NTUYWANG103/GenColor

[NeurIPS 2025 (Spotlight)] Official PyTorch Implementation of Paper "GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation"

19
/ 100
Experimental

This project helps photographers, designers, or anyone working with images to enhance their colors while ensuring all fine details, like text or textures, remain perfectly clear and unchanged. You provide an image that needs color adjustment and a reference image with the desired color style. The tool then outputs a new image with enhanced colors, but with pixel-perfect preservation of all original textures and details.

Use this if you need to dramatically improve the colors of an image without introducing any blurriness or distortion to critical details like text, logos, or intricate patterns.

Not ideal if you're looking for a simple, automated 'one-click fix' for general image brightness or contrast, or if precise texture preservation is not a primary concern.

photography graphic-design image-editing digital-restoration visual-content-creation
No License No Package No Dependents
Maintenance 10 / 25
Adoption 4 / 25
Maturity 5 / 25
Community 0 / 25

How are scores calculated?

Stars

8

Forks

Language

Jupyter Notebook

License

Last pushed

Jan 23, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/NTUYWANG103/GenColor"

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