Skip to main content
POST
/
vendors
/
alibaba
/
v1
/
qwen-image-max
/
generation
Create Generation Task
curl --request POST \
  --url https://api.mulerouter.ai/vendors/alibaba/v1/qwen-image-max/generation \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "prompt": "<string>",
  "negative_prompt": "<string>",
  "size": "1664*928",
  "prompt_extend": true,
  "seed": 1073741823
}
'
{
  "task_info": {
    "id": "3c90c3cc-0d44-4b50-8888-8dd25736052a",
    "status": "pending",
    "created_at": "2023-11-07T05:31:56Z",
    "updated_at": "2023-11-07T05:31:56Z"
  }
}

​
Overview

Generate highly realistic and natural images from text descriptions using the qwen-image-max model. This advanced text-to-image model improves upon the Plus series with enhanced realism and reduced AI-generated artifacts.

​
Key Features

  • Enhanced Realism: Produces more natural-looking images with fewer AI artifacts
  • Character Excellence: Superior rendering of human textures, skin tones, and facial details
  • Text Rendering: Excels at generating clear, legible text in images
  • Multi-line Text: Supports paragraph-level text generation within images
  • Fine Details: Outstanding performance in rendering intricate details
  • Multiple Styles: Supports various artistic and photographic styles
  • High Resolution: Multiple aspect ratios from 1:1 to 16:9

​
Pricing

$0.075 per image

​
Resolution Options

ResolutionAspect RatioBest For
1664*928 (default)16:9Landscape photos, banners, wide scenes
1472*11044:3Standard photos, presentations
1328*13281:1Social media posts, profile images
1104*14723:4Portraits, vertical content
928*16649:16Mobile screens, stories

​
Example Requests

​
Basic Text-to-Image

{
  "prompt": "A professional portrait photograph of a woman in her 30s, natural lighting, soft smile, business attire"
}

​
Complex Scene with Text

{
  "prompt": "A cozy coffee shop interior with a chalkboard menu on the wall displaying 'Daily Special: Cappuccino $4.50', warm ambient lighting, wooden furniture, customers in the background",
  "size": "1664*928",
  "prompt_extend": true
}

​
Artistic Style Generation

{
  "prompt": "An oil painting of a sunset over mountains, impressionist style, vibrant colors, thick brush strokes",
  "negative_prompt": "low resolution, low quality, AI-like, overly smooth, waxy, no facial details",
  "size": "1472*1104"
}

​
Parameters

​
prompt (Required)

  • Type: String
  • Max Length: 800 characters
  • Languages: Chinese and English supported

​
negative_prompt

  • Type: String or null
  • Max Length: 500 characters

​
size

  • Type: String (enum)
  • Default: “1664*928” (16:9)

​
prompt_extend

  • Type: Boolean
  • Default: true

​
seed

  • Range: 0 to 2,147,483,647

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json
​
prompt
string
required

Text description for the image (max 800 characters). Describes the desired content, style, and composition of the generated image. Supports both Chinese and English.

Maximum string length: 800
​
negative_prompt
string

Negative prompt describing unwanted content (max 500 characters). Used to constrain the image generation. Example: low resolution, low quality, deformed limbs, deformed fingers, oversaturated, waxy, no facial details, overly smooth, AI-like, chaotic composition, blurry text, distorted text.

Maximum string length: 500
​
size
enum<string>
default:1664*928

Image resolution in format "width*height".

Default: 1664*928

Available resolutions and aspect ratios:

  • 1664*928 (default): 16:9
  • 1472*1104: 4:3
  • 1328*1328: 1:1
  • 1104*1472: 3:4
  • 928*1664: 9:16
Available options:
1664*928,
1472*1104,
1328*1328,
1104*1472,
928*1664
​
prompt_extend
boolean
default:true

Enable intelligent prompt rewriting. When enabled, the model optimizes and refines the positive prompt. Keep enabled if your input prompt is simple or if you want the model to be more creative. Set to false if your prompt is already detailed and professional.

​
seed
integer

Random seed for reproducibility [0, 2147483647]. Using the same seed produces more consistent results. Note: Results are not guaranteed to be identical for every call even with the same seed.

Required range: 0 <= x <= 2147483647

Response

202 - application/json

Accepted - Task created successfully

​
task_info
object