mattroz/diffusion-ddpm

Implementation of "Denoising Diffusion Probabilistic Models", Ho et al., 2020

28
/ 100
Experimental

This project helps machine learning researchers and practitioners understand and implement Denoising Diffusion Probabilistic Models (DDPMs) for generating new images. It takes a collection of existing images and uses them to learn how to create novel, similar images. This is for users who want a clear, direct implementation of the original DDPM paper to study or build upon.

No commits in the last 6 months.

Use this if you are a machine learning researcher or student looking for a transparent and faithful PyTorch implementation of the original DDPM paper to understand the core architecture without complex abstractions.

Not ideal if you are an end-user seeking a ready-to-use application for creative image generation, or if you need the absolute latest, most performant diffusion model architectures.

image-generation machine-learning-research deep-learning-models generative-ai
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

33

Forks

5

Language

Python

License

Last pushed

Jan 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mattroz/diffusion-ddpm"

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