mdsrqbl/omnihuman

AI model that understands text & humanoids.

58
/ 100
Established

OmniHuman helps creative professionals and researchers generate video content from text instructions. You provide a text description of an action and an initial image or video of a humanoid figure, and it outputs a new video showing the humanoid performing that action. This tool is for animators, content creators, or AI researchers working with human-computer interaction.

134 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to generate realistic video sequences of humanoids performing actions based on text descriptions or existing visual content.

Not ideal if you need to generate videos of non-human subjects or require highly detailed, custom character animations without an initial visual reference.

video-generation animation human-computer-interaction content-creation visual-storytelling
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 21 / 25

How are scores calculated?

Stars

134

Forks

35

Language

Python

License

Apache-2.0

Last pushed

May 17, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/mdsrqbl/omnihuman"

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