Bytedance/Omnihuman-1.5

omni-human-1.5

Omnihuman 1.5LLMs.txt

OmniHuman 1.5 — a film-grade digital human model that turns a single image, audio, and text prompt into lifelike video performances. It supports full prompt input, unrestricted camera and character movement, and intelligent audio understanding for natural, expressive, and story-driven results.

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/8931fb55-905f-4ae8-8924-1b4e583ff789.png",
  "init_audio": "https://assets.modelslab.com/generations/7e1221ae-c5a9-4b1a-96cb-3448cc73c6e3.m4a",
  "prompt": "The camera zoomed in. The woman spoke to the camera, and after finishing, she quickly turned around and ran backward.",
  "model_id": "omni-human-1.5",
  "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`	Image to upscale/enhance
Reference Audio	`init_audio`	Audio file to clone voice from (for voice cloning)
Prompt	`prompt`	Text description of the image you want to generate
Model id	`model_id`	Model to use for generation