Plain-AyI
← All projects
AI models & research

Denoising Diffusion Probabilistic Model, in Pytorch

Code that recreates diffusion models, the method behind many AI image generators, so you can train your own.

Research-backedNew this week

What it does

Diffusion models learn to make images by starting from random noise and cleaning it up step by step. This project is a PyTorch version of the research paper that made this method popular.

You can point it at a folder of images and train a model that then produces new images in a similar style. It also includes many later research ideas as optional add-ons.

Training takes many steps, so it is meant for people comfortable running machine learning experiments.

Who it's for

Researchers, students and developers who want to study or experiment with how AI image generation works.

Can I use it without coding?

Developers only. You write Python code to train and sample from models. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it