koi953215/NaRCan

[NeurIPS 2024] NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing

29
/ 100
Experimental

This tool helps video editors modify the style or content of specific elements within a video while maintaining a natural, consistent look. You provide a video, and it generates an editable "canonical image" that represents the core visual information. After you edit this image (e.g., using AI art tools), the system applies those changes back to your entire video, producing a new, stylized video. It's ideal for visual effects artists, content creators, or animators who need precise control over video aesthetics.

169 stars. No commits in the last 6 months.

Use this if you need to perform advanced stylistic edits or transformations on elements within a video and want to ensure visual consistency across all frames.

Not ideal if you're looking for simple, one-click video filters or basic cuts and transitions, as this tool is for more complex, AI-assisted visual effects workflows.

video-editing visual-effects content-creation animation stylized-video
No License Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 9 / 25

How are scores calculated?

Stars

169

Forks

8

Language

Python

License

Last pushed

Sep 05, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/koi953215/NaRCan"

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