Seedance 2.0 is here - create consistent, multimodal AI videos faster with images, videos, and audio in one prompt.

Try Now
Skip to main content
Available now on ModelsLab · Video Generation

OmnihumanOmnihuman Animates Humans

Build Videos From Inputs

Image + Audio

Lip-Synced Realism

Pairs single human image with audio for precise lip-sync and emotion-matched motion.

Any Aspect Ratio

Portrait to Full-Body

Handles portrait, half-body, full-body images in varied ratios with consistent quality.

Multimodal Control

Audio Drives Motion

Uses audio signals for natural expressions, body language, and scene dynamics.

Examples

See what Omnihuman can create

Copy any prompt below and try it yourself in the playground.

Cityscape Talk

Professional man in suit stands in bustling city street at dusk, speaking energetically about urban innovation, realistic lighting, dynamic camera pan, high detail textures.

Product Demo

Engineer holds sleek gadget in modern lab, explains features with precise gestures, bright overhead lights, subtle background tech displays, sharp focus.

Nature Guide

Hiker in forest clearing describes trail map, natural arm movements synced to audio, dappled sunlight through trees, realistic fabric textures.

Abstract Art

Stylized figure in geometric studio dances to rhythm, fluid morphing forms, vibrant color shifts, continuous motion with soft glows.

For Developers

A few lines of code.
Video from image, audio.

ModelsLab handles the infrastructure: fast inference, auto-scaling, and a developer-friendly API. No GPU management needed.

  • Serverless: scales to zero, scales to millions
  • Pay per second, no minimums
  • Python and JavaScript SDKs, plus REST API
import requests
response = requests.post(
"https://modelslab.com/api/v7/video-fusion/image-to-video",
json={
"key": "YOUR_API_KEY",
"init_audio": "https://assets.modelslab.ai/generations/efc19902-2b68-4dac-aa8a-b84960651790",
"init_image": "https://assets.modelslab.ai/generations/18011592-127a-4d6e-adf7-c66d1ce7693c"
}
)
print(response.json())

FAQ

Common questions about Omnihuman

Read the docs

Ready to create?

Start generating with Omnihuman on ModelsLab.