Welcome to Potato Diffusion—a no-nonsense dive into building a diffusion model from the ground up. This repository is all about implementing the core components—VAE, CLIP, and UNet—using PyTorch, with a focus on simplicity and transparency.
- Learn by Doing: Build everything from scratch to truly understand how diffusion models work.
- Core AI Components: Master the architecture behind VAE, CLIP, and UNet.
- Clean and Modular: Code that's easy to read, extend, and experiment with.
- Clone the repository:
git clone https://github.com/your-username/potato-diffusion.git
- Install dependencies:
cd potato-diffusion && pip install -r requirements.txt
- Run the project:
python main.py
Found an issue or have an idea? Open a pull request and help improve the project.
This project is licensed under the MIT License.