Omnihuman

Create OmniHuman audio-to-video tasks and helper tasks for human identification and subject-mask detection through RunAPI. Use when the user asks an agent to generate talking-head video from an image and audio file, identify human regions, or detect subject masks with OmniHuman. Default to the RunAPI CLI for one-off calls; use SDKs only when integrating RunAPI into an app or backend.

runapi-ai Updated

File contents

runapi-ai/omnihuman commit 5aea214fa7

Frequently asked questions

npx get-skill add runapi-ai/omnihuman