lixiaowen-xw/DiffuEraser

DiffuEraser is a diffusion model for video inpainting, which performs great content completeness and temporal consistency while maintaining acceptable efficiency.

45
/ 100
Emerging

This project helps video editors, content creators, and post-production specialists seamlessly remove unwanted objects, watermarks, or blemishes from videos. You provide a video and a mask indicating the areas to be removed, and it outputs a new video with those areas intelligently filled in, maintaining smooth, realistic motion and content. It's designed for anyone needing to clean up video footage with high visual quality and temporal consistency.

625 stars. No commits in the last 6 months.

Use this if you need to erase distracting elements from videos while ensuring the repaired areas blend naturally and consistently across frames.

Not ideal if you are working with extremely low-resolution video or if you require real-time processing on consumer-grade hardware.

video-editing post-production content-creation visual-effects media-restoration
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

625

Forks

59

Language

Python

License

Apache-2.0

Last pushed

Apr 17, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/lixiaowen-xw/DiffuEraser"

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