snap-research/MoCoGAN-HD

[ICLR 2021 Spotlight] A Good Image Generator Is What You Need for High-Resolution Video Synthesis

41
/ 100
Emerging

This project helps researchers and creative professionals generate high-resolution videos from existing images or a different video's motion. You provide a collection of images (like faces or animals) and optionally a video to extract motion from. The output is a new, high-quality video synthesizing the appearance of your images with the motion from the input video, or generating motion within the same image domain. This tool is ideal for academic researchers and media professionals exploring advanced video generation.

246 stars. No commits in the last 6 months.

Use this if you need to create realistic, high-resolution videos by combining static images with motion from either the same domain or a completely different type of video.

Not ideal if you're looking for a simple, off-the-shelf video editing tool or want to generate abstract animations without specific image or motion inputs.

video generation digital media creation computer vision research visual effects synthetic media
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

246

Forks

25

Language

Python

License

Last pushed

Feb 04, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/snap-research/MoCoGAN-HD"

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