Home/Explore/Avatar Lipsync/bytedance/avatar-omni-human

image-to-video

bytedance/avatar-omni-human

Transform your portrait photos into dynamic avatar videos with OmniHuman technology. Create realistic human motion and expressions from a single portrait image. 0.12$ per second.

Doc

Hint: You can drag and drop a file or click to upload

preview

Hint: You can drag and drop a file or click to upload

If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

Your request will cost $0.12 per run.

For $10 you can run this model approximately 83 times.

One more thing:

ExamplesView all

README

OmniHuman

OmniHuman is a cutting-edge end-to-end AI framework developed by ByteDance, designed to generate highly realistic human videos from just a single image and an audio input, with advanced features such as lip sync, facial animation, and gesture synthesis. Whether you provide a portrait, half-body, or full-body photo, OmniHuman brings it to life with natural movements, expressive gestures, accurate lip synchronization to audio, and remarkable attention to detail. By combining multiple input types—such as images and audio—OmniHuman creates vivid, high-quality video results. The model is highly adaptable, supporting not only real human portraits but also animated or cartoon characters, making it suitable for a wide range of applications including content creation, singing, lip sync videos, and performance scenarios. 0.12$ per second.

OmniHuman Avatar Effect

Requirements

Number of Images

  • Only one image can be uploaded per generation.

Image Requirements

  • Only human portrait images are supported.
  • For best results, use clear, front-facing portraits with good lighting.
  • Supported formats: PNG, JPEG, JPG, WebP.
  • Maximum file size: 50MB.

Output Characteristics

  • Produces natural human motion, facial expressions, and accurate lip sync to audio.
  • Works best with clear, well-lit portrait photos.
  • May not perform optimally with extreme poses or poor lighting.

Best Practices

  1. Use a clear, front-facing portrait photo.
  2. Ensure the image is well-lit.
  3. Avoid extreme angles or poses.
  4. Make sure the face is clearly visible.
  5. Avoid images with multiple people.

Keywords

  • lip sync
  • facial animation
  • gesture synthesis
  • portrait animation
  • audio-driven video generation