HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing

[ICML2025] An 8-step inversion and 8-step editing process works effectively with the FLUX-dev model. (3x speedup with results that are comparable or even superior to baseline methods)

40
/ 100
Emerging

This project helps graphic designers, digital artists, and marketers quickly and efficiently edit images by modifying their style, adding new elements, or replacing existing ones. You provide an original image and a text prompt describing the desired changes, and the tool generates a new, semantically edited image. This is ideal for anyone needing rapid, high-quality image manipulation without complex manual editing.

287 stars. No commits in the last 6 months.

Use this if you need to quickly re-style images, add or replace objects, or make other semantic edits with text prompts, especially if you prioritize speed and quality.

Not ideal if you require pixel-perfect precision for minute details or if your workflow does not involve text-to-image semantic editing.

digital-art graphic-design image-editing creative-marketing visual-content
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

287

Forks

17

Language

Python

License

Apache-2.0

Last pushed

May 01, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HolmesShuan/FireFlow-Fast-Inversion-of-Rectified-Flow-for-Image-Semantic-Editing"

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