Seedance 2.0

Create an asynchronous video generation task. Supports multiple input modes:

• Text-to-video
• Image-to-video (first frame / first+last frame)
• Multimodal reference (image + video + audio combinations)
• Video editing
• Video extension
• Web search enhanced generation

Poll GET /v1/video/generations/{id} until status is succeeded.

POST /v1/video/generations

Create Video Generation Task

cURL

curl --request POST \
  --url https://www.anyfast.ai/v1/video/generations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "seedance",
  "content": [
    {
      "type": "text",
      "text": "A cat playing piano in a sunlit room"
    },
    {
      "type": "image_url",
      "image_url": {
        "url": "https://example.com/reference.jpg"
      },
      "role": "reference_image"
    }
  ],
  "generate_audio": true,
  "resolution": "720p",
  "ratio": "adaptive",
  "duration": 5,
  "tools": [
    {
      "type": "web_search"
    }
  ],
  "watermark": false,
  "return_last_frame": false
}
'

200

{
  "id": "cgt-20260312231129-7db6s",
  "task_id": "cgt-20260312231129-7db6s",
  "object": "video",
  "model": "seedance",
  "status": "",
  "progress": 0,
  "created_at": 1773328294
}

Authorizations

Authorization · string · header · required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

model · enum<string> · required

Model ID

Available options: seedance

Example:

"seedance"

content · object[] · required

Input content array for video generation. Supports text, images, videos, and audio in various combinations:

• Text only
• Text (optional) + Image(s)
• Text (optional) + Video(s)
• Text (optional) + Image + Audio
• Text (optional) + Image + Video
• Text (optional) + Video + Audio
• Text (optional) + Image + Video + Audio

Show child attributes

Example:

[
  {
    "type": "text",
    "text": "A cat playing piano in a sunlit room"
  },
  {
    "type": "image_url",
    "image_url": {
      "url": "https://example.com/reference.jpg"
    },
    "role": "reference_image"
  }
]

generate_audio · boolean · default: true

Generate synchronized audio with the video.

• true — Video includes auto-generated voice, sound effects, and background music
• false — Silent video

resolution · enum<string> · default: 720p

Output video resolution.

Available options: 480p, 720p, 1080p

ratio · enum<string> · default: adaptive

Output aspect ratio. adaptive automatically selects the best ratio based on input.

Available options: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive

duration · integer · default: 5

Video duration in seconds (integer, 4–15).

Required range: 4 <= x <= 15

tools · object[]

Tools for the model to use. Currently supports web search (text-to-video only).

Show child attributes

watermark · boolean · default: false

Add watermark to the generated video.

return_last_frame · boolean · default: false

Return the last frame of the generated video as an image.

Response

200

application/json

Video generation task created

id · string

Task ID for polling

Example:

"cgt-20260312231129-7db6s"

task_id · string

Task ID (same as id)

Example:

"cgt-20260312231129-7db6s"

object · string

Example:

"video"

model · string

Example:

"seedance"

status · string

Initially empty

Example:

""

progress · integer

Example:

0

created_at · integer

Unix timestamp

Example:

1773328294