snap-research/MMVID

[CVPR 2022] Show Me What and Tell Me How: Video Synthesis via Multimodal Conditioning

42
/ 100
Emerging

This project helps create short videos of people speaking, based on text descriptions and other cues. You input text describing what you want the video to show, and optionally provide images, drawings, or masks to guide the visual content. The output is a generated video that aligns with your input. This is useful for researchers in generative AI, computer graphics, or multimedia content creation.

192 stars. No commits in the last 6 months.

Use this if you need to generate video clips of people from various forms of input, such as descriptive text, sketches, or reference images.

Not ideal if you're looking for a user-friendly application to produce polished, high-quality videos for commercial use without programming expertise.

generative-AI video-synthesis computer-graphics multimedia-content-creation AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

192

Forks

23

Language

Python

License

Last pushed

Jun 16, 2022

Commits (30d)

0

Get this data via API

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

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