cvondrick/videogan

Generating Videos with Scene Dynamics. NIPS 2016.

43
/ 100
Emerging

This project helps researchers and artists create short, dynamic video clips from scratch. By training the system on existing videos of a specific scene type (like a beach or a golf course), it learns to generate new, unique video sequences that show realistic motion for that scene. The output is a tiny video, 'hallucinated' by the model, which can be used for creative projects or studying generative models. This tool is for researchers and creatives exploring synthetic video generation.

713 stars. No commits in the last 6 months.

Use this if you need to generate short, artificial video clips that mimic the realistic motions of a specific environment or action.

Not ideal if you need to generate photorealistic, high-resolution, or long videos, or if you require precise control over the generated content.

generative-art video-synthesis motion-capture-research creative-media AI-art
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 25 / 25

How are scores calculated?

Stars

713

Forks

141

Language

Lua

License

Last pushed

May 03, 2018

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/cvondrick/videogan"

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