Metadata-Version: 2.1
Name: stablefused
Version: 0.1.2
Summary: StableFused
Home-page: UNKNOWN
Author: Aryan V S
Author-email: contact.aryanvs+stablefused@gmail.com
License: MIT
Platform: UNKNOWN
Requires-Python: >=3.6.0
Description-Content-Type: text/markdown
Provides-Extra: dev
License-File: LICENSE

# StableFused

StableFused is a toy library to experiment with Stable Diffusion inspired by 🤗 diffusers and various other sources!

## Installation

For usage, install the package from PyPI.

```bash
pip install stablefused
```

For development, fork the repository, clone it and install the package in editable mode.

```bash
git clone https://github.com/<YOUR_USERNAME>/stablefused.git
cd stablefused
pip install -e ".[dev]"
```

## Usage

Checkout the [examples](./examples) folder for notebooks 🥰

## Contributing

Contributions are welcome! Note that this project is not a serious implementation for training/inference/fine-tuning diffusion models. It is a toy library. I am working on it for fun and experimentation purposes (and because I'm too stupid to modify large codebases and understand what's going on).

As I'm not an expert in this field, I will have probably made a lot of mistakes. If you find any, please open an issue or a PR. I'll be happy to learn from you!

## Acknowledgements

The following sources have been very helpful in helping me understand Stable Diffusion. I highly recommend you to check them out!

- [🤗 diffusers](https://github.com/huggingface/diffusers)
- [Karpathy's gist on latent walking](https://gist.github.com/karpathy/00103b0037c5aaea32fe1da1af553355)
- [Nateraw's stable-diffusion-videos](https://github.com/nateraw/stable-diffusion-videos)
- [🤗 Annotated Diffusion Blog](https://huggingface.co/blog/annotated-diffusion)
- [Keras CV](https://github.com/keras-team/keras-cv)
- [Lillian Weng's Blogs](https://lilianweng.github.io/)
- [Emilio Dorigatti's Blogs](https://e-dorigatti.github.io/)
- [The AI Summer Diffusion Models Blog](https://theaisummer.com/diffusion-models/)

## Results

#### Visualization of diffusion process

These results are generated using the [text_to_image](https://github.com/a-r-r-o-w/stablefused/blob/main/examples/text_to_image_diffusion.ipynb) notebook. Refer to the notebook for more details and enjoy the denoising process!

<div align="center">
  <video src="https://github.com/a-r-r-o-w/stablefused/assets/72266394/9528329d-ddc4-461e-9664-cbab3eb97123" />
</div>


