OmniHuman 1.5 Subject Detection: model and API overview
OmniHuman 1.5 Subject Detection is part of ByteDance's OmniHuman family. This card covers a specialist media workflow. It can create or analyze a digital human and its presence in the frame. Consider it when the task involves a speaking character, identification, or avatar preparation. Input: Images, Video; output: not specified.
External model reference page. This page does not confirm availability in Neiron.
Capabilities
OmniHuman 1.5 Subject Detection: For a specialist operation, it can create or analyze a digital human and its presence in the frame.
Input: Images, Video; output: not specified.
Purpose: Vision; developer: ByteDance; region: China.
Use cases
Reviewed facts
Benchmarks
No comparable benchmark is recorded in this card.
Sources
What to verify before use
FAQ
What is OmniHuman 1.5 Subject Detection?
OmniHuman 1.5 Subject Detection is part of ByteDance's OmniHuman family. This card covers a specialist media workflow. It can create or analyze a digital human and its presence in the frame. Consider it when the task involves a speaking character, identification, or avatar preparation. Input: Images, Video; output: not specified.
What task is OmniHuman 1.5 Subject Detection suited to?
Create or analyze a digital human and its presence in the frame. Choose it when the task involves a speaking character, identification, or avatar preparation.
What does OmniHuman 1.5 Subject Detection accept and return?
Reviewed input modalities: Images, Video. Output: not specified. The record was checked on 2026-08-26.