Skip to content

Potato Diffusion is a hands-on repository that demystifies diffusion models by building them from scratch using PyTorch. Dive into implementing core AI components like VAE, CLIP, and UNet with clean, modular, and easy-to-read code—perfect for learning through doing.

License

Notifications You must be signed in to change notification settings

6DEADSHOT9/Potato-Diffusion

Repository files navigation

What is this all about?

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.

Why This Matters

  • 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.

Quick Start

  1. Clone the repository:
    git clone https://github.com/your-username/potato-diffusion.git
  2. Install dependencies:
    cd potato-diffusion && pip install -r requirements.txt
  3. Run the project:
    python main.py

Contribute

Found an issue or have an idea? Open a pull request and help improve the project.

License

This project is licensed under the MIT License.

About

Potato Diffusion is a hands-on repository that demystifies diffusion models by building them from scratch using PyTorch. Dive into implementing core AI components like VAE, CLIP, and UNet with clean, modular, and easy-to-read code—perfect for learning through doing.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages