Animadversio/DiffusionFromScratch

Rebuild the Stable Diffusion Model in a single python script. Tutorial for Harvard ML from Scratch Series

29
/ 100
Experimental

This project helps machine learning practitioners understand the inner workings of Stable Diffusion by rebuilding the model from scratch. You can input standard image datasets like MNIST or CelebA and output your own generated images, observing how each component contributes to the final result. It's designed for those learning about generative AI models.

224 stars. No commits in the last 6 months.

Use this if you are a machine learning student or researcher who wants to learn the fundamental architecture of Stable Diffusion models by implementing them yourself.

Not ideal if you're looking for a tool to apply Stable Diffusion for production-ready image generation or to simply use a pre-built model for creative tasks.

machine-learning-education generative-ai deep-learning-research model-architecture image-synthesis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

224

Forks

15

Language

Python

License

Last pushed

Jan 22, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Animadversio/DiffusionFromScratch"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.