Bytedance/Omnihuman

omni-human

Omnihuman Image + Audio to VideoLLMs.txt

Generates hyper-realistic full-body videos from a single image and audio/video input using advanced diffusion transformers, supporting diverse styles, natural motion, and HD outputs up to 1024×1024 at 30fps.

API Playground API Documentation

API Endpoint URL

Base URL for all API requests to this endpoint.

https://modelslab.com/api/v7/video-fusion/image-to-video

API Authentication

Authentication requires a valid API key included in the request. Generate and manage your API keys from your developer dashboard. Include the key in the key parameter for all API requests.

Integration Examples

Production-ready code samples for API integration

{
  "init_image": "https://assets.modelslab.com/generations/18011592-127a-4d6e-adf7-c66d1ce7693c",
  "init_audio": "https://assets.modelslab.com/generations/efc19902-2b68-4dac-aa8a-b84960651790",
  "model_id": "omni-human",
  "key": "YOUR_API_KEY"
}

SDKs

Official SDKs

Production-ready SDKs and client libraries for all major programming languages

JavaScript

Python

PHP

API Parameters

Technical specifications for API request parameters.

Field Name	Parameter	Technical Description
Reference Image	`init_image`	Upload the reference image
reference audio	`init_audio`	reference audio should have less than 30 sec
model_id	`model_id`	Model to use for generation