garibida/cross-image-attention

Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

39
/ 100
Emerging

This tool helps creative professionals or visual artists combine the visual style of one image with the structure of another. You provide two images: one with the desired shape or layout (e.g., a cat's pose) and another with the desired look and feel (e.g., a painting style or a specific texture). The output is a new image where the first image's structure adopts the second image's appearance.

395 stars. No commits in the last 6 months.

Use this if you need to quickly generate new images that blend the composition of one photo with the artistic style or texture of another, without needing complex editing software or manual adjustments.

Not ideal if you need pixel-perfect accuracy or intricate, detailed modifications that require fine-grained control over individual elements, as this tool focuses on broader appearance transfer.

digital-art visual-design image-generation creative-workflows concept-art
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

395

Forks

27

Language

Python

License

MIT

Last pushed

May 05, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/garibida/cross-image-attention"

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