mandt-lab/PSLD

Official Implementation of the paper: A Complete Recipe for Diffusion Generative Models

29
/ 100
Experimental

This project offers a comprehensive method for creating new diffusion generative models. It takes training image datasets (like CIFAR-10 or CelebA) and outputs high-quality synthetic images, outperforming existing models. This tool is designed for machine learning researchers and practitioners focused on generative AI and image synthesis.

No commits in the last 6 months.

Use this if you are an AI researcher or practitioner looking to develop advanced generative models for creating realistic images with improved sample quality and a principled approach to diffusion process design.

Not ideal if you are looking for a plug-and-play image generation tool without diving into model architecture and training configurations.

generative-ai image-synthesis diffusion-models machine-learning-research computer-vision
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

30

Forks

2

Language

Python

License

MIT

Last pushed

Nov 01, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mandt-lab/PSLD"

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