Skip to main content
POST
/
generate
/
vol
/
seedream
Seedream Image Generation
curl --request POST \
  --url https://api.sinancode.com/v1/generate/vol/seedream \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "把这张照片变成黏土风格。放在一张拍立得照片中...",
  "images": [
    "https://media.sinancode.com/uploads/1765851887405-rfpmtj1u.png"
  ],
  "max_images": 4,
  "size": "2K",
  "version": "5.0-lite"
}
'
{
  "task_id": "01234567-89ab-cdef-0123-456789abcdef"
}

Documentation Index

Fetch the complete documentation index at: https://docs.sinancode.com/llms.txt

Use this file to discover all available pages before exploring further.

Generate images using ByteDance’s Seedream model, supporting both single image and multi-image modes. Key Features:
  • Multi-Version Support - Supports 5.0-lite (default), 4.5, and 4.0
  • Flexible Output Modes - Single image (max_images=1) or multi-image (max_images=2-15)
  • Text-to-Image & Image-to-Image - Generate from text or reference images (up to 14)
  • HD Output - 5.0-lite supports 2K/3K, 4.5/4.0 supports 2K/4K, or specify exact resolution

Authorizations

​
Authorization
string
header
required

Please use your API Token for authentication

Body

application/json

Task parameters

​
prompt
string
required

Prompt (required, recommended not to exceed 300 Chinese characters or 600 English words)

Required string length: 1 - 2000
Example:

"把这张照片变成黏土风格。放在一张拍立得照片中..."

​
images
string[]

Input images (optional, supports multiple reference images, up to 14) Example: ["https://example.com/1.jpg", "https://example.com/2.jpg"]

Example:
[
  "https://media.sinancode.com/uploads/1765851887405-rfpmtj1u.png"
]
​
max_images
integer
default:1

Maximum number of images (optional, default 1)

  • Set to 1: Generate a single image (disables group image function)
  • Set to 2-15: Generate a group of images, up to N images (input image count + generated count ≤ 15)
Required range: 1 <= x <= 15
Example:

4

​
size
string
default:2K

Image size (optional, default 2K) Two formats are supported:

  • Tier: 2K, 3K (for 5.0-lite) or 2K, 4K (for 4.5/4.0), where the model automatically determines the aspect ratio based on the prompt
  • Exact resolution: width x height, e.g., "2048x2048", "2560x1440"
Example:

"2K"

​
version
enum<string>
default:5.0-lite

Model version (optional, default 5.0-lite) Available values: 4.0, 4.5, 5.0-lite

Available options:
4.0,
4.5,
5.0-lite
Example:

"5.0-lite"

Response

OK

​
task_id
string
required

Task ID

Example:

"01234567-89ab-cdef-0123-456789abcdef"