UCSB-NLP-Chang/CoPaint

Implementation of paper 'Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models'

29
/ 100
Experimental

This tool helps you flawlessly fill in missing or damaged parts of an image, making it look complete and natural. You provide a partially visible image and a mask indicating the missing areas, and it intelligently generates the missing content, ensuring it blends seamlessly with the existing parts. This is ideal for graphic designers, photo retouchers, or anyone needing to restore or complete images with high visual quality.

No commits in the last 6 months.

Use this if you need to precisely fill in holes or remove unwanted objects from images, ensuring the added content matches the surrounding context without visible seams or inconsistencies.

Not ideal if you're looking for a simple, quick fix for minor imperfections or require real-time image processing for live feeds.

image-restoration photo-editing digital-art visual-content-creation computer-vision
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

77

Forks

8

Language

Python

License

Last pushed

Apr 03, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/UCSB-NLP-Chang/CoPaint"

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