kunheek/style-aware-discriminator

CVPR 2022 - Official PyTorch implementation of "A Style-Aware Discriminator for Controllable Image Translation"

42
/ 100
Emerging

This project helps graphic designers, digital artists, and marketing professionals transform images by applying diverse styles from one image to another. It takes an input image and a 'style reference' image, then intelligently combines their characteristics. The output is a new image where the content of the input image is rendered with the aesthetic properties (like time of day, weather, age, or textures) extracted from the style reference.

115 stars.

Use this if you need fine-grained, controllable style transfer to generate variations of existing images or create new visuals with specific aesthetic qualities.

Not ideal if you're looking for simple, pre-set image filters or don't require the advanced control over style attributes that this tool offers.

digital-art image-manipulation graphic-design visual-content-creation advertising-design
No Package No Dependents
Maintenance 6 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

115

Forks

8

Language

Python

License

MIT

Last pushed

Oct 28, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/kunheek/style-aware-discriminator"

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