flow-matching

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

[ICLR 2026] TangoFlux: Super Fast and Faithful Text to Audio Generation with Flow Matching

Multimodal RL training framework for diffusion & omni models

Implementation of π₀, the robotic foundation model architecture proposed by Physical Intelligence

Official implementation of AsymFlow, pi-Flow, GMFlow

[ECCV 2024, Oral] FMBoost: Boosting Latent Diffusion with Flow Matching

[ICLR 2025] Rectified Diffusion: Straightness Is Not Your Need

Annotated Flow Matching paper

[ICML 2025] Gaussian Mixture Flow Matching Models (GMFlow)

Educational implementation of the Discrete Flow Matching paper

The official repository for the paper "Optimal Flow Matching: Learning Straight Trajectories in Just One Step" (NeurIPS 2024)

🚀 [ICLR 2026] SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image Distillation

[ICML 2026] a unified reinforcement learning toolbox for joint RL on language models and diffusion models

This repository is the official code source of PPFlow: Target-Aware Peptide Design with Torsional Flow Matching (ICML2024)

[ICML 2025] 🧬 ReQFlow: Rectified Quaternion Flow for Efficient and High-Quality Protein Backbone Generation

Real-Time Streamable Generative Speech Restoration with Flow Matching

Implementation of the world model architecture for self driving out of Wayve

Official Code for GPIC: A Giant Permissive Image Corpus for Visual Generation

Toy-scale unified multimodal model experiments — encoder-free understanding & generation with Mixture-of-Transformers on MLX/Apple Silicon

Zero-shot voice cloning text-to-speech (TTS) with explicit emotion class conditioning built on F5-TTS