yuanzhi-zhu/OFTSR

[ICLR2026] "OFTSR: One-Step Flow for Image Super-Resolution with Tunable Fidelity-Realism Trade-offs"

25
/ 100
Experimental

This project helps image editors and graphic designers enhance the resolution of low-quality images to produce sharper, more detailed versions. It takes a blurry or pixelated image and outputs a high-resolution image, offering control over how realistic or faithful to the original the enhanced image appears. It's designed for professionals who need to quickly upgrade image quality for various visual applications.

Use this if you need to upscale images with a focus on balancing crisp details and a natural look, especially when dealing with varied image sources like portraits or general photography.

Not ideal if you primarily need to perform object detection or other image analysis tasks, as this tool focuses solely on image quality enhancement.

image-upscaling photo-enhancement graphic-design digital-art visual-media
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

39

Forks

Language

Python

License

Last pushed

Feb 07, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/yuanzhi-zhu/OFTSR"

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