gmongaras/Diffusion_models_from_scratch

Creating a diffusion model from scratch in PyTorch to learn exactly how they work.

40
/ 100
Emerging

This project helps researchers and machine learning practitioners understand and implement diffusion models for image generation. It provides a toolkit to train new models using existing image datasets like ImageNet, or to use pre-trained models to generate novel 64x64 images. The end user is typically an AI researcher, data scientist, or machine learning engineer exploring generative AI.

394 stars. No commits in the last 6 months.

Use this if you are a researcher or engineer looking to dive deep into the mechanics of diffusion models and want to build, train, or experiment with various architectures for generating images.

Not ideal if you need a user-friendly application for generating high-resolution images immediately, as this project focuses on the foundational implementation details and smaller image sizes.

Generative AI Image Synthesis Machine Learning Research Deep Learning Models Computer Vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

394

Forks

30

Language

Python

License

MIT

Last pushed

Apr 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/gmongaras/Diffusion_models_from_scratch"

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