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>"
  ]
}
'
import requests

url = "https://www.qingbo.dev/v1/tasks"

payload = {
    "model": "<string>",
    "action": "<string>",
    "prompt": "<string>",
    "n": 123,
    "seed": 123,
    "aspect_ratio": "<string>",
    "resolution": "<string>",
    "image_urls": ["<string>"],
    "callback_url": "<string>",
    "callback_events": ["<string>"]
}
headers = {"Content-Type": "application/json"}

response = requests.post(url, json=payload, headers=headers)

print(response.text)
const options = {
  method: 'POST',
  headers: {'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: '<string>',
    action: '<string>',
    prompt: '<string>',
    n: 123,
    seed: 123,
    aspect_ratio: '<string>',
    resolution: '<string>',
    image_urls: ['<string>'],
    callback_url: '<string>',
    callback_events: ['<string>']
  })
};

fetch('https://www.qingbo.dev/v1/tasks', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));
package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://www.qingbo.dev/v1/tasks"

	payload := strings.NewReader("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"seed\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "application/json")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}
HttpResponse<String> response = Unirest.post("https://www.qingbo.dev/v1/tasks")
  .header("Content-Type", "application/json")
  .body("{\n  \"model\": \"<string>\",\n  \"action\": \"<string>\",\n  \"prompt\": \"<string>\",\n  \"n\": 123,\n  \"seed\": 123,\n  \"aspect_ratio\": \"<string>\",\n  \"resolution\": \"<string>\",\n  \"image_urls\": [\n    \"<string>\"\n  ],\n  \"callback_url\": \"<string>\",\n  \"callback_events\": [\n    \"<string>\"\n  ]\n}")
  .asString();
{
  "task_id": "task-wave1775285160b950328499",
  "model": "qwen-image-2.0-pro",
  "action": "generate",
  "status": "queued",
  "created_at": 1775285160040,
  "progress": 0
}
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"
  }'

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",
    "action": "image2image",
    "prompt": "Convert this photo to cyberpunk style, preserve facial features",
    "image_urls": ["https://cdn.example.com/portrait.jpg"],
    "resolution": "2K",
    "aspect_ratio": "9:16"
  }'

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",
    "action": "reference",
    "prompt": "Dress the character from the first image in the outfit from the second, place them in the scene from the third",
    "image_urls": [
      "https://cdn.example.com/character.jpg",
      "https://cdn.example.com/outfit.jpg",
      "https://cdn.example.com/scene.jpg"
    ],
    "resolution": "2K",
    "aspect_ratio": "16:9"
  }'

{
  "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