lebellig/flow-matching
Annotated Flow Matching paper
Implements Flow Matching for generative modeling using optimal transport conditional vector fields, with equation-by-equation annotations matching the original paper for educational clarity. Leverages the Zuko package for ODE solving and sampling, enabling efficient training of continuous normalizing flows. Provides a pedagogical reference implementation that bridges the theoretical framework and practical code, consulting prior minimal implementations while maintaining paper notation for direct correlation.
229 stars. No commits in the last 6 months.
Stars
229
Forks
14
Language
Jupyter Notebook
License
—
Category
Last pushed
Sep 14, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/lebellig/flow-matching"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
IRedDragonICY/auraflow_rrf
Relativistic Resonant Flow (RRF) Sampler: A novel discretization method for Rectified Flow...
AlejandroMllo/action_flow_matching
Code for the paper "Action Flow Matching for Continual Robot Learning" presented at Robotics:...
AngeClementAkazan/Sequential-FeatureForestFlow
This repository contains the code source of the Heterogeneous Sequential Feature Forest Flow...
uhh-pd-ml/EPiC-FM
EPiC Flow Matching Implementation for Generating Jets as Point Clouds (https://arxiv.org/abs/2310.00049)
ericbill21/FOCUS
Official codebase for FOCUS: Optimal Control Meets Flow Matching: A Principled Route to...