YangLing0818/consistency_flow_matching

Official Implementation for "Consistency Flow Matching: Defining Straight Flows with Velocity Consistency"

35
/ 100
Emerging

This project provides an efficient method for generating high-quality images from random noise. By defining a direct path between noise and desired images, it allows for faster training and better visual outputs compared to other techniques. It's designed for researchers and practitioners working on advanced image synthesis.

260 stars. No commits in the last 6 months.

Use this if you need to generate realistic images from scratch with a focus on both speed of training and the quality of the generated output.

Not ideal if your primary goal is simple image manipulation or if you don't require high-fidelity generative modeling.

image-synthesis generative-AI computational-photography deep-learning AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 9 / 25

How are scores calculated?

Stars

260

Forks

10

Language

Python

License

MIT

Last pushed

Jan 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/YangLing0818/consistency_flow_matching"

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