zhang-zx/AVID

This respository contains the code for the CVPR 2024 paper AVID: Any-Length Video Inpainting with Diffusion Model.

26
/ 100
Experimental

This tool helps video editors and content creators seamlessly remove unwanted objects or fill in missing areas within video footage. You provide a video, specify the region to change in the first frame, and describe the desired outcome with a text prompt. The output is an edited video where the specified area is intelligently inpainted, maintaining visual and temporal consistency across the entire clip.

177 stars. No commits in the last 6 months.

Use this if you need to erase objects, replace backgrounds, or repair damaged sections in videos of any length using a text description, and require the edits to flow smoothly over time.

Not ideal if you need to perform precise, frame-by-frame manual touch-ups or require extremely fine-grained control over individual pixels without text guidance.

video-editing content-creation visual-effects post-production media-repair
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

177

Forks

Language

License

MIT

Last pushed

Feb 27, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/zhang-zx/AVID"

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