sooyeon-go/eye_for_an_eye

Eye-for-an-eye: Appearance Transfer with Semantic Correspondence in Diffusion Models

25
/ 100
Experimental

This tool helps you transfer the visual appearance (like colors and textures) from one image onto another, while preserving the second image's original structure. You provide a 'structure' image and an 'appearance' image, and the tool generates a new image where elements like a bird's wing or a car's wheel take on the colors from the corresponding part in the appearance image. This is ideal for artists, designers, or anyone needing to visually re-style existing images with precision.

Use this if you need to precisely repaint an object in an image using the color scheme and textures from a different image, ensuring that specific parts (like a head or a wing) maintain their original structure but adopt the appearance of their semantic counterparts.

Not ideal if you're looking for simple, broad image recoloring or style transfer that doesn't require precise semantic mapping between objects.

image-editing digital-art visual-design creative-imaging
No License No Package No Dependents
Maintenance 10 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

32

Forks

Language

Jupyter Notebook

License

Last pushed

Mar 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sooyeon-go/eye_for_an_eye"

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