KemingWu/HybridLayout

[ICCV 2025] Hybrid Layout Control for Diffusion Transformer: Fewer Annotations, Superior Aesthetics.

19
/ 100
Experimental

This project helps designers, artists, and marketers generate high-quality images with precise control over the placement and composition of elements. You provide text prompts and layout specifications, and it produces visually appealing images where objects are positioned exactly as desired, even with minimal initial input. It's ideal for anyone who needs to create consistent and aesthetically pleasing visual content efficiently.

Use this if you need to create visually appealing images with specific object placements and layouts, without needing extensive manual adjustments or detailed annotations.

Not ideal if you primarily need to generate free-form images without any particular layout constraints or if you prefer a system that requires exhaustive annotation for every detail.

generative-design digital-art visual-content-creation graphic-design marketing-visuals
No License No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 7 / 25
Community 0 / 25

How are scores calculated?

Stars

18

Forks

Language

Jupyter Notebook

License

Last pushed

Oct 23, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/KemingWu/HybridLayout"

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