RQ-Wu/LAMP

[CVPR 2024] | LAMP: Learn a Motion Pattern for Few-Shot Based Video Generation

36
/ 100
Emerging

This project helps video creators, marketers, or artists generate new videos with specific motions using minimal examples. You provide a few short videos demonstrating a desired motion (like a horse running or a person smiling) and a text description, and it produces new videos applying that motion to different subjects or scenes. The ideal user is someone who needs to create custom video content but lacks extensive motion capture data or wants to iterate on motion styles quickly.

283 stars. No commits in the last 6 months.

Use this if you need to generate short video clips with a particular learned motion, using only a handful of example videos and a text prompt to guide the output.

Not ideal if you need to generate very long videos, precise control over individual frames, or complex, multi-stage actions beyond a single learned motion pattern.

video-creation motion-graphics content-generation digital-art short-form-video
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 10 / 25

How are scores calculated?

Stars

283

Forks

13

Language

Python

License

Last pushed

Apr 22, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/RQ-Wu/LAMP"

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