MizuhoAOKI/jax_generative_models
Minimal JAX implementation unifying Diffusion and Flow Matching algorithms as alternative strategies for transporting data distributions.
This project helps researchers and machine learning engineers experiment with new generative AI models. It takes in existing datasets (like images or numerical distributions) and trains models to generate new, similar data. The primary users are those working on advancing or understanding generative AI techniques.
Use this if you are an AI researcher or machine learning engineer looking to implement, compare, or develop new generative models using JAX.
Not ideal if you are a practitioner looking for a ready-to-use application to generate specific content, as this is a research and development tool.
Stars
63
Forks
3
Language
Python
License
MIT
Category
Last pushed
Dec 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MizuhoAOKI/jax_generative_models"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.