LituRout/RF-Inversion
Rectified Flow Inversion (RF-Inversion) - ICLR 2025
This tool helps creative professionals and artists easily modify images. You provide an existing image and a text description of the desired change, and it transforms the original image while preserving its core elements. It's designed for anyone working with digital imagery who needs to re-style or edit images based on textual prompts.
471 stars. No commits in the last 6 months.
Use this if you want to efficiently apply semantic edits or stylization to an image using simple text descriptions, without needing to manually create new content or use complex image manipulation software.
Not ideal if you need pixel-perfect photo retouching, require precise control over individual image elements, or are working with non-photographic data.
Stars
471
Forks
19
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 19, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/LituRout/RF-Inversion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
milad1378yz/MOTFM
Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality
OpenImagingLab/FlashVSR
[CVPR 2026] Towards Real-Time Diffusion-Based Streaming Video Super-Resolution — An efficient...
X-GenGroup/Flow-Factory
A unified framework for easy reinforcement learning in Flow-Matching models
fallenshock/FlowEdit
Official implementation of the paper: "FlowEdit: Inversion-Free Text-Based Editing Using...
haidog-yaqub/MeanFlow
Pytorch Implementation (unofficial) of the paper "Mean Flows for One-step Generative Modeling"...