class AttnBlock(nn.Module):
+    def __init__(self, in_channels):
+        super().__init__()
+        self.in_channels = in_channels
+
+        self.norm = Normalize(in_channels)
+        self.q = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.k = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.v = torch.nn.Conv2d(in_channels,
+                                 in_channels,
+                                 kernel_size=1,
+                                 stride=1,
+                                 padding=0)
+        self.proj_out = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=1,
+                                        stride=1,
+                                        padding=0)
+
+
+    def forward(self, x):
+        h_ = x
+        h_ = self.norm(h_)
+        q = self.q(h_)
+        k = self.k(h_)
+        v = self.v(h_)
+
+        # compute attention
+        b,c,h,w = q.shape
+        q = q.reshape(b,c,h*w)
+        q = q.permute(0,2,1)   # b,hw,c
+        k = k.reshape(b,c,h*w) # b,c,hw
+        w_ = torch.bmm(q,k)     # b,hw,hw    w[b,i,j]=sum_c q[b,i,c]k[b,c,j]
+        w_ = w_ * (int(c)**(-0.5))
+        w_ = torch.nn.functional.softmax(w_, dim=2)
+
+        # attend to values
+        v = v.reshape(b,c,h*w)
+        w_ = w_.permute(0,2,1)   # b,hw,hw (first hw of k, second of q)
+        h_ = torch.bmm(v,w_)     # b, c,hw (hw of q) h_[b,c,j] = sum_i v[b,c,i] w_[b,i,j]
+        h_ = h_.reshape(b,c,h,w)
+
+        h_ = self.proj_out(h_)
+
+        return x+h_
+
+
+def make_attn(in_channels, attn_type="vanilla"):
+    assert attn_type in ["vanilla", "linear", "none"], f'attn_type {attn_type} unknown'
+    print(f"making attention of type '{attn_type}' with {in_channels} in_channels")
+    if attn_type == "vanilla":
+        return AttnBlock(in_channels)
+    elif attn_type == "none":
+        return nn.Identity(in_channels)
+    else:
+        return LinAttnBlock(in_channels)
+
+
+class Model(nn.Module):
+    def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
+                 attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
+                 resolution, use_timestep=True, use_linear_attn=False, attn_type="vanilla"):
+        super().__init__()
+        if use_linear_attn: attn_type = "linear"
+        self.ch = ch
+        self.temb_ch = self.ch*4
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        self.resolution = resolution
+        self.in_channels = in_channels
+
+        self.use_timestep = use_timestep
+        if self.use_timestep:
+            # timestep embedding
+            self.temb = nn.Module()
+            self.temb.dense = nn.ModuleList([
+                torch.nn.Linear(self.ch,
+                                self.temb_ch),
+                torch.nn.Linear(self.temb_ch,
+                                self.temb_ch),
+            ])
+
+        # downsampling
+        self.conv_in = torch.nn.Conv2d(in_channels,
+                                       self.ch,
+                                       kernel_size=3,
+                                       stride=1,
+                                       padding=1)
+
+        curr_res = resolution
+        in_ch_mult = (1,)+tuple(ch_mult)
+        self.down = nn.ModuleList()
+        for i_level in range(self.num_resolutions):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_in = ch*in_ch_mult[i_level]
+            block_out = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks):
+                block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(make_attn(block_in, attn_type=attn_type))
+            down = nn.Module()
+            down.block = block
+            down.attn = attn
+            if i_level != self.num_resolutions-1:
+                down.downsample = Downsample(block_in, resamp_with_conv)
+                curr_res = curr_res // 2
+            self.down.append(down)
+
+        # middle
+        self.mid = nn.Module()
+        self.mid.block_1 = ResnetBlock(in_channels=block_in,
+                                       out_channels=block_in,
+                                       temb_channels=self.temb_ch,
+                                       dropout=dropout)
+        self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
+        self.mid.block_2 = ResnetBlock(in_channels=block_in,
+                                       out_channels=block_in,
+                                       temb_channels=self.temb_ch,
+                                       dropout=dropout)
+
+        # upsampling
+        self.up = nn.ModuleList()
+        for i_level in reversed(range(self.num_resolutions)):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_out = ch*ch_mult[i_level]
+            skip_in = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks+1):
+                if i_block == self.num_res_blocks:
+                    skip_in = ch*in_ch_mult[i_level]
+                block.append(ResnetBlock(in_channels=block_in+skip_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(make_attn(block_in, attn_type=attn_type))
+            up = nn.Module()
+            up.block = block
+            up.attn = attn
+            if i_level != 0:
+                up.upsample = Upsample(block_in, resamp_with_conv)
+                curr_res = curr_res * 2
+            self.up.insert(0, up) # prepend to get consistent order
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        out_ch,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, x, t=None, context=None):
+        #assert x.shape[2] == x.shape[3] == self.resolution
+        if context is not None:
+            # assume aligned context, cat along channel axis
+            x = torch.cat((x, context), dim=1)
+        if self.use_timestep:
+            # timestep embedding
+            assert t is not None
+            temb = get_timestep_embedding(t, self.ch)
+            temb = self.temb.dense[0](temb)
+            temb = nonlinearity(temb)
+            temb = self.temb.dense[1](temb)
+        else:
+            temb = None
+
+        # downsampling
+        hs = [self.conv_in(x)]
+        for i_level in range(self.num_resolutions):
+            for i_block in range(self.num_res_blocks):
+                h = self.down[i_level].block[i_block](hs[-1], temb)
+                if len(self.down[i_level].attn) > 0:
+                    h = self.down[i_level].attn[i_block](h)
+                hs.append(h)
+            if i_level != self.num_resolutions-1:
+                hs.append(self.down[i_level].downsample(hs[-1]))
+
+        # middle
+        h = hs[-1]
+        h = self.mid.block_1(h, temb)
+        h = self.mid.attn_1(h)
+        h = self.mid.block_2(h, temb)
+
+        # upsampling
+        for i_level in reversed(range(self.num_resolutions)):
+            for i_block in range(self.num_res_blocks+1):
+                h = self.up[i_level].block[i_block](
+                    torch.cat([h, hs.pop()], dim=1), temb)
+                if len(self.up[i_level].attn) > 0:
+                    h = self.up[i_level].attn[i_block](h)
+            if i_level != 0:
+                h = self.up[i_level].upsample(h)
+
+        # end
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        return h
+
+    def get_last_layer(self):
+        return self.conv_out.weight
+
+
+class Encoder(nn.Module):
+    def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
+                 attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
+                 resolution, z_channels, double_z=True, use_linear_attn=False, attn_type="vanilla",
+                 **ignore_kwargs):
+        super().__init__()
+        if use_linear_attn: attn_type = "linear"
+        self.ch = ch
+        self.temb_ch = 0
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        self.resolution = resolution
+        self.in_channels = in_channels
+
+        # downsampling
+        self.conv_in = torch.nn.Conv2d(in_channels,
+                                       self.ch,
+                                       kernel_size=3,
+                                       stride=1,
+                                       padding=1)
+
+        curr_res = resolution
+        in_ch_mult = (1,)+tuple(ch_mult)
+        self.in_ch_mult = in_ch_mult
+        self.down = nn.ModuleList()
+        for i_level in range(self.num_resolutions):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_in = ch*in_ch_mult[i_level]
+            block_out = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks):
+                block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(make_attn(block_in, attn_type=attn_type))
+            down = nn.Module()
+            down.block = block
+            down.attn = attn
+            if i_level != self.num_resolutions-1:
+                down.downsample = Downsample(block_in, resamp_with_conv)
+                curr_res = curr_res // 2
+            self.down.append(down)
+
+        # middle
+        self.mid = nn.Module()
+        self.mid.block_1 = ResnetBlock(in_channels=block_in,
+                                       out_channels=block_in,
+                                       temb_channels=self.temb_ch,
+                                       dropout=dropout)
+        self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
+        self.mid.block_2 = ResnetBlock(in_channels=block_in,
+                                       out_channels=block_in,
+                                       temb_channels=self.temb_ch,
+                                       dropout=dropout)
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        2*z_channels if double_z else z_channels,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, x):
+        # timestep embedding
+        temb = None
+
+        # downsampling
+        hs = [self.conv_in(x)]
+        for i_level in range(self.num_resolutions):
+            for i_block in range(self.num_res_blocks):
+                h = self.down[i_level].block[i_block](hs[-1], temb)
+                if len(self.down[i_level].attn) > 0:
+                    h = self.down[i_level].attn[i_block](h)
+                hs.append(h)
+            if i_level != self.num_resolutions-1:
+                hs.append(self.down[i_level].downsample(hs[-1]))
+
+        # middle
+        h = hs[-1]
+        h = self.mid.block_1(h, temb)
+        h = self.mid.attn_1(h)
+        h = self.mid.block_2(h, temb)
+
+        # end
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        return h
+
+
+class Decoder(nn.Module):
+    def __init__(self, *, ch, out_ch, ch_mult=(1,2,4,8), num_res_blocks,
+                 attn_resolutions, dropout=0.0, resamp_with_conv=True, in_channels,
+                 resolution, z_channels, give_pre_end=False, tanh_out=False, use_linear_attn=False,
+                 attn_type="vanilla", **ignorekwargs):
+        super().__init__()
+        if use_linear_attn: attn_type = "linear"
+        self.ch = ch
+        self.temb_ch = 0
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        self.resolution = resolution
+        self.in_channels = in_channels
+        self.give_pre_end = give_pre_end
+        self.tanh_out = tanh_out
+
+        # compute in_ch_mult, block_in and curr_res at lowest res
+        in_ch_mult = (1,)+tuple(ch_mult)
+        block_in = ch*ch_mult[self.num_resolutions-1]
+        curr_res = resolution // 2**(self.num_resolutions-1)
+        self.z_shape = (1,z_channels,curr_res,curr_res)
+        print("Working with z of shape {} = {} dimensions.".format(
+            self.z_shape, np.prod(self.z_shape)))
+
+        # z to block_in
+        self.conv_in = torch.nn.Conv2d(z_channels,
+                                       block_in,
+                                       kernel_size=3,
+                                       stride=1,
+                                       padding=1)
+
+        # middle
+        self.mid = nn.Module()
+        self.mid.block_1 = ResnetBlock(in_channels=block_in,
+                                       out_channels=block_in,
+                                       temb_channels=self.temb_ch,
+                                       dropout=dropout)
+        self.mid.attn_1 = make_attn(block_in, attn_type=attn_type)
+        self.mid.block_2 = ResnetBlock(in_channels=block_in,
+                                       out_channels=block_in,
+                                       temb_channels=self.temb_ch,
+                                       dropout=dropout)
+
+        # upsampling
+        self.up = nn.ModuleList()
+        for i_level in reversed(range(self.num_resolutions)):
+            block = nn.ModuleList()
+            attn = nn.ModuleList()
+            block_out = ch*ch_mult[i_level]
+            for i_block in range(self.num_res_blocks+1):
+                block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+                if curr_res in attn_resolutions:
+                    attn.append(make_attn(block_in, attn_type=attn_type))
+            up = nn.Module()
+            up.block = block
+            up.attn = attn
+            if i_level != 0:
+                up.upsample = Upsample(block_in, resamp_with_conv)
+                curr_res = curr_res * 2
+            self.up.insert(0, up) # prepend to get consistent order
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        out_ch,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, z):
+        #assert z.shape[1:] == self.z_shape[1:]
+        self.last_z_shape = z.shape
+
+        # timestep embedding
+        temb = None
+
+        # z to block_in
+        h = self.conv_in(z)
+
+        # middle
+        h = self.mid.block_1(h, temb)
+        h = self.mid.attn_1(h)
+        h = self.mid.block_2(h, temb)
+
+        # upsampling
+        for i_level in reversed(range(self.num_resolutions)):
+            for i_block in range(self.num_res_blocks+1):
+                h = self.up[i_level].block[i_block](h, temb)
+                if len(self.up[i_level].attn) > 0:
+                    h = self.up[i_level].attn[i_block](h)
+            if i_level != 0:
+                h = self.up[i_level].upsample(h)
+
+        # end
+        if self.give_pre_end:
+            return h
+
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        if self.tanh_out:
+            h = torch.tanh(h)
+        return h
+
+
+class SimpleDecoder(nn.Module):
+    def __init__(self, in_channels, out_channels, *args, **kwargs):
+        super().__init__()
+        self.model = nn.ModuleList([nn.Conv2d(in_channels, in_channels, 1),
+                                     ResnetBlock(in_channels=in_channels,
+                                                 out_channels=2 * in_channels,
+                                                 temb_channels=0, dropout=0.0),
+                                     ResnetBlock(in_channels=2 * in_channels,
+                                                out_channels=4 * in_channels,
+                                                temb_channels=0, dropout=0.0),
+                                     ResnetBlock(in_channels=4 * in_channels,
+                                                out_channels=2 * in_channels,
+                                                temb_channels=0, dropout=0.0),
+                                     nn.Conv2d(2*in_channels, in_channels, 1),
+                                     Upsample(in_channels, with_conv=True)])
+        # end
+        self.norm_out = Normalize(in_channels)
+        self.conv_out = torch.nn.Conv2d(in_channels,
+                                        out_channels,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, x):
+        for i, layer in enumerate(self.model):
+            if i in [1,2,3]:
+                x = layer(x, None)
+            else:
+                x = layer(x)
+
+        h = self.norm_out(x)
+        h = nonlinearity(h)
+        x = self.conv_out(h)
+        return x
+
+
+class UpsampleDecoder(nn.Module):
+    def __init__(self, in_channels, out_channels, ch, num_res_blocks, resolution,
+                 ch_mult=(2,2), dropout=0.0):
+        super().__init__()
+        # upsampling
+        self.temb_ch = 0
+        self.num_resolutions = len(ch_mult)
+        self.num_res_blocks = num_res_blocks
+        block_in = in_channels
+        curr_res = resolution // 2 ** (self.num_resolutions - 1)
+        self.res_blocks = nn.ModuleList()
+        self.upsample_blocks = nn.ModuleList()
+        for i_level in range(self.num_resolutions):
+            res_block = []
+            block_out = ch * ch_mult[i_level]
+            for i_block in range(self.num_res_blocks + 1):
+                res_block.append(ResnetBlock(in_channels=block_in,
+                                         out_channels=block_out,
+                                         temb_channels=self.temb_ch,
+                                         dropout=dropout))
+                block_in = block_out
+            self.res_blocks.append(nn.ModuleList(res_block))
+            if i_level != self.num_resolutions - 1:
+                self.upsample_blocks.append(Upsample(block_in, True))
+                curr_res = curr_res * 2
+
+        # end
+        self.norm_out = Normalize(block_in)
+        self.conv_out = torch.nn.Conv2d(block_in,
+                                        out_channels,
+                                        kernel_size=3,
+                                        stride=1,
+                                        padding=1)
+
+    def forward(self, x):
+        # upsampling
+        h = x
+        for k, i_level in enumerate(range(self.num_resolutions)):
+            for i_block in range(self.num_res_blocks + 1):
+                h = self.res_blocks[i_level][i_block](h, None)
+            if i_level != self.num_resolutions - 1:
+                h = self.upsample_blocks[k](h)
+        h = self.norm_out(h)
+        h = nonlinearity(h)
+        h = self.conv_out(h)
+        return h
+
+
+class LatentRescaler(nn.Module):
+    def __init__(self, factor, in_channels, mid_channels, out_channels, depth=2):
+        super().__init__()
+        # residual block, interpolate, residual block
+        self.factor = factor
+        self.conv_in = nn.Conv2d(in_channels,
+                                 mid_channels,
+                                 kernel_size=3,
+                                 stride=1,
+                                 padding=1)
+        self.res_block1 = nn.ModuleList([ResnetBlock(in_channels=mid_channels,
+                                                     out_channels=mid_channels,
+                                                     temb_channels=0,
+                                                     dropout=0.0) for _ in range(depth)])
+        self.attn = AttnBlock(mid_channels)
+        self.res_block2 = nn.ModuleList([ResnetBlock(in_channels=mid_channels,
+                                                     out_channels=mid_channels,
+                                                     temb_channels=0,
+                                                     dropout=0.0) for _ in range(depth)])
+
+        self.conv_out = nn.Conv2d(mid_channels,
+                                  out_channels,
+                                  kernel_size=1,
+                                  )
+
+    def forward(self, x):
+        x = self.conv_in(x)
+        for block in self.res_block1:
+            x = block(x, None)
+        x = torch.nn.functional.interpolate(x, size=(int(round(x.shape[2]*self.factor)), int(round(x.shape[3]*self.factor))))
+        x = self.attn(x)
+        for block in self.res_block2:
+            x = block(x, None)
+        x = self.conv_out(x)
+        return x
+
+
+class MergedRescaleEncoder(nn.Module):
+    def __init__(self, in_channels, ch, resolution, out_ch, num_res_blocks,
+                 attn_resolutions, dropout=0.0, resamp_with_conv=True,
+                 ch_mult=(1,2,4,8), rescale_factor=1.0, rescale_module_depth=1):
+        super().__init__()
+        intermediate_chn = ch * ch_mult[-1]
+        self.encoder = Encoder(in_channels=in_channels, num_res_blocks=num_res_blocks, ch=ch, ch_mult=ch_mult,
+                               z_channels=intermediate_chn, double_z=False, resolution=resolution,
+                               attn_resolutions=attn_resolutions, dropout=dropout, resamp_with_conv=resamp_with_conv,
+                               out_ch=None)
+        self.rescaler = LatentRescaler(factor=rescale_factor, in_channels=intermediate_chn,
+                                       mid_channels=intermediate_chn, out_channels=out_ch, depth=rescale_module_depth)
+
+    def forward(self, x):
+        x = self.encoder(x)
+        x = self.rescaler(x)
+        return x
+
+
+class MergedRescaleDecoder(nn.Module):
+    def __init__(self, z_channels, out_ch, resolution, num_res_blocks, attn_resolutions, ch, ch_mult=(1,2,4,8),
+                 dropout=0.0, resamp_with_conv=True, rescale_factor=1.0, rescale_module_depth=1):
+        super().__init__()
+        tmp_chn = z_channels*ch_mult[-1]
+        self.decoder = Decoder(out_ch=out_ch, z_channels=tmp_chn, attn_resolutions=attn_resolutions, dropout=dropout,
+                               resamp_with_conv=resamp_with_conv, in_channels=None, num_res_blocks=num_res_blocks,
+                               ch_mult=ch_mult, resolution=resolution, ch=ch)
+        self.rescaler = LatentRescaler(factor=rescale_factor, in_channels=z_channels, mid_channels=tmp_chn,
+                                       out_channels=tmp_chn, depth=rescale_module_depth)
+
+    def forward(self, x):
+        x = self.rescaler(x)
+        x = self.decoder(x)
+        return x
+
+
+class Upsampler(nn.Module):
+    def __init__(self, in_size, out_size, in_channels, out_channels, ch_mult=2):
+        super().__init__()
+        assert out_size >= in_size
+        num_blocks = int(np.log2(out_size//in_size))+1
+        factor_up = 1.+ (out_size % in_size)
+        print(f"Building {self.__class__.__name__} with in_size: {in_size} --> out_size {out_size} and factor {factor_up}")
+        self.rescaler = LatentRescaler(factor=factor_up, in_channels=in_channels, mid_channels=2*in_channels,
+                                       out_channels=in_channels)
+        self.decoder = Decoder(out_ch=out_channels, resolution=out_size, z_channels=in_channels, num_res_blocks=2,
+                               attn_resolutions=[], in_channels=None, ch=in_channels,
+                               ch_mult=[ch_mult for _ in range(num_blocks)])
+
+    def forward(self, x):
+        x = self.rescaler(x)
+        x = self.decoder(x)
+        return x
+
+
+class Resize(nn.Module):
+    def __init__(self, in_channels=None, learned=False, mode="bilinear"):
+        super().__init__()
+        self.with_conv = learned
+        self.mode = mode
+        if self.with_conv:
+            print(f"Note: {self.__class__.__name} uses learned downsampling and will ignore the fixed {mode} mode")
+            raise NotImplementedError()
+            assert in_channels is not None
+            # no asymmetric padding in torch conv, must do it ourselves
+            self.conv = torch.nn.Conv2d(in_channels,
+                                        in_channels,
+                                        kernel_size=4,
+                                        stride=2,
+                                        padding=1)
+
+    def forward(self, x, scale_factor=1.0):
+        if scale_factor==1.0:
+            return x
+        else:
+            x = torch.nn.functional.interpolate(x, mode=self.mode, align_corners=False, scale_factor=scale_factor)
+        return x
+
+class FirstStagePostProcessor(nn.Module):
+
+    def __init__(self, ch_mult:list, in_channels,
+                 pretrained_model:nn.Module=None,
+                 reshape=False,
+                 n_channels=None,
+                 dropout=0.,
+                 pretrained_config=None):
+        super().__init__()
+        if pretrained_config is None:
+            assert pretrained_model is not None, 'Either "pretrained_model" or "pretrained_config" must not be None'
+            self.pretrained_model = pretrained_model
+        else:
+            assert pretrained_config is not None, 'Either "pretrained_model" or "pretrained_config" must not be None'
+            self.instantiate_pretrained(pretrained_config)
+
+        self.do_reshape = reshape
+
+        if n_channels is None:
+            n_channels = self.pretrained_model.encoder.ch
+
+        self.proj_norm = Normalize(in_channels,num_groups=in_channels//2)
+        self.proj = nn.Conv2d(in_channels,n_channels,kernel_size=3,
+                            stride=1,padding=1)
+
+        blocks = []
+        downs = []
+        ch_in = n_channels
+        for m in ch_mult:
+            blocks.append(ResnetBlock(in_channels=ch_in,out_channels=m*n_channels,dropout=dropout))
+            ch_in = m * n_channels
+            downs.append(Downsample(ch_in, with_conv=False))
+
+        self.model = nn.ModuleList(blocks)
+        self.downsampler = nn.ModuleList(downs)
+
+
+    def instantiate_pretrained(self, config):
+        model = instantiate_from_config(config)
+        self.pretrained_model = model.eval()
+        # self.pretrained_model.train = False
+        for param in self.pretrained_model.parameters():
+            param.requires_grad = False
+
+
+    @torch.no_grad()
+    def encode_with_pretrained(self,x):
+        c = self.pretrained_model.encode(x)
+        if isinstance(c, DiagonalGaussianDistribution):
+            c = c.mode()
+        return  c
+
+    def forward(self,x):
+        z_fs = self.encode_with_pretrained(x)
+        z = self.proj_norm(z_fs)
+        z = self.proj(z)
+        z = nonlinearity(z)
+
+        for submodel, downmodel in zip(self.model,self.downsampler):
+            z = submodel(z,temb=None)
+            z = downmodel(z)
+
+        if self.do_reshape:
+            z = rearrange(z,'b c h w -> b (h w) c')
+        return z
+

stable_diffusion/ldm/modules/diffusionmodules/openaimodel.py

@@ -0,0 +1,961 @@
+from abc import abstractmethod
+from functools import partial
+import math
+from typing import Iterable
+
+import numpy as np
+import torch as th
+import torch.nn as nn
+import torch.nn.functional as F
+
+from ldm.modules.diffusionmodules.util import (
+    checkpoint,
+    conv_nd,
+    linear,
+    avg_pool_nd,
+    zero_module,
+    normalization,
+    timestep_embedding,
+)
+from ldm.modules.attention import SpatialTransformer
+
+
+# dummy replace
+def convert_module_to_f16(x):
+    pass
+
+def convert_module_to_f32(x):
+    pass
+
+
+## go
+class AttentionPool2d(nn.Module):
+    """
+    Adapted from CLIP: https://github.com/openai/CLIP/blob/main/clip/model.py
+    """
+
+    def __init__(
+        self,
+        spacial_dim: int,
+        embed_dim: int,
+        num_heads_channels: int,
+        output_dim: int = None,
+    ):
+        super().__init__()
+        self.positional_embedding = nn.Parameter(th.randn(embed_dim, spacial_dim ** 2 + 1) / embed_dim ** 0.5)
+        self.qkv_proj = conv_nd(1, embed_dim, 3 * embed_dim, 1)
+        self.c_proj = conv_nd(1, embed_dim, output_dim or embed_dim, 1)
+        self.num_heads = embed_dim // num_heads_channels
+        self.attention = QKVAttention(self.num_heads)
+
+    def forward(self, x):
+        b, c, *_spatial = x.shape
+        x = x.reshape(b, c, -1)  # NC(HW)
+        x = th.cat([x.mean(dim=-1, keepdim=True), x], dim=-1)  # NC(HW+1)
+        x = x + self.positional_embedding[None, :, :].to(x.dtype)  # NC(HW+1)
+        x = self.qkv_proj(x)
+        x = self.attention(x)
+        x = self.c_proj(x)
+        return x[:, :, 0]
+
+
+class TimestepBlock(nn.Module):
+    """
+    Any module where forward() takes timestep embeddings as a second argument.
+    """
+
+    @abstractmethod
+    def forward(self, x, emb):
+        """
+        Apply the module to `x` given `emb` timestep embeddings.
+        """
+
+
+class TimestepEmbedSequential(nn.Sequential, TimestepBlock):
+    """
+    A sequential module that passes timestep embeddings to the children that
+    support it as an extra input.
+    """
+
+    def forward(self, x, emb, context=None):
+        for layer in self:
+            if isinstance(layer, TimestepBlock):
+                x = layer(x, emb)
+            elif isinstance(layer, SpatialTransformer):
+                x = layer(x, context)
+            else:
+                x = layer(x)
+        return x
+
+
+class Upsample(nn.Module):
+    """
+    An upsampling layer with an optional convolution.
+    :param channels: channels in the inputs and outputs.
+    :param use_conv: a bool determining if a convolution is applied.
+    :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
+                 upsampling occurs in the inner-two dimensions.
+    """
+
+    def __init__(self, channels, use_conv, dims=2, out_channels=None, padding=1):
+        super().__init__()
+        self.channels = channels
+        self.out_channels = out_channels or channels
+        self.use_conv = use_conv
+        self.dims = dims
+        if use_conv:
+            self.conv = conv_nd(dims, self.channels, self.out_channels, 3, padding=padding)
+
+    def forward(self, x):
+        assert x.shape[1] == self.channels
+        if self.dims == 3:
+            x = F.interpolate(
+                x, (x.shape[2], x.shape[3] * 2, x.shape[4] * 2), mode="nearest"
+            )
+        else:
+            x = F.interpolate(x, scale_factor=2, mode="nearest")
+        if self.use_conv:
+            x = self.conv(x)
+        return x
+
+class TransposedUpsample(nn.Module):
+    'Learned 2x upsampling without padding'
+    def __init__(self, channels, out_channels=None, ks=5):
+        super().__init__()
+        self.channels = channels
+        self.out_channels = out_channels or channels
+
+        self.up = nn.ConvTranspose2d(self.channels,self.out_channels,kernel_size=ks,stride=2)
+
+    def forward(self,x):
+        return self.up(x)
+
+
+class Downsample(nn.Module):
+    """
+    A downsampling layer with an optional convolution.
+    :param channels: channels in the inputs and outputs.
+    :param use_conv: a bool determining if a convolution is applied.
+    :param dims: determines if the signal is 1D, 2D, or 3D. If 3D, then
+                 downsampling occurs in the inner-two dimensions.
+    """
+
+    def __init__(self, channels, use_conv, dims=2, out_channels=None,padding=1):
+        super().__init__()
+        self.channels = channels
+        self.out_channels = out_channels or channels
+        self.use_conv = use_conv
+        self.dims = dims
+        stride = 2 if dims != 3 else (1, 2, 2)
+        if use_conv:
+            self.op = conv_nd(
+                dims, self.channels, self.out_channels, 3, stride=stride, padding=padding
+            )
+        else:
+            assert self.channels == self.out_channels
+            self.op = avg_pool_nd(dims, kernel_size=stride, stride=stride)
+
+    def forward(self, x):
+        assert x.shape[1] == self.channels
+        return self.op(x)
+
+
+class ResBlock(TimestepBlock):
+    """
+    A residual block that can optionally change the number of channels.
+    :param channels: the number of input channels.
+    :param emb_channels: the number of timestep embedding channels.
+    :param dropout: the rate of dropout.
+    :param out_channels: if specified, the number of out channels.
+    :param use_conv: if True and out_channels is specified, use a spatial
+        convolution instead of a smaller 1x1 convolution to change the
+        channels in the skip connection.
+    :param dims: determines if the signal is 1D, 2D, or 3D.
+    :param use_checkpoint: if True, use gradient checkpointing on this module.
+    :param up: if True, use this block for upsampling.
+    :param down: if True, use this block for downsampling.
+    """
+
+    def __init__(
+        self,
+        channels,
+        emb_channels,
+        dropout,
+        out_channels=None,
+        use_conv=False,
+        use_scale_shift_norm=False,
+        dims=2,
+        use_checkpoint=False,
+        up=False,
+        down=False,
+    ):
+        super().__init__()
+        self.channels = channels
+        self.emb_channels = emb_channels
+        self.dropout = dropout
+        self.out_channels = out_channels or channels
+        self.use_conv = use_conv
+        self.use_checkpoint = use_checkpoint
+        self.use_scale_shift_norm = use_scale_shift_norm
+
+        self.in_layers = nn.Sequential(
+            normalization(channels),
+            nn.SiLU(),
+            conv_nd(dims, channels, self.out_channels, 3, padding=1),
+        )
+
+        self.updown = up or down
+
+        if up:
+            self.h_upd = Upsample(channels, False, dims)
+            self.x_upd = Upsample(channels, False, dims)
+        elif down:
+            self.h_upd = Downsample(channels, False, dims)
+            self.x_upd = Downsample(channels, False, dims)
+        else:
+            self.h_upd = self.x_upd = nn.Identity()
+
+        self.emb_layers = nn.Sequential(
+            nn.SiLU(),
+            linear(
+                emb_channels,
+                2 * self.out_channels if use_scale_shift_norm else self.out_channels,
+            ),
+        )
+        self.out_layers = nn.Sequential(
+            normalization(self.out_channels),
+            nn.SiLU(),
+            nn.Dropout(p=dropout),
+            zero_module(
+                conv_nd(dims, self.out_channels, self.out_channels, 3, padding=1)
+            ),
+        )
+
+        if self.out_channels == channels:
+            self.skip_connection = nn.Identity()
+        elif use_conv:
+            self.skip_connection = conv_nd(
+                dims, channels, self.out_channels, 3, padding=1
+            )
+        else:
+            self.skip_connection = conv_nd(dims, channels, self.out_channels, 1)
+
+    def forward(self, x, emb):
+        """
+        Apply the block to a Tensor, conditioned on a timestep embedding.
+        :param x: an [N x C x ...] Tensor of features.
+        :param emb: an [N x emb_channels] Tensor of timestep embeddings.
+        :return: an [N x C x ...] Tensor of outputs.
+        """
+        return checkpoint(
+            self._forward, (x, emb), self.parameters(), self.use_checkpoint
+        )
+
+
+    def _forward(self, x, emb):
+        if self.updown:
+            in_rest, in_conv = self.in_layers[:-1], self.in_layers[-1]
+            h = in_rest(x)
+            h = self.h_upd(h)
+            x = self.x_upd(x)
+            h = in_conv(h)
+        else:
+            h = self.in_layers(x)
+        emb_out = self.emb_layers(emb).type(h.dtype)
+        while len(emb_out.shape) < len(h.shape):
+            emb_out = emb_out[..., None]
+        if self.use_scale_shift_norm:
+            out_norm, out_rest = self.out_layers[0], self.out_layers[1:]
+            scale, shift = th.chunk(emb_out, 2, dim=1)
+            h = out_norm(h) * (1 + scale) + shift
+            h = out_rest(h)
+        else:
+            h = h + emb_out
+            h = self.out_layers(h)
+        return self.skip_connection(x) + h
+
+
+class AttentionBlock(nn.Module):
+    """
+    An attention block that allows spatial positions to attend to each other.
+    Originally ported from here, but adapted to the N-d case.
+    https://github.com/hojonathanho/diffusion/blob/1e0dceb3b3495bbe19116a5e1b3596cd0706c543/diffusion_tf/models/unet.py#L66.
+    """
+
+    def __init__(
+        self,
+        channels,
+        num_heads=1,
+        num_head_channels=-1,
+        use_checkpoint=False,
+        use_new_attention_order=False,
+    ):
+        super().__init__()
+        self.channels = channels
+        if num_head_channels == -1:
+            self.num_heads = num_heads
+        else:
+            assert (
+                channels % num_head_channels == 0
+            ), f"q,k,v channels {channels} is not divisible by num_head_channels {num_head_channels}"
+            self.num_heads = channels // num_head_channels
+        self.use_checkpoint = use_checkpoint
+        self.norm = normalization(channels)
+        self.qkv = conv_nd(1, channels, channels * 3, 1)
+        if use_new_attention_order:
+            # split qkv before split heads
+            self.attention = QKVAttention(self.num_heads)
+        else:
+            # split heads before split qkv
+            self.attention = QKVAttentionLegacy(self.num_heads)
+
+        self.proj_out = zero_module(conv_nd(1, channels, channels, 1))
+
+    def forward(self, x):
+        return checkpoint(self._forward, (x,), self.parameters(), True)   # TODO: check checkpoint usage, is True # TODO: fix the .half call!!!
+        #return pt_checkpoint(self._forward, x)  # pytorch
+
+    def _forward(self, x):
+        b, c, *spatial = x.shape
+        x = x.reshape(b, c, -1)
+        qkv = self.qkv(self.norm(x))
+        h = self.attention(qkv)
+        h = self.proj_out(h)
+        return (x + h).reshape(b, c, *spatial)
+
+
+def count_flops_attn(model, _x, y):
+    """
+    A counter for the `thop` package to count the operations in an
+    attention operation.
+    Meant to be used like:
+        macs, params = thop.profile(
+            model,
+            inputs=(inputs, timestamps),
+            custom_ops={QKVAttention: QKVAttention.count_flops},
+        )
+    """
+    b, c, *spatial = y[0].shape
+    num_spatial = int(np.prod(spatial))
+    # We perform two matmuls with the same number of ops.
+    # The first computes the weight matrix, the second computes
+    # the combination of the value vectors.
+    matmul_ops = 2 * b * (num_spatial ** 2) * c
+    model.total_ops += th.DoubleTensor([matmul_ops])
+
+
+class QKVAttentionLegacy(nn.Module):
+    """
+    A module which performs QKV attention. Matches legacy QKVAttention + input/ouput heads shaping
+    """
+
+    def __init__(self, n_heads):
+        super().__init__()
+        self.n_heads = n_heads
+
+    def forward(self, qkv):
+        """
+        Apply QKV attention.
+        :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs.
+        :return: an [N x (H * C) x T] tensor after attention.
+        """
+        bs, width, length = qkv.shape
+        assert width % (3 * self.n_heads) == 0
+        ch = width // (3 * self.n_heads)
+        q, k, v = qkv.reshape(bs * self.n_heads, ch * 3, length).split(ch, dim=1)
+        scale = 1 / math.sqrt(math.sqrt(ch))
+        weight = th.einsum(
+            "bct,bcs->bts", q * scale, k * scale
+        )  # More stable with f16 than dividing afterwards
+        weight = th.softmax(weight.float(), dim=-1).type(weight.dtype)
+        a = th.einsum("bts,bcs->bct", weight, v)
+        return a.reshape(bs, -1, length)
+
+    @staticmethod
+    def count_flops(model, _x, y):
+        return count_flops_attn(model, _x, y)
+
+
+class QKVAttention(nn.Module):
+    """
+    A module which performs QKV attention and splits in a different order.
+    """
+
+    def __init__(self, n_heads):
+        super().__init__()
+        self.n_heads = n_heads
+
+    def forward(self, qkv):
+        """
+        Apply QKV attention.
+        :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs.
+        :return: an [N x (H * C) x T] tensor after attention.
+        """
+        bs, width, length = qkv.shape
+        assert width % (3 * self.n_heads) == 0
+        ch = width // (3 * self.n_heads)
+        q, k, v = qkv.chunk(3, dim=1)
+        scale = 1 / math.sqrt(math.sqrt(ch))
+        weight = th.einsum(
+            "bct,bcs->bts",
+            (q * scale).view(bs * self.n_heads, ch, length),
+            (k * scale).view(bs * self.n_heads, ch, length),
+        )  # More stable with f16 than dividing afterwards
+        weight = th.softmax(weight.float(), dim=-1).type(weight.dtype)
+        a = th.einsum("bts,bcs->bct", weight, v.reshape(bs * self.n_heads, ch, length))
+        return a.reshape(bs, -1, length)
+
+    @staticmethod
+    def count_flops(model, _x, y):
+        return count_flops_attn(model, _x, y)
+
+
+class UNetModel(nn.Module):
+    """
+    The full UNet model with attention and timestep embedding.
+    :param in_channels: channels in the input Tensor.
+    :param model_channels: base channel count for the model.
+    :param out_channels: channels in the output Tensor.
+    :param num_res_blocks: number of residual blocks per downsample.
+    :param attention_resolutions: a collection of downsample rates at which
+        attention will take place. May be a set, list, or tuple.
+        For example, if this contains 4, then at 4x downsampling, attention
+        will be used.
+    :param dropout: the dropout probability.
+    :param channel_mult: channel multiplier for each level of the UNet.
+    :param conv_resample: if True, use learned convolutions for upsampling and
+        downsampling.
+    :param dims: determines if the signal is 1D, 2D, or 3D.
+    :param num_classes: if specified (as an int), then this model will be
+        class-conditional with `num_classes` classes.
+    :param use_checkpoint: use gradient checkpointing to reduce memory usage.
+    :param num_heads: the number of attention heads in each attention layer.
+    :param num_heads_channels: if specified, ignore num_heads and instead use
+                               a fixed channel width per attention head.
+    :param num_heads_upsample: works with num_heads to set a different number
+                               of heads for upsampling. Deprecated.
+    :param use_scale_shift_norm: use a FiLM-like conditioning mechanism.
+    :param resblock_updown: use residual blocks for up/downsampling.
+    :param use_new_attention_order: use a different attention pattern for potentially
+                                    increased efficiency.
+    """
+
+    def __init__(
+        self,
+        image_size,
+        in_channels,
+        model_channels,
+        out_channels,
+        num_res_blocks,
+        attention_resolutions,
+        dropout=0,
+        channel_mult=(1, 2, 4, 8),
+        conv_resample=True,
+        dims=2,
+        num_classes=None,
+        use_checkpoint=False,
+        use_fp16=False,
+        num_heads=-1,
+        num_head_channels=-1,
+        num_heads_upsample=-1,
+        use_scale_shift_norm=False,
+        resblock_updown=False,
+        use_new_attention_order=False,
+        use_spatial_transformer=False,    # custom transformer support
+        transformer_depth=1,              # custom transformer support
+        context_dim=None,                 # custom transformer support
+        n_embed=None,                     # custom support for prediction of discrete ids into codebook of first stage vq model
+        legacy=True,
+    ):
+        super().__init__()
+        if use_spatial_transformer:
+            assert context_dim is not None, 'Fool!! You forgot to include the dimension of your cross-attention conditioning...'
+
+        if context_dim is not None:
+            assert use_spatial_transformer, 'Fool!! You forgot to use the spatial transformer for your cross-attention conditioning...'
+            from omegaconf.listconfig import ListConfig
+            if type(context_dim) == ListConfig:
+                context_dim = list(context_dim)
+
+        if num_heads_upsample == -1:
+            num_heads_upsample = num_heads
+
+        if num_heads == -1:
+            assert num_head_channels != -1, 'Either num_heads or num_head_channels has to be set'
+
+        if num_head_channels == -1:
+            assert num_heads != -1, 'Either num_heads or num_head_channels has to be set'
+
+        self.image_size = image_size
+        self.in_channels = in_channels
+        self.model_channels = model_channels
+        self.out_channels = out_channels
+        self.num_res_blocks = num_res_blocks
+        self.attention_resolutions = attention_resolutions
+        self.dropout = dropout
+        self.channel_mult = channel_mult
+        self.conv_resample = conv_resample
+        self.num_classes = num_classes
+        self.use_checkpoint = use_checkpoint
+        self.dtype = th.float16 if use_fp16 else th.float32
+        self.num_heads = num_heads
+        self.num_head_channels = num_head_channels
+        self.num_heads_upsample = num_heads_upsample
+        self.predict_codebook_ids = n_embed is not None
+
+        time_embed_dim = model_channels * 4
+        self.time_embed = nn.Sequential(
+            linear(model_channels, time_embed_dim),
+            nn.SiLU(),
+            linear(time_embed_dim, time_embed_dim),
+        )
+
+        if self.num_classes is not None:
+            self.label_emb = nn.Embedding(num_classes, time_embed_dim)
+
+        self.input_blocks = nn.ModuleList(
+            [
+                TimestepEmbedSequential(
+                    conv_nd(dims, in_channels, model_channels, 3, padding=1)
+                )
+            ]
+        )
+        self._feature_size = model_channels
+        input_block_chans = [model_channels]
+        ch = model_channels
+        ds = 1
+        for level, mult in enumerate(channel_mult):
+            for _ in range(num_res_blocks):
+                layers = [
+                    ResBlock(
+                        ch,
+                        time_embed_dim,
+                        dropout,
+                        out_channels=mult * model_channels,
+                        dims=dims,
+                        use_checkpoint=use_checkpoint,
+                        use_scale_shift_norm=use_scale_shift_norm,
+                    )
+                ]
+                ch = mult * model_channels
+                if ds in attention_resolutions:
+                    if num_head_channels == -1:
+                        dim_head = ch // num_heads
+                    else:
+                        num_heads = ch // num_head_channels
+                        dim_head = num_head_channels
+                    if legacy:
+                        #num_heads = 1
+                        dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
+                    layers.append(
+                        AttentionBlock(
+                            ch,
+                            use_checkpoint=use_checkpoint,
+                            num_heads=num_heads,
+                            num_head_channels=dim_head,
+                            use_new_attention_order=use_new_attention_order,
+                        ) if not use_spatial_transformer else SpatialTransformer(
+                            ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
+                        )
+                    )
+                self.input_blocks.append(TimestepEmbedSequential(*layers))
+                self._feature_size += ch
+                input_block_chans.append(ch)
+            if level != len(channel_mult) - 1:
+                out_ch = ch
+                self.input_blocks.append(
+                    TimestepEmbedSequential(
+                        ResBlock(
+                            ch,
+                            time_embed_dim,
+                            dropout,
+                            out_channels=out_ch,
+                            dims=dims,
+                            use_checkpoint=use_checkpoint,
+                            use_scale_shift_norm=use_scale_shift_norm,
+                            down=True,
+                        )
+                        if resblock_updown
+                        else Downsample(
+                            ch, conv_resample, dims=dims, out_channels=out_ch
+                        )
+                    )
+                )
+                ch = out_ch
+                input_block_chans.append(ch)
+                ds *= 2
+                self._feature_size += ch
+
+        if num_head_channels == -1:
+            dim_head = ch // num_heads
+        else:
+            num_heads = ch // num_head_channels
+            dim_head = num_head_channels
+        if legacy:
+            #num_heads = 1
+            dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
+        self.middle_block = TimestepEmbedSequential(
+            ResBlock(
+                ch,
+                time_embed_dim,
+                dropout,
+                dims=dims,
+                use_checkpoint=use_checkpoint,
+                use_scale_shift_norm=use_scale_shift_norm,
+            ),
+            AttentionBlock(
+                ch,
+                use_checkpoint=use_checkpoint,
+                num_heads=num_heads,
+                num_head_channels=dim_head,
+                use_new_attention_order=use_new_attention_order,
+            ) if not use_spatial_transformer else SpatialTransformer(
+                            ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
+                        ),
+            ResBlock(
+                ch,
+                time_embed_dim,
+                dropout,
+                dims=dims,
+                use_checkpoint=use_checkpoint,
+                use_scale_shift_norm=use_scale_shift_norm,
+            ),
+        )
+        self._feature_size += ch
+
+        self.output_blocks = nn.ModuleList([])
+        for level, mult in list(enumerate(channel_mult))[::-1]:
+            for i in range(num_res_blocks + 1):
+                ich = input_block_chans.pop()
+                layers = [
+                    ResBlock(
+                        ch + ich,
+                        time_embed_dim,
+                        dropout,
+                        out_channels=model_channels * mult,
+                        dims=dims,
+                        use_checkpoint=use_checkpoint,
+                        use_scale_shift_norm=use_scale_shift_norm,
+                    )
+                ]
+                ch = model_channels * mult
+                if ds in attention_resolutions:
+                    if num_head_channels == -1:
+                        dim_head = ch // num_heads
+                    else:
+                        num_heads = ch // num_head_channels
+                        dim_head = num_head_channels
+                    if legacy:
+                        #num_heads = 1
+                        dim_head = ch // num_heads if use_spatial_transformer else num_head_channels
+                    layers.append(
+                        AttentionBlock(
+                            ch,
+                            use_checkpoint=use_checkpoint,
+                            num_heads=num_heads_upsample,
+                            num_head_channels=dim_head,
+                            use_new_attention_order=use_new_attention_order,
+                        ) if not use_spatial_transformer else SpatialTransformer(
+                            ch, num_heads, dim_head, depth=transformer_depth, context_dim=context_dim
+                        )
+                    )
+                if level and i == num_res_blocks:
+                    out_ch = ch
+                    layers.append(
+                        ResBlock(
+                            ch,
+                            time_embed_dim,
+                            dropout,
+                            out_channels=out_ch,
+                            dims=dims,
+                            use_checkpoint=use_checkpoint,
+                            use_scale_shift_norm=use_scale_shift_norm,
+                            up=True,
+                        )
+                        if resblock_updown
+                        else Upsample(ch, conv_resample, dims=dims, out_channels=out_ch)
+                    )
+                    ds //= 2
+                self.output_blocks.append(TimestepEmbedSequential(*layers))
+                self._feature_size += ch
+
+        self.out = nn.Sequential(
+            normalization(ch),
+            nn.SiLU(),
+            zero_module(conv_nd(dims, model_channels, out_channels, 3, padding=1)),
+        )
+        if self.predict_codebook_ids:
+            self.id_predictor = nn.Sequential(
+            normalization(ch),
+            conv_nd(dims, model_channels, n_embed, 1),
+            #nn.LogSoftmax(dim=1)  # change to cross_entropy and produce non-normalized logits
+        )
+
+    def convert_to_fp16(self):
+        """
+        Convert the torso of the model to float16.
+        """
+        self.input_blocks.apply(convert_module_to_f16)
+        self.middle_block.apply(convert_module_to_f16)
+        self.output_blocks.apply(convert_module_to_f16)
+
+    def convert_to_fp32(self):
+        """
+        Convert the torso of the model to float32.
+        """
+        self.input_blocks.apply(convert_module_to_f32)
+        self.middle_block.apply(convert_module_to_f32)
+        self.output_blocks.apply(convert_module_to_f32)
+
+    def forward(self, x, timesteps=None, context=None, y=None,**kwargs):
+        """
+        Apply the model to an input batch.
+        :param x: an [N x C x ...] Tensor of inputs.
+        :param timesteps: a 1-D batch of timesteps.
+        :param context: conditioning plugged in via crossattn
+        :param y: an [N] Tensor of labels, if class-conditional.
+        :return: an [N x C x ...] Tensor of outputs.
+        """
+        assert (y is not None) == (
+            self.num_classes is not None
+        ), "must specify y if and only if the model is class-conditional"
+        hs = []
+        t_emb = timestep_embedding(timesteps, self.model_channels, repeat_only=False)
+        emb = self.time_embed(t_emb)
+
+        if self.num_classes is not None:
+            assert y.shape == (x.shape[0],)
+            emb = emb + self.label_emb(y)
+
+        h = x.type(self.dtype)
+        for module in self.input_blocks:
+            h = module(h, emb, context)
+            hs.append(h)
+        h = self.middle_block(h, emb, context)
+        for module in self.output_blocks:
+            h = th.cat([h, hs.pop()], dim=1)
+            h = module(h, emb, context)
+        h = h.type(x.dtype)
+        if self.predict_codebook_ids:
+            return self.id_predictor(h)
+        else:
+            return self.out(h)
+
+
+class EncoderUNetModel(nn.Module):
+    """
+    The half UNet model with attention and timestep embedding.
+    For usage, see UNet.
+    """
+
+    def __init__(
+        self,
+        image_size,
+        in_channels,
+        model_channels,
+        out_channels,
+        num_res_blocks,
+        attention_resolutions,
+        dropout=0,
+        channel_mult=(1, 2, 4, 8),
+        conv_resample=True,
+        dims=2,
+        use_checkpoint=False,
+        use_fp16=False,
+        num_heads=1,
+        num_head_channels=-1,
+        num_heads_upsample=-1,
+        use_scale_shift_norm=False,
+        resblock_updown=False,
+        use_new_attention_order=False,
+        pool="adaptive",
+        *args,
+        **kwargs
+    ):
+        super().__init__()
+
+        if num_heads_upsample == -1:
+            num_heads_upsample = num_heads
+
+        self.in_channels = in_channels
+        self.model_channels = model_channels
+        self.out_channels = out_channels
+        self.num_res_blocks = num_res_blocks
+        self.attention_resolutions = attention_resolutions
+        self.dropout = dropout
+        self.channel_mult = channel_mult
+        self.conv_resample = conv_resample
+        self.use_checkpoint = use_checkpoint
+        self.dtype = th.float16 if use_fp16 else th.float32
+        self.num_heads = num_heads
+        self.num_head_channels = num_head_channels
+        self.num_heads_upsample = num_heads_upsample
+
+        time_embed_dim = model_channels * 4
+        self.time_embed = nn.Sequential(
+            linear(model_channels, time_embed_dim),
+            nn.SiLU(),
+            linear(time_embed_dim, time_embed_dim),
+        )
+
+        self.input_blocks = nn.ModuleList(
+            [
+                TimestepEmbedSequential(
+                    conv_nd(dims, in_channels, model_channels, 3, padding=1)
+                )
+            ]
+        )
+        self._feature_size = model_channels
+        input_block_chans = [model_channels]
+        ch = model_channels
+        ds = 1
+        for level, mult in enumerate(channel_mult):
+            for _ in range(num_res_blocks):
+                layers = [
+                    ResBlock(
+                        ch,
+                        time_embed_dim,
+                        dropout,
+                        out_channels=mult * model_channels,
+                        dims=dims,
+                        use_checkpoint=use_checkpoint,
+                        use_scale_shift_norm=use_scale_shift_norm,
+                    )
+                ]
+                ch = mult * model_channels
+                if ds in attention_resolutions:
+                    layers.append(
+                        AttentionBlock(
+                            ch,
+                            use_checkpoint=use_checkpoint,
+                            num_heads=num_heads,
+                            num_head_channels=num_head_channels,
+                            use_new_attention_order=use_new_attention_order,
+                        )
+                    )
+                self.input_blocks.append(TimestepEmbedSequential(*layers))
+                self._feature_size += ch
+                input_block_chans.append(ch)
+            if level != len(channel_mult) - 1:
+                out_ch = ch
+                self.input_blocks.append(
+                    TimestepEmbedSequential(
+                        ResBlock(
+                            ch,
+                            time_embed_dim,
+                            dropout,
+                            out_channels=out_ch,
+                            dims=dims,
+                            use_checkpoint=use_checkpoint,
+                            use_scale_shift_norm=use_scale_shift_norm,
+                            down=True,
+                        )
+                        if resblock_updown
+                        else Downsample(
+                            ch, conv_resample, dims=dims, out_channels=out_ch
+                        )
+                    )
+                )
+                ch = out_ch
+                input_block_chans.append(ch)
+                ds *= 2
+                self._feature_size += ch
+
+        self.middle_block = TimestepEmbedSequential(
+            ResBlock(
+                ch,
+                time_embed_dim,
+                dropout,
+                dims=dims,
+                use_checkpoint=use_checkpoint,
+                use_scale_shift_norm=use_scale_shift_norm,
+            ),
+            AttentionBlock(
+                ch,
+                use_checkpoint=use_checkpoint,
+                num_heads=num_heads,
+                num_head_channels=num_head_channels,
+                use_new_attention_order=use_new_attention_order,
+            ),
+            ResBlock(
+                ch,
+                time_embed_dim,
+                dropout,
+                dims=dims,
+                use_checkpoint=use_checkpoint,
+                use_scale_shift_norm=use_scale_shift_norm,
+            ),
+        )
+        self._feature_size += ch
+        self.pool = pool
+        if pool == "adaptive":
+            self.out = nn.Sequential(
+                normalization(ch),
+                nn.SiLU(),
+                nn.AdaptiveAvgPool2d((1, 1)),
+                zero_module(conv_nd(dims, ch, out_channels, 1)),
+                nn.Flatten(),
+            )
+        elif pool == "attention":
+            assert num_head_channels != -1
+            self.out = nn.Sequential(
+                normalization(ch),
+                nn.SiLU(),
+                AttentionPool2d(
+                    (image_size // ds), ch, num_head_channels, out_channels
+                ),
+            )
+        elif pool == "spatial":
+            self.out = nn.Sequential(
+                nn.Linear(self._feature_size, 2048),
+                nn.ReLU(),
+                nn.Linear(2048, self.out_channels),
+            )
+        elif pool == "spatial_v2":
+            self.out = nn.Sequential(
+                nn.Linear(self._feature_size, 2048),
+                normalization(2048),
+                nn.SiLU(),
+                nn.Linear(2048, self.out_channels),
+            )
+        else:
+            raise NotImplementedError(f"Unexpected {pool} pooling")
+
+    def convert_to_fp16(self):
+        """
+        Convert the torso of the model to float16.
+        """
+        self.input_blocks.apply(convert_module_to_f16)
+        self.middle_block.apply(convert_module_to_f16)
+
+    def convert_to_fp32(self):
+        """
+        Convert the torso of the model to float32.
+        """
+        self.input_blocks.apply(convert_module_to_f32)
+        self.middle_block.apply(convert_module_to_f32)
+
+    def forward(self, x, timesteps):
+        """
+        Apply the model to an input batch.
+        :param x: an [N x C x ...] Tensor of inputs.
+        :param timesteps: a 1-D batch of timesteps.
+        :return: an [N x K] Tensor of outputs.
+        """
+        emb = self.time_embed(timestep_embedding(timesteps, self.model_channels))
+
+        results = []
+        h = x.type(self.dtype)
+        for module in self.input_blocks:
+            h = module(h, emb)
+            if self.pool.startswith("spatial"):
+                results.append(h.type(x.dtype).mean(dim=(2, 3)))
+        h = self.middle_block(h, emb)
+        if self.pool.startswith("spatial"):
+            results.append(h.type(x.dtype).mean(dim=(2, 3)))
+            h = th.cat(results, axis=-1)
+            return self.out(h)
+        else:
+            h = h.type(x.dtype)
+            return self.out(h)
+