Explore/bytedance/avatar-omni-human

image-to-image

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.

HOT
NEW

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.

Idle

https://portal.volccdn.com/obj/volcfe/cloud-universal-doc/upload_e85bf7e9ab70752ac2730926434b181a.jpeg

Your request will cost $0.02 per run.

For $1 you can run this model approximately 50 times.

README

OmniHuman Avatar Effect

Requirements

Number of Images

  • Required, only supports uploading one image.

Image Requirements

  • Only supports human portrait images
  • Better results with clear, front-facing portraits with good lighting
  • Supported image formats: PNG, JPEG, JPG, WebP
  • Maximum file size: 50MB

Effect Boundaries

  • Generates natural human motion and expressions
  • Best results with clear, well-lit portrait photos
  • May have limitations with extreme poses or poor lighting conditions

Best Practices

  1. Use clear, front-facing portrait photos
  2. Ensure good lighting in the input image
  3. Avoid extreme angles or poses
  4. Make sure the face is clearly visible
  5. Avoid images with multiple people