ByteDance Seed logoByteDance SeedVideo

OmniHuman 2.0

ByteDance's image-and-audio workflow for talking-avatar video generation.

Playground

Video Generator

Model

OmniHuman 2.0

No videos generated yet

Enter a prompt and click Generate to create your first AI video.

About this model

Capabilities & specifications

Input
Image · Audio
Output
Video

OmniHuman 2.0 generates talking-avatar video from a portrait image and audio. BytePlus's published tooling documents a separate Vision AI task workflow, so it should not be treated as an interchangeable generic text-to-video endpoint.

  • Reference control
  • Motion transfer
Video generation

Examples

OmniHuman 2.0 speech demonstration excerpt

Model output documented by the source.

omnihuman2.org

Questions and answers

Where do OmniHuman 2.0 specifications come from?

The references below identify the sources for this model’s capabilities. Confirm current access, request limits and pricing with your service provider before integration.

Where do OmniHuman 2.0 specifications come from?

Things to consider

Review generated results before use. Available modes and request limits depend on the service you choose; check the linked documentation before integration.

Model information sources

  • OmniHuman 2.0 reference