Seedance 2.0 API

Complete API reference for Seedance 2.0 video generation models by ByteDance.

Model Variants

This API supports six model variants:

Quick Comparison

Supported Aspect Ratios

21:9, 16:9, 9:16, 1:1, 4:3, 3:4

Resolution Options

Seedance 2.0 Text to Video

Endpoint

POST /api/v1/video/task

Request Parameters

Required

Optional

Example Request

javascriptCopy
const response = await fetch('https://api.flaq.ai/api/v1/video/task', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model_name: 'seedance-v2.0-text-to-video',
    prompt: 'A golden retriever running through a sunlit meadow',
    duration: 6,
    resolution: '720p',
    aspect_ratio: '16:9'
  })
});

const { data } = await response.json();
const taskId = data.task_id;

Seedance 2.0 Image to Video

Request Parameters

Required

Optional

Example Request

javascriptCopy
{
  model_name: 'seedance-v2.0-image-to-video',
  image_url: 'https://example.com/image.jpg',
  image_end_url: 'https://example.com/end-frame.jpg',
  prompt: 'Camera slowly pulls back to reveal the full landscape',
  duration: 6,
  resolution: '720p',
  aspect_ratio: '16:9'
}

Seedance 2.0 Reference to Video

Request Parameters

Required

Reference Media

Submit 1-9 images. Images may be omitted only when at least one reference video is provided.

@ (AT) Reference Placeholders

The @ (AT) reference feature links reference media to the prompt through numbered <<<...>>> placeholders. Numbering starts at 1 independently for each media type and follows the order of the corresponding array:

For example, if the first image is a character reference and the second image is a scene reference, use <<<image_1>>> for the character and <<<image_2>>> for the scene in prompt. Each placeholder must point to an item that exists in its corresponding array.

Optional

Example Request

javascriptCopy
{
  model_name: 'seedance-v2.0-reference-to-video',
  prompt: 'Use image one for the subject, video one for the movement, and audio one for the atmosphere',
  duration: 8,
  resolution: '1080p',
  aspect_ratio: '16:9',
  sound: true,
  images: ['https://example.com/subject-reference.jpg'],
  videos: ['https://example.com/motion-reference.mp4'],
  audios: ['https://example.com/atmosphere-reference.mp3']
}

@ (AT) Reference-to-Video Request Example

javascriptCopy
{
  model_name: 'seedance-v2.0-reference-to-video',
  prompt: 'Place the explorer from <<<image_1>>> in the environment from <<<image_2>>>, following the camera movement in <<<video_1>>> and speaking with the reference voice from <<<audio_1>>>',
  duration: 8,
  resolution: '1080p',
  aspect_ratio: '16:9',
  sound: true,
  images: [
    'https://example.com/explorer-reference.jpg',
    'https://example.com/environment-reference.jpg'
  ],
  videos: ['https://example.com/camera-movement-reference.mp4'],
  audios: ['https://example.com/voice-reference.mp3']
}

Fast Variants

The fast variants prioritize processing speed. All Fast models support only "480p" and "720p" output. Fast Text-to-Video and Fast Image-to-Video otherwise follow their corresponding standard request shapes, while Fast Reference-to-Video uses the same reference media limits as the standard reference model.

Example Fast Request

javascriptCopy
{
  model_name: 'seedance-v2.0-fast-reference-to-video',
  prompt: 'Use image one for the subject, follow the movement from video one, and use audio one for the atmosphere',
  duration: 8,
  resolution: '720p',
  aspect_ratio: '9:16',
  sound: true,
  images: ['https://example.com/subject-reference.jpg'],
  videos: ['https://example.com/motion-reference.mp4'],
  audios: ['https://example.com/atmosphere-reference.mp3']
}

@ (AT) Fast Reference-to-Video Request Example

javascriptCopy
{
  model_name: 'seedance-v2.0-fast-reference-to-video',
  prompt: 'Have the dancer from <<<image_1>>> perform the movement from <<<video_1>>> on the stage in <<<image_2>>>, using the rhythm from <<<audio_1>>>',
  duration: 8,
  resolution: '720p',
  aspect_ratio: '9:16',
  sound: true,
  images: [
    'https://example.com/dancer-reference.jpg',
    'https://example.com/stage-reference.jpg'
  ],
  videos: ['https://example.com/dance-movement-reference.mp4'],
  audios: ['https://example.com/rhythm-reference.mp3']
}

Seedance 2.0 Fast Reference-to-Video Parameters

Required

Reference Media

The same 1-based placeholder convention described above applies to the Fast Reference-to-Video model.

Optional

Response Format

Initial Response

All models return a task_id for polling:

jsonCopy
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "submitted"
  }
}

Polling Response

Poll GET /api/v1/video/{taskId} to check status:

jsonCopy
{
  "code": 0,
  "message": "success",
  "data": {
    "task_id": "{task_id}",
    "response_url": "https://api.flaq.ai/api/v1/video/{task_id}",
    "task_status": "succeed",
    "task_status_msg": null,
    "task_result": {
      "videos": [
        {
          "url": "https://example.com/generated-video.mp4"
        }
      ]
    }
  }
}

Status Values

• submitted: Task accepted and waiting to be processed
• processing: Video generation in progress
• succeed: Video generation completed
• failed: Video generation failed

Processing Time

Standard Models: 3-8 minutes depending on duration and resolution.

Fast Models: 1-4 minutes for most configurations.

Poll every 5-10 seconds to check status.

Best Practices

1. Choose the Right Variant: Use fast models for iteration, standard models for final output
2. Describe Motion Clearly: Include specific movement descriptions in prompts
3. Resolution Selection: All standard Seedance 2.0 models support 480p, 720p, 1080p, and 4k; all Fast models support only 480p and 720p
4. Reference Ordering: Keep images, videos, and audios in intentional order and refer to them consistently in the prompt
5. Video-Only Requests: Use an empty images array only when at least one reference video is provided
6. Media Duration: Keep every reference audio and video between 2 and 15 seconds
7. Audio Enhancement: Omit sound to use its default value of true, or set it to false to disable generated sound