Skip to main content
POST
/
v1
/
tasks
Qwen Image Series
curl --request POST \
  --url https://www.qingbo.dev/v1/tasks \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "action": "<string>",
  "prompt": "<string>",
  "n": 123,
  "seed": 123,
  "aspect_ratio": "<string>",
  "resolution": "<string>",
  "image_urls": [
    "<string>"
  ],
  "callback_url": "<string>",
  "callback_events": [
    "<string>"
  ]
}
'
{
  "task_id": "task-wave1775285160b950328499",
  "model": "qwen-image-2.0-pro",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}

Documentation Index

Fetch the complete documentation index at: https://docs.qingbo.dev/llms.txt

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

Alibaba Tongyi Qianwen image series, with two tiers:
  • 2.0 Pro — Flagship highest-fidelity tier. Native 2K, strong detail, accurate composition, professional-grade text rendering. Suited for infographics, posters, and marketing assets
  • 2.0 — Standard version. Combined generation and editing, supports very long prompts, 2K high-quality output. Suited for use cases needing clear text and professional design aesthetics
Per-image pricing, unified interface supporting text-to-image / image-to-image / multi-image reference.

Pricing

ModelPrice (per image)
qwen-image-2.0-pro$0.053125
qwen-image-2.0$0.02125

Mode Quick Reference

ModeTrigger FieldSupported Versions
Text-to-imageprompt onlyAll
Image-to-image+ image_urls (single) + action: "image2image"All
Multi-image reference fusion+ image_urls (multiple) + action: "reference"All

Examples

curl -X POST https://www.qingbo.dev/v1/tasks \
  -H "Authorization: Bearer $WAVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen-image-2.0-pro",
    "prompt": "Chinese-style poster: ink-wash landscape background, vertical title \"千问\" centered, gold-foil accents, professional typography",
    "resolution": "2K",
    "aspect_ratio": "3:4"
  }'
{
  "task_id": "task-wave1775285160b950328499",
  "model": "qwen-image-2.0-pro",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}
After submission, poll status with GET /v1/tasks/{task_id}. See Task System for details.

Available Models

Model IDDescription
qwen-image-2.0-proFlagship, native 2K, strong detail, accurate composition, professional-grade text rendering
qwen-image-2.0Standard, combined generation + editing, very long prompts, 2K high-quality output

Common Parameters

model
string
required
Choose one from the Available Models list
action
string
default:"generate"
Operation type. Options:
  • generate — Text-to-image (default)
  • image2image — Image-to-image (use with image_urls)
  • reference — Multi-image reference fusion (use with multiple image_urls)
prompt
string
required
Image description. Supports Chinese and English. Qwen Image is friendly to very long prompts and Chinese text rendering
n
integer
default:"1"
Number of images to generate (returned in a single call)
seed
integer
default:"-1"
Random seed. -1 for random; a fixed value reproduces similar results
aspect_ratio
string
default:"1:1"
Aspect ratio. Options:
  • 1:1 — Square
  • 4:3 / 3:4 — Standard landscape / portrait
  • 16:9 / 9:16 — Widescreen landscape / portrait
  • 3:2 / 2:3 — Camera ratio landscape / portrait
resolution
string
default:"2K"
Output resolution. Options:
  • 1K — Standard resolution
  • 2K — High resolution (default)
image_urls
string[]
Array of reference / input image URLs. Only publicly accessible URLs are supported; base64 is not accepted
  • image2image mode: 1 image
  • reference mode: multiple images
callback_url
string
Webhook callback URL, invoked when the task reaches a terminal state. See Callback Mechanism
callback_events
string[]
Subscribed callback event types. Defaults to terminal states (succeeded / failed)

Model-Specific Parameters

Supported actions: generate / image2image / referenceresolution: 1K / 2Kaspect_ratio: 1:1 / 4:3 / 3:4 / 16:9 / 9:16 / 3:2 / 2:3Key features: Flagship highest-fidelity tier. Native 2K, strong detail, accurate composition, professional-grade text rendering. Suited for infographics, posters, and marketing assetsNo model-specific parameters; all tunable fields are listed under Common Parameters.

Resource Limits

ItemLimit
prompt length≤ 800 characters
negative_prompt length≤ 500 characters
Reference image sourceMust be a publicly accessible URL; base64 upload not supported
Single reference image size≤ 30MB, supports JPG / PNG / WEBP
Output resolution1K / 2K
Output fileURL valid for 24 hours