gcorso/particle-guidance

Implementation of Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

23
/ 100
Experimental

This project helps image creators and computational chemists generate a diverse range of high-quality outputs from diffusion models, rather than many similar ones. For image generation, you input a text prompt and get back a diverse set of images. For chemistry, you input a molecule's SMILES string and receive a more accurate and diverse set of 3D molecular structures (conformers). This is useful for anyone needing variety in AI-generated images or precise molecular shapes for drug discovery.

No commits in the last 6 months.

Use this if you need to generate a truly diverse set of images from text prompts or a wider, more accurate range of 3D molecular structures for chemical research.

Not ideal if your primary goal is to generate single, highly specific images or molecular conformers without emphasis on diversity, or if you don't use diffusion models.

generative-AI image-generation computational-chemistry drug-discovery molecular-modeling
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

78

Forks

3

Language

Python

License

Last pushed

Oct 23, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/gcorso/particle-guidance"

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