Qwen | Qwen Cloud

POST

/services/aigc/multimodal-generation/generation

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--data '{
  "model": "qwen-image-2.0-pro",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "image": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/fpakfo/image36.webp"
          },
          {
            "text": "Generate an image that matches the depth map, following this description: A dilapidated red bicycle is parked on a muddy path with a dense primeval forest in the background."
          }
        ]
      }
    ]
  },
  "parameters": {
    "n": 2,
    "negative_prompt": " ",
    "prompt_extend": true,
    "watermark": false,
    "size": "1536*1024"
  }
}'

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "content": [
            {
              "image": "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx"
            },
            {
              "image": "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx"
            }
          ],
          "role": "assistant"
        }
      }
    ]
  },
  "usage": {
    "width": 1536,
    "image_count": 2,
    "height": 1024
  },
  "request_id": "bf37ca26-0abe-98e4-8065-xxxxxx"
}

Get an API key and set it as an environment variable. If using the SDK, install it.

Authorizations

string

header

required

DashScope API Key. Create one in the Qwen Cloud console.

Body

application/json

enum<string>

required

Model name.

Available options:qwen-image-2.0-pro,qwen-image-2.0-pro-2026-03-03,qwen-image-2.0,qwen-image-2.0-2026-03-03,qwen-image-edit-max,qwen-image-edit-max-2026-01-16,qwen-image-edit-plus,qwen-image-edit-plus-2025-12-15,qwen-image-edit-plus-2025-10-30,qwen-image-edit

Example:qwen-image-2.0-pro

object

required

Input data containing the messages array.

Show child attributes

object[]

required

Single-turn only. Exactly one message with role user.

Required range:items: 1–1

Show child attributes

enum<string>

required

Must be user.

Available options:user

object[]

required

Message content array. Must contain 1 to 3 image objects and exactly one text object. For multi-image input, images are referenced by position (Image 1, Image 2, Image 3). The output aspect ratio is determined by the last image.

Required range:items: 2–4

Show child attributes

string

Input image as a public URL (HTTP/HTTPS) or Base64-encoded string (data:{mime_type};base64,{data}). Supported formats: JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF (first frame only). For optimal results, width and height should be between 384 and 3072 pixels. Maximum file size: 10 MB.

Example:https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/fpakfo/image36.webp

string

Image editing instruction describing elements and visual features you want in the output image. Supports Chinese and English, max 800 characters. Excess is auto-truncated. Only one text input is supported per request.

Example:Generate an image that matches the depth map, following this description: A dilapidated red bicycle is parked on a muddy path with a dense primeval forest in the background.

Required range:length <= 800

object

Image editing parameters.

Show child attributes

integer

default1

Number of images to generate. qwen-image-2.0, qwen-image-edit-max, and qwen-image-edit-plus series: 1-6. qwen-image-edit: only 1.

Required range:1 <= x <= 6

string

Describes content you do NOT want in the image. Supports Chinese and English, max 500 characters. Excess is auto-truncated.

Required range:length <= 500

string

Output resolution as width*height. qwen-image-2.0 series: total pixels between 512*512 and 2048*2048. Default: same as input image (or last image in multi-image request). qwen-image-edit-max/plus: width and height each in [512, 2048]. Default: ~1024*1024 with aspect ratio similar to input. Automatically adjusted to nearest multiple of 16. qwen-image-edit: not supported. Recommended sizes: 1024*1024 (1:1), 768*1152 / 1024*1536 (2:3), 1152*768 / 1536*1024 (3:2), 720*1280 / 1080*1920 (9:16), 1280*720 / 1920*1080 (16:9).

Example:1024*1536

boolean

defaulttrue

Enable prompt rewriting. When enabled, the model optimizes the editing instruction. Significantly improves results when prompts lack detail. Not supported by qwen-image-edit.

boolean

defaultfalse

Add a "Qwen-Image" watermark to the bottom-right corner of the image.

integer

Random number seed. Range: [0, 2147483647]. Same seed produces more consistent (but not identical) results. If omitted, a random seed is used.

Required range:0 <= x <= 2147483647

Response

200-application/json

object

Show child attributes

object[]

List of generated results.

Show child attributes

string

stop means normal completion.

Example:stop

object

Show child attributes

enum<string>

Always assistant.

Available options:assistant

object[]

Response content array containing generated image URLs.

Show child attributes

string

URL of the generated image (PNG). Valid for 24 hours. Download promptly.

object

Usage statistics (successful results only).

Show child attributes

integer

Number of images generated.

integer

Width of the generated image in pixels.

integer

Height of the generated image in pixels.

string

default"bf37ca26-0abe-98e4-8065-xxxxxx"

Unique request identifier for tracing and troubleshooting.

Example:bf37ca26-0abe-98e4-8065-xxxxxx