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": "flux-kontext-pro",
    "prompt": "一只橘猫趴在窗台上晒太阳，水彩画风格",
    "size": "16:9"
  }'

{
  "code": "success",
  "data": "task-wave17200000001234567890abcdef"
}
Async processing mode — submit a request and receive a task ID. Use the Query Task Status endpoint to retrieve generation results. 
curl -X POST https://qingbo.dev/v1/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "flux-kontext-pro",
    "prompt": "一只橘猫趴在窗台上晒太阳，水彩画风格",
    "size": "16:9"
  }'

{
  "code": "success",
  "data": "task-wave17200000001234567890abcdef"
}

​
Available Models

Model IDDescription
flux-kontext-proFLUX Kontext Pro, excels at image editing and style transfer
flux-kontext-maxFLUX Kontext Max, enhanced version
flux-2-proFLUX 2.0 Pro, general-purpose image generation
flux-2-devFLUX 2.0 Dev, development version

​
Common Parameters

​
model
string
required
Model ID, see the model list above
​
prompt
string
required
Image description text, maximum 1000 characters
​
image_urls
array
Reference image URL array

​
Model-Specific Parameters

Applies to flux-kontext-pro and flux-kontext-max
​
size
string
default:"match_input_image"
Image sizeSupported: match_input_image, auto, 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9, 9:21
​
response_format
string
default:"png"
Output format: png, jpg
​
safety_tolerance
integer
default:"2"
Content safety level, range 0-6. Higher values are more permissive
​
prompt_upsampling
boolean
default:"false"
Enable prompt optimization enhancement
The Kontext series focuses on image editing. image_urls accepts a maximum of 1 reference image.

​
Response

Returns a task ID. Use Query Task Status to retrieve the final image result.
​
code
string
Status code, "success" on success
​
data
string
Task ID, formatted as task-wave{timestamp}{userId}{random}