lebellig/discrete-fm
Educational implementation of the Discrete Flow Matching paper
This project helps machine learning researchers and students understand how to generate new, realistic discrete images. It takes an input of an existing dataset of discrete images and applies a technique called Discrete Flow Matching to produce novel images that share the same characteristics as the input. This is ideal for those learning about advanced generative models.
133 stars. No commits in the last 6 months.
Use this if you are an AI researcher or student wanting to learn and experiment with discrete image generation techniques, specifically Discrete Flow Matching.
Not ideal if you need a production-ready solution for generating high-resolution images or working with continuous data types.
Stars
133
Forks
7
Language
Jupyter Notebook
License
—
Category
Last pushed
Aug 26, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/lebellig/discrete-fm"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AngeClementAkazan/Sequential-FeatureForestFlow
This repository contains the code source of the Heterogeneous Sequential Feature Forest Flow...
AlejandroMllo/action_flow_matching
Code for the paper "Action Flow Matching for Continual Robot Learning" presented at Robotics:...
dsgiitr/flux-watermarking
Official Implementation of the paper WMARK@ICLR Detection Limits and Statistical Separability of...
ericbill21/FOCUS
Official codebase for FOCUS: Optimal Control Meets Flow Matching: A Principled Route to...
lebellig/flow-matching
Annotated Flow Matching paper