HyeonHo99/Video-Motion-Customization

VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models (CVPR 2024)

34
/ 100
Emerging

This project helps video creators, marketers, and artists transform existing video clips by applying new visual elements while preserving the original motion. You provide an input video and a text description, and it generates a new video where the described objects move exactly like those in your input. This is ideal for quickly generating diverse visual content with consistent motion.

198 stars. No commits in the last 6 months.

Use this if you need to create multiple video variations with different subjects but the same dynamic movement, or apply a specific artistic style to an existing video's motion.

Not ideal if you need to generate entirely new motions from scratch or perform detailed, frame-by-frame video editing.

video-generation motion-retargeting creative-content-production video-style-transfer digital-art
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

198

Forks

7

Language

Python

License

Apache-2.0

Last pushed

Mar 29, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/HyeonHo99/Video-Motion-Customization"

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