Generation Modes

The Seedance 2.0 official format expresses text, image, video, and audio inputs through content[]. Image assets use role: reference_image, video assets use role: reference_video, and audio assets use role: reference_audio.

All examples below are submitted to the official endpoint POST /api/v3/contents/generations/tasks.

Text to video

{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {
      "type": "text",
      "text": "A golden Shiba Inu running under cherry blossoms, camera slowly rising"
    }
  ],
  "resolution": "480p",
  "ratio": "16:9",
  "duration": 5,
  "watermark": false
}

Image to video

{
  "model": "doubao-seedance-2-0-fast-260128",
  "content": [
    {
      "type": "text",
      "text": "Have the person in the frame slowly turn around and smile"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/photo.jpg"
      },
      "role": "reference_image"
    }
  ],
  "resolution": "720p",
  "ratio": "16:9",
  "duration": 5,
  "watermark": false
}

Video to video

{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {
      "type": "text",
      "text": "Turn the person in the video into a cartoon style"
    },
    {
      "type": "video_url",
      "video_url": {
        "url": "https://example.com/reference-video.mp4"
      },
      "role": "reference_video"
    }
  ],
  "resolution": "480p",
  "ratio": "16:9",
  "duration": 5,
  "generate_audio": true,
  "watermark": false
}

Audio-visual sync (image + audio)

{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {
      "type": "text",
      "text": "Make the character speak according to the audio"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/reference-image.jpg"
      },
      "role": "reference_image"
    },
    {
      "type": "audio_url",
      "audio_url": {
        "url": "https://example.com/reference-audio.mp3"
      },
      "role": "reference_audio"
    }
  ],
  "resolution": "480p",
  "ratio": "16:9",
  "duration": 5,
  "watermark": false
}

Multiple references (image + video)

{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {
      "type": "text",
      "text": "Restyle this video to match the image's style"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/reference-image.jpg"
      },
      "role": "reference_image"
    },
    {
      "type": "video_url",
      "video_url": {
        "url": "https://example.com/reference-video.mp4"
      },
      "role": "reference_video"
    }
  ],
  "resolution": "480p",
  "ratio": "16:9",
  "duration": 5,
  "watermark": false
}

Dynamic sound effects (video + audio)

{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {
      "type": "text",
      "text": "Add sound effects to the video that match the audio"
    },
    {
      "type": "video_url",
      "video_url": {
        "url": "https://example.com/reference-video.mp4"
      },
      "role": "reference_video"
    },
    {
      "type": "audio_url",
      "audio_url": {
        "url": "https://example.com/reference-audio.mp3"
      },
      "role": "reference_audio"
    }
  ],
  "resolution": "480p",
  "ratio": "16:9",
  "duration": 5,
  "watermark": false
}

Full multimodal generation (image + video + audio)

{
  "model": "doubao-seedance-2-0-260128",
  "content": [
    {
      "type": "text",
      "text": "Apply the image's style and this voice to the scene where the lead speaks, and edit the video"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/reference-image.jpg"
      },
      "role": "reference_image"
    },
    {
      "type": "video_url",
      "video_url": {
        "url": "https://example.com/reference-video.mp4"
      },
      "role": "reference_video"
    },
    {
      "type": "audio_url",
      "audio_url": {
        "url": "https://example.com/reference-audio.mp3"
      },
      "role": "reference_audio"
    }
  ],
  "resolution": "480p",
  "ratio": "16:9",
  "duration": 5,
  "generate_audio": true,
  "watermark": false
}

The same modes can also be expressed with the generic video format.