Flow Matching Python Packages

rectified-flow-pytorch

Implementation of rectified flow and some of its followup research / improvements in Pytorch

f5-tts-mlx

Implementation of F5-TTS in MLX

transfusion-pytorch

Pytorch implementation of Transfusion, "Predict the Next Token and Diffuse Images with One Multi-Modal Model", from MetaAI

pi-zero-pytorch

π0 in Pytorch

gaia2-pytorch

Gaia2 - Pytorch

flowmatching-bdt

Flow Matching with BDTs

symupe

SyMuPe: Affective and Controllable Symbolic Music Performance (ACM MM '25, Outstanding Paper Award)

e2tts-mlx

Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS in MLX

gensbi-examples

Examples for the GenSBI library

gensbi

GenSBI is a library for Simulation-Based Inference using generative models in JAX.

mlx-e2-tts

Implementation of E2-TTS, "Embarrassingly Easy Fully Non-Autoregressive Zero-Shot TTS", in MLX

mintflow

Generation of disentangled microenvironment-induced and intrinsic gene expression vectors from spatial transcriptomics data

mixture-of-flows

This work introduces Flow Matching Mixture of Experts (FM-MoE), a framework that replaces conventional MLP experts with flow matching networks. Each expert learns a continuous transformation through an ordinary differential equation (ODE), enabling more expressive feature mappings while maintaining the computational efficiency of sparse experts

multicom-ligand

Comprehensive ensembling of protein-ligand structure and affinity prediction methods (CASP16)

inigen

Generation of disentangled microenvironment-induced and intrinsic gene expression vectors from spatial transcriptomics data