homerjed/sbgm

Score-based Diffusion models in JAX.

42
/ 100
Emerging

This project helps machine learning researchers implement and extend score-based diffusion models. It takes in existing datasets (like images) and outputs new, similar data samples or calculated data likelihoods. Researchers working with generative models for complex data like images would use this to experiment with diffusion model architectures and training.

Available on PyPI.

Use this if you are a machine learning researcher or practitioner looking to build, train, and experiment with score-based diffusion models for generating data or estimating likelihoods.

Not ideal if you need an out-of-the-box solution for generating data without needing to understand or customize the underlying diffusion model architecture.

generative-modeling deep-learning-research image-synthesis data-simulation stochastic-processes
Maintenance 6 / 25
Adoption 6 / 25
Maturity 25 / 25
Community 5 / 25

How are scores calculated?

Stars

18

Forks

1

Language

Python

License

MIT

Last pushed

Dec 29, 2025

Commits (30d)

0

Dependencies

16

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/homerjed/sbgm"

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