aurelio-amerio/GenSBI

Generative Models for Simulation-Based Inference in JAX

40
/ 100
Emerging

Implements Optimal Transport Conditional Flow Matching and Diffusion Models for posterior inference when likelihoods are intractable. Built on JAX and Flax NNX with support for CPUs, GPUs, and TPUs, it includes pre-built transformer architectures (Flux1, Simformer) and a high-level recipes API for streamlined training and sampling workflows.

Available on PyPI.

Maintenance 13 / 25
Adoption 9 / 25
Maturity 18 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Python

License

Last pushed

Mar 16, 2026

Monthly downloads

128

Commits (30d)

0

Dependencies

17

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/aurelio-amerio/GenSBI"

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