https://github.com/martin-rizzo/tinyautoencoderconverter

Command-line tool to build VAEs and Transcoders (from Tiny AutoEncoders).
https://github.com/martin-rizzo/tinyautoencoderconverter

auto1111 comfyui flux stable-diffusion text2image transcoder txt2img vae

Last synced: 7 days ago
JSON representation

Command-line tool to build VAEs and Transcoders (from Tiny AutoEncoders).

• Host: GitHub
• URL: https://github.com/martin-rizzo/tinyautoencoderconverter
• Owner: martin-rizzo
• License: mit
• Created: 2024-11-26T15:31:10.000Z (25 days ago)
• Default Branch: master
• Last Pushed: 2024-12-13T20:49:32.000Z (8 days ago)
• Last Synced: 2024-12-13T21:27:32.014Z (8 days ago)
• Topics: auto1111, comfyui, flux, stable-diffusion, text2image, transcoder, txt2img, vae
• Language: Python
• Homepage:
• Size: 44.9 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        


# Tiny AutoEncoder Converter















**Tiny AutoEncoder Converter** is a command-line utility that converts Tiny AutoEncoders into comfyui-compatible Variational AutoEncoders (VAEs) and Transcoders.

## What are Tiny AutoEncoders?

Tiny AutoEncoders (TAEs) are highly optimized autoencoders that share the same latent space as Stable Diffusion and Flux VAEs.  This enables significantly faster and more resource-efficient image encoding and decoding.  These models were developed and trained by Ollin Boer Bohan, to whom I express my sincere gratitude. You can find Ollin's original implementation and pre-trained models in the [Tiny AutoEncoder Repository](https://github.com/madebyollin/taesd).

## Command-Line Tools

This project provides the following command-line conversion tools:

- `build_tiny_vae.py`: Generates a comfyui-compatible VAE model from a Tiny AutoEncoder.

- `build_tiny_transcoder.py`: Creates a transcoder enabling latent space conversion between different models (e.g., SDXL to SD).

## Installation and Usage

1. **Clone the Repository:**  

   First, you need to clone this repository to your local machine.

   ```bash

   git clone https://github.com/martin-rizzo/TinyAutoEncoderConverter.git

   ```

2. **Download Original Models:**  

   Navigate into the cloned directory and download the necessary models from Hugging Face.

   ```bash

   cd TinyAutoEncoderConverter

   wget https://huggingface.co/madebyollin/taef1/blob/main/diffusion_pytorch_model.safetensors -P original_taesd_models/taef1

   wget https://huggingface.co/madebyollin/taesd/blob/main/diffusion_pytorch_model.safetensors -P original_taesd_models/taesd

   wget https://huggingface.co/madebyollin/taesd3/blob/main/diffusion_pytorch_model.safetensors -P original_taesd_models/taesd3

   wget https://huggingface.co/madebyollin/taesdx/blob/main/diffusion_pytorch_model.safetensors -P original_taesd_models/taesdx   

   ```

4. **Run the Bash Script:**  

   Execute the `makeall.sh` script to generate.

   ```bash

   ./makeall.sh

   ```

## Output

When running the general `makeall.sh` script, it will generate several files with the following naming format:

- `tiny_vae_*.safetensors`: VAE models compatible with ComfyUI.

- `transcoder_from_*_to_*.safetensors`: Transcoder model files.

## License

**Copyright (c) 2024 Martin Rizzo**  

This project is licensed under the MIT license.  

Details can be found in the ["LICENSE"](LICENSE) file.

## Disclaimer

This tool is provided "as is" without any warranty. Use at your own risk.