Upload folder using huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+license: mit
+language:
+- en
+pipeline_tag: image-to-image
+tags:
+- pytorch
+- robotics
+library_name: diffusers
+base_model:
+- timbrooks/instruct-pix2pix
+---
+
+<h1> UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations</h1>
+<p>
+<a href="https://kimhanjung.github.io/UniSkill">Website</a>&nbsp | &nbsp <a href="https://arxiv.org/abs/">Paper</a>&nbsp | &nbsp <a href="https://github.com/KimHanjung/UniSkill">Github</a> &nbsp 
+<br>
+
+- UniSkill is a universal skill representation learning approach that enables the use of large-scale video data by removing the need for labels or any form of alignment constraints.
+
+- UniSkill shows effective human-to-robot and robot-to-robot imitation in both simulation and real-world experiments through its embodiment-agnostic skill representation.
+
+## Model Summary
+
+- **Developed by:** Yonsei University 
+- **Model type:** image generation (language, image => robot actions)
+- **License:** MIT
+- **Finetuned from:** [`InstructPix2Pix`](https://huggingface.co/timbrooks/instruct-pix2pix)
+- **Website:** https://kimhanjung.github.io/UniSkill/
+- **Paper:** https://arxiv.org/abs/
+- **Code:** https://github.com/KimHanjung/UniSkill
+
+### Uses
+
+UniSkill is designed to learn cross-embodiment skill representations from large-scale human and robot video datasets. Its embodiment-agnostic skill representations can be used in various ways, such as training policies and generating sub-goal images.
+
+
+## License
+The model is licensed under the [MIT license](./LICENSE).

UniSkill_final_weight/.gitattributes

@@ -0,0 +1,2 @@
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text

UniSkill_final_weight/idm.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50db59970ea8c523165da669967f94d03a13618d193c1d70c0d6415cc630f8ba
+size 80338210

UniSkill_final_weight/unet/config.json

@@ -0,0 +1,68 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.30.2",
+  "_name_or_path": "timbrooks/instruct-pix2pix",
+  "act_fn": "silu",
+  "addition_embed_type": null,
+  "addition_embed_type_num_heads": 64,
+  "addition_time_embed_dim": null,
+  "attention_head_dim": 8,
+  "attention_type": "default",
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "class_embed_type": null,
+  "class_embeddings_concat": false,
+  "conv_in_kernel": 3,
+  "conv_out_kernel": 3,
+  "cross_attention_dim": 768,
+  "cross_attention_norm": null,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dropout": 0.0,
+  "dual_cross_attention": false,
+  "encoder_hid_dim": null,
+  "encoder_hid_dim_type": null,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 8,
+  "layers_per_block": 2,
+  "mid_block_only_cross_attention": null,
+  "mid_block_scale_factor": 1,
+  "mid_block_type": "UNetMidBlock2DCrossAttn",
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "num_attention_heads": null,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "projection_class_embeddings_input_dim": null,
+  "resnet_out_scale_factor": 1.0,
+  "resnet_skip_time_act": false,
+  "resnet_time_scale_shift": "default",
+  "reverse_transformer_layers_per_block": null,
+  "sample_size": 64,
+  "time_cond_proj_dim": null,
+  "time_embedding_act_fn": null,
+  "time_embedding_dim": null,
+  "time_embedding_type": "positional",
+  "timestep_post_act": null,
+  "transformer_layers_per_block": 1,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

UniSkill_final_weight/unet/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b80622ee6c5038079df0f6d0aaadad654aec4f56bf0c691810c2dd1d76589bf
+size 3438213624