VSAnimator/collage-diffusion

Implementation of Collage Diffusion (https://arxiv.org/abs/2303.00262)

21
/ 100
Experimental

This tool helps designers and digital artists create complex, multi-layered images by generating different elements separately and then combining them. You provide text descriptions for each desired image layer and then arrange them like a collage to produce a final, coherent image. It's ideal for anyone creating visual assets or concept art who needs precise control over individual components within a generated image.

No commits in the last 6 months.

Use this if you need to generate images with multiple distinct objects or scenes that interact in a specific, layered way.

Not ideal if you just need a simple, single-subject image generated from a single text prompt.

digital-art graphic-design concept-art image-generation visual-asset-creation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

38

Forks

2

Language

Jupyter Notebook

License

Last pushed

May 29, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/VSAnimator/collage-diffusion"

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