mingyanmingyan
wechatwechat
mingyan

Seedance1.5 - Create Task

Create video generation tasks using Volcano Engine Seedance1.5 model, supporting text-to-video and image-to-video

POST/kyyReactApiServer/v1/seedance/videos

Seedance1.5 Create Video Task

Create high-quality video generation tasks using Volcano Engine Seedance1.5 (即梦) AI model, supporting text-to-video, image-to-video (first frame/first and last frames), and more.

Authentication

Get Key
All requests require a Bearer token in the request header:
cURL
Authorization: Bearer {{YOUR_API_KEY}}

Base URL

https://zcbservice.aizfw.cn/kyyReactApiServer
baseUrl is the shared prefix for all public APIs. The api field in the current page frontmatter shows the full endpoint. Use this baseUrl as the common prefix when reading or composing request paths.

Supported Models

Seedance 1.5 Series (Billed by Second)

480p

seedance_1_5_pro_480p
Supports audio generation, image-to-video

720p

seedance_1_5_pro_720p
Supports audio generation, image-to-video

1080p

seedance_1_5_pro_1080p
Supports audio generation, image-to-video

Request Parameters

modelstringrequired
Model name, see supported models list above
contentarrayrequired
Input content array, supports text and image formats. See content array structure below
ratiostring
Video aspect ratio
Options: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive
Default values:
  • Text-to-video: 16:9 (Seedance 1.5 Pro uses adaptive)
  • Image-to-video: adaptive
durationinteger
Video duration in seconds, supports 2-12 seconds, defaults to 5
Seedance 1.5 pro special notes:
  • Specific duration: Integer from 4-12 seconds
  • Auto-select duration: Set to -1, model automatically selects 4-12 seconds

Content Array Structure

Text Content Object

typestringrequired
Fixed value: text
textstringrequired
Text prompt, Chinese up to 500 characters, English up to 1000 words
Example:
JSON
{
  "type": "text",
  "text": "A cat yawning at the camera"
}

Image Content Object

typestringrequired
Fixed value: image_url
image_url.urlstringrequired
Image URL
rolestring
Image role, choose based on use case:
  • first_frame or omit - First frame image (image-to-video with first frame)
  • last_frame - Last frame image (image-to-video with first and last frames)
  • reference_image - Reference image (Seedance 1.0 lite i2v, 1-4 images)
Image Requirements:
  • Format: jpeg, png, webp, bmp, tiff, gif (Seedance 1.5 pro supports heic, heif)
  • Aspect ratio: (0.4, 2.5)
  • Dimensions: (300px, 6000px)
  • Size: < 30 MB
Example:
JSON
{
  "type": "image_url",
  "image_url": {
    "url": "https://example.com/image.jpg"
  },
  "role": "first_frame"
}

Response Parameters

idstring
Video generation task ID, stored for 1 day, used for querying task status
objectstring
Object type, fixed as video
createdinteger
Task creation timestamp
modelstring
Model name used
statusstring
Task status:
  • queued - Queued
  • processing - Processing
  • completed - Completed
  • failed - Failed
  • cancelled - Cancelled

Use Cases

Text-to-Video

Generate video using only text prompts

Image-to-Video (First Frame)

Use 1 image as first frame, combined with text to generate video

Image-to-Video (First & Last)

Use 2 images as first and last frames to control video start and end

Important Notes

Important Limitations:
  • Image scenarios are mutually exclusive: first frame, first and last frames, and reference images cannot be mixed
  • Audio generation is only supported by Seedance 1.5 pro series
  • Task IDs are stored for 1 day, please save generated videos promptly
Best Practices:
  1. Video generation is asynchronous, use the returned id to query task status and results
  2. Choose appropriate resolution and duration to balance quality and cost
  3. For image-to-video, image quality directly affects generation results