moatifbutt/color-peel

we propose to generate a series of geometric shapes with target colors to disentangle (or peel off ) the target colors from the shapes. By jointly learning on multiple color-shape images, we found that the method can successfully disentangle the color and shape concepts.

27
/ 100
Experimental

This tool helps researchers and developers in computer vision generate basic 2D or 3D geometric shapes with precise target colors. By providing RGB color triplets or color coordinates, it creates images of these shapes, which helps in separating color and shape concepts in image generation models. It's designed for those working on fine-tuning how AI models understand and apply specific colors.

No commits in the last 6 months.

Use this if you are developing or experimenting with diffusion models and need a way to specifically train models to understand and reproduce colors accurately, independent of shape.

Not ideal if you are a general user looking for a tool to generate complex images or apply colors to existing photographs.

computer-vision diffusion-models AI-image-generation color-science machine-learning-research
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

68

Forks

7

Language

Python

License

Last pushed

Oct 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/moatifbutt/color-peel"

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