---
language:
- en
license_name: stabilityai-ai-community
license_link: LICENSE.md
library_name: diffusers
pipeline_tag: text-to-image
tags:
- text-to-image
base_model:
- suzushi/miso-diffusion-m-1.0
- stabilityai/stable-diffusion-3.5-medium
---
<div style="display: flex; justify-content: center; gap: 20px; margin-bottom: 20px;">
    <img src="demo1.png" width="400" />
    <img src="demo2.png" width="400" />
</div>


## Change in model behavior
Trained with brand new dataset this time, it might take some time or more epoch before 
the model can properly adapt, please be aware that some older prompts might degrade 
or create some artifact. 

## Version History
| Version | Base Training | Aesthetic Training | Total Epochs |
|---------|--------------|-------------------|--------------|
| alpha     | 250K images  | 0 images        | 1           |
| beta     | 160K images  | 0 images        | 3           |
| 1.0     | 600k images   | 0 images        | 2 + (3 from beta)    |
| 1.1     | 710k images   | 0 images | 5                   |
| 2.0     | 1.08M images   | 0 images | 5                   |
| 2.1     | 1.32M images  | 0 images      | 5               | 

## Training Methodology

Training is done on gh200 with 96gb vram, now that prior training shows 
decent results, I am slightly increasing learning rate.

Training setting: Adafactor with a batchsize of 40, lr_scheduler: cosine
SD3.5 Specific setting:
enable_scaled_pos_embed = true

pos_emb_random_crop_rate = 0.2

weighting_scheme = "flow"
learning_rate = 8e-6

learning_rate_te1 = 5e-6

learning_rate_te2 = 5e-6

Train Clip: true, Train t5xxl: false

## Support Me
At the moment training an epoch cost around 130 dollars. If you like my project please consider supporting me: https://ko-fi.com/suzushi2024

Lastly, huge thanks to meg who has been supporting this project, without him this project would not have been possible !