🚀 Z-Image Turbo Image-to-Image is Live — Unlimited Generations for Premium Users

Try Now
Skip to main content
Omnihuman thumbnail

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 PlaygroundAPI Documentation

Input

Customize your API request

File preview

File preview

or record audio
Audio recording is not supported in your browser

Output

Generation complete

Idle

Unknown content type

Related Models

Discover similar models you might be interested in

kling V2.1 Master Text To Video
KlingAI

kling V2.1 Master Text To Video

Seedance 1.0 Pro Fast Text to Video
Bytedance

Seedance 1.0 Pro Fast Text to Video

Veo 3 Fast
Popular
Google

Veo 3 Fast

Seedance 1.0 Pro Image to Video
Popular
Bytedance

Seedance 1.0 Pro Image to Video

Alibaba

Wan2.6 Image To Video

Hailuo 2.3 Fast Image To Video
Minmax

Hailuo 2.3 Fast Image To Video

Hailuo 02 Text To Video
Minmax

Hailuo 02 Text To Video

Sora 2 Pro Text To Video
Open Ai

Sora 2 Pro Text To Video

Kling V2.5 Turbo Image To Video
KlingAI

Kling V2.5 Turbo Image To Video

Veo 3 Fast preview
Google

Veo 3 Fast preview

Wan 2.5 Image to Video
Alibaba

Wan 2.5 Image to Video

Hailuo 2.3 Text To Video
Minmax

Hailuo 2.3 Text To Video