MurrellGroup/Flowfusion.jl

Unifying flow matching and diffusion on Riemannian manifolds and discrete spaces, for generative deep learning.

45
/ 100
Emerging

This is a Julia package designed for machine learning researchers and practitioners working with generative deep learning. It helps you build and train models that can generate new data points by learning how to transform one distribution into another. You provide starting and ending data distributions, and the tool helps create a model that can generate diverse, high-quality samples matching the target distribution, even across complex data types like continuous, discrete, or manifold data.

Use this if you are a machine learning researcher or deep learning practitioner who needs to generate synthetic data, fill in missing data, or explore complex data transformations across various data structures, including those on geometric manifolds.

Not ideal if you are looking for a pre-trained, out-of-the-box generative model for common tasks, or if you are not comfortable with deep learning model development in Julia.

generative-modeling deep-learning manifold-learning data-synthesis machine-learning-research
No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

38

Forks

5

Language

Julia

License

MIT

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/MurrellGroup/Flowfusion.jl"

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