mahmoudnafifi/HistoGAN

Reference code for the paper HistoGAN: Controlling Colors of GAN-Generated and Real Images via Color Histograms (CVPR 2021).

41
/ 100
Emerging

This project helps graphic designers, photographers, and digital artists precisely control the color palette of images. You provide an image and a 'target' color profile (a color histogram), and it generates a new version of your image with those specific colors, while keeping the original content intact. This tool is for creative professionals who need fine-grained control over image color and style.

291 stars. No commits in the last 6 months.

Use this if you need to recolor existing images or generate new images with a specific, predefined color scheme, like matching brand guidelines or creating a consistent aesthetic across a series of visuals.

Not ideal if you're looking for simple color adjustments like brightness or contrast, or if your primary goal is general image enhancement without a specific target color profile.

graphic-design photo-editing digital-art color-grading visual-branding
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

291

Forks

29

Language

Jupyter Notebook

License

MIT

Last pushed

Feb 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/mahmoudnafifi/HistoGAN"

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