Skip to main content
POST
/
v1
/
tasks
curl -X POST https://qingbo.dev/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5.0",
    "action": "generate",
    "prompt": "一只柴犬穿宇航服站在月球上",
    "size": "16:9",
    "resolution": "2K",
    "watermark": false
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "seedream-5.0",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}
Async processing mode — submit a request and receive a task ID. Use the Query Task Status endpoint to retrieve generation results. Image links are valid for 24 hours — please save them promptly. 
curl -X POST https://qingbo.dev/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedream-5.0",
    "action": "generate",
    "prompt": "一只柴犬穿宇航服站在月球上",
    "size": "16:9",
    "resolution": "2K",
    "watermark": false
  }'

{
  "task_id": "task-wave1775285160b950328499",
  "model": "seedream-5.0",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

​
Available Models

Model IDDescription
seedream-5.0Seedream 5.0, supports multi-image sets, web search, and streaming output
seedream-4.5Seedream 4.5, supports multi-image sets and 4K resolution
seedream-4.0Seedream 4.0, supports multi-image sets, 1K-4K resolution

​
Common Parameters

​
model
string
required
Model group name: seedream-5.0, seedream-4.5, seedream-4.0
​
action
string
default:"generate"
Operation type
​
prompt
string
required
Text prompt, supports Chinese and English, recommended no more than 300 Chinese characters
​
image_urls
string[]
Reference image URL array, up to 14 images, each up to 10MB
​
size
string
default:"1:1"
Aspect ratio: 1:1, 2:3, 3:2, 3:4, 4:3, 9:16, 16:9, 21:9
​
resolution
string
default:"2K"
Resolution, available values depend on the model (see model tabs)
​
n
integer
default:"1"
Number of images to generate. Values greater than 1 enable multi-image set mode
​
watermark
boolean
default:"true"
Whether to add a watermark
​
callback_url
string
Webhook callback URL upon task completion
​
extra
object
Additional parameters passed through to the upstream model (see model tabs)

​
Model-Specific Parameters

resolution options: 2K, 3Ksize additional support: 4:5, 5:4
​
extra.output_format
string
default:"jpeg"
Output image format: png, jpeg
​
extra.response_format
string
default:"url"
Return format: url (download link) or b64_json (Base64)
​
extra.stream
boolean
default:"false"
Streaming output, returns each image result immediately
​
extra.optimize_prompt_options
object
Prompt optimization configuration
​
extra.tools
array
Model tools, supports web search to improve timeliness
"extra": { "tools": [{"type": "web_search"}] }

​
Generation Modes

ModeParametersDescription
Text-to-imagepromptPure text generation
Single image-to-imageprompt + image_urls (1 image)Reference image + text
Multi-image-to-imageprompt + image_urls (2-14 images)Multiple reference image fusion
Image setn > 1Generate a set of related images
In image set mode, the total of reference images + generated images must be 15 or fewer.

​
Response

​
task_id
string
Task ID
​
model
string
Model ID used
​
action
string
Operation type
​
status
string
Task status: queued
​
created_at
integer
Creation time (Unix millisecond timestamp)
​
progress
integer
Progress, initially 0