Wan 2.7 synchronous | 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": "wan2.7-image-pro",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "A serene mountain lake at sunrise, with mist rising from the water, surrounded by pine trees, photorealistic"
          }
        ]
      }
    ]
  },
  "parameters": {
    "n": 1,
    "size": "2K",
    "watermark": false,
    "thinking_mode": true
  }
}'

{
  "output": {
    "choices": [
      {
        "finish_reason": "stop",
        "message": {
          "content": [
            {
              "image": "https://dashscope-result-intl.oss-cn-singapore.aliyuncs.com/xxx.png?Expires=xxx",
              "type": "image"
            }
          ],
          "role": "assistant"
        }
      }
    ],
    "finished": true
  },
  "usage": {
    "image_count": 1,
    "input_tokens": 18790,
    "output_tokens": 2,
    "size": "2985*1405",
    "total_tokens": 18792
  },
  "request_id": "a3f4befe-cacd-49c9-8298-xxxxxx"
}

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

This synchronous endpoint supports wan2.7-image-pro and wan2.7-image. Retrieve generated images directly in a single request without polling. For asynchronous processing, use the async submit endpoint.

Authorizations

string

header

required

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

Body

application/json

enum<string>

required

The model name. Valid values: wan2.7-image-pro, wan2.7-image.

Available options:wan2.7-image-pro,wan2.7-image

Example:wan2.7-image-pro

object

required

Input data containing the messages array.

Show child attributes

object[]

required

An array of request content. Currently, only single-turn conversations are supported. This means you can pass only one set of role and content parameters. Multi-turn conversations are not supported.

Required range:items: 1–1

Show child attributes

enum<string>

required

Message role. Must be user.

Available options:user

object[]

required

Message content array. Must contain exactly one text object and 0 to 9 image objects.

When using multiple images, include multiple image objects in the array. Image order is determined by array position.

Show child attributes

string

The user-entered prompt. Supports Chinese and English. The length cannot exceed 5,000 characters. Each Chinese character, letter, number, or symbol counts as one character. Any excess is automatically truncated. The content array must contain exactly one text object.

Example:Spray the graffiti from image 2 onto the car in image 1

Required range:length <= 5000

string

Input image as a public URL (HTTP/HTTPS) or Base64-encoded string (data:{mime_type};base64,{data}).

Image constraints:

Formats: JPEG, JPG, PNG (alpha channel not supported), BMP, WEBP.
Resolution: Width and height each between 240 and 8,000 pixels. Aspect ratio [1:8, 8:1].
File size: Max 20 MB.
Quantity: 0 to 9 images per request.

Example:https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20251229/pjeqdf/car.webp

object

Image processing parameters.

Show child attributes

string

Output image resolution. Two specification methods are available; they cannot be used together.

wan2.7-image-pro:

Method 1 (recommended): 1K, 2K (default), or 4K.
- Scope: Text-to-image (no image input, not generating an image set) supports 1K, 2K, and 4K. Other scenarios support 1K and 2K only.
- Total pixels: 1K = 1024×1024, 2K = 2048×2048, 4K = 4096×4096.
- Aspect ratio: With image input, output matches the aspect ratio of the last input image scaled to the selected resolution. Without image input, output is square.
Method 2: Specify width*height in pixels, aspect ratio [1:8, 8:1].
- Text-to-image: total pixels in [768×768, 4096×4096].
- Other scenarios: total pixels in [768×768, 2048×2048].

wan2.7-image:

Method 1 (recommended): 1K or 2K (default). 4K is not supported.
Method 2: Specify width*height in pixels. All scenarios: total pixels in [768×768, 2048×2048], aspect ratio [1:8, 8:1].

The pixel value of the output image may differ slightly from the specified value.

Example:2K

integer

default4

Number of images to generate.

Note: The value of n directly affects the cost. Cost = Unit Price × Number of successfully generated images.

When image set mode is disabled (enable_sequential=false): This value represents the number of images to generate. Range: 1–4. Default: 4.
When image set mode is enabled (enable_sequential=true): This value represents the maximum number of images to generate. Range: 1–12. Default: 12. The actual number is determined by the model and will not exceed n.

Required range:1 <= x <= 12

boolean

defaultfalse

Controls the image generation mode.

false: Default value.
true: Enables image set output mode.

boolean

defaulttrue

Specifies whether to enable thinking mode. The default is true (enabled). This parameter is effective only when image set mode is disabled and there is no image input. When enabled, the model enhances its inference capabilities to improve image quality, but this increases generation time.

integer[][][]

The selected area for interactive editing.

Correspondence: The length of the list must match the number of input images. If an image does not require editing, pass an empty list [] at the corresponding position.
Coordinate format: [x1, y1, x2, y2] (top-left x, top-left y, bottom-right x, bottom-right y). Use absolute pixel coordinates of the original image. The top-left coordinate is (0, 0).
Condition: A single image supports a maximum of 2 bounding boxes.

object[]

A custom color theme. An array of objects containing color (hex) and proportion (ratio). It must include 3 to 10 colors. We recommend setting it to 8. Available only when image set mode is disabled (enable_sequential=false).

Example:

[
  {
    "hex": "#C2D1E6",
    "ratio": "60.00%"
  },
  {
    "hex": "#636574",
    "ratio": "25.00%"
  },
  {
    "hex": "#CBD4E4",
    "ratio": "15.00%"
  }
]

Required range:items: 3–10

Show child attributes

string

required

The color value in hexadecimal (HEX) format. Example: #C2D1E6.

string

required

The percentage of the color. It must be accurate to two decimal places (for example, "25.00%"). The sum of all ratio values must be 100.00%.

boolean

defaultfalse

Adds a watermark label in the bottom-right corner of the image with fixed text "AI Generated".

integer

Random number seed. Valid range: [0, 2147483647]. Using the same seed yields similar outputs. If omitted, the algorithm uses a random seed. Note: Image generation is probabilistic. Even with the same seed, results may vary.

Required range:0 <= x <= 2147483647

Response

200-application/json

object

Show child attributes

object[]

List of generated results.

Show child attributes

string

Reason for generation completion.

Example:stop

object

Show child attributes

string

Example:assistant

object[]

Show child attributes

string

URL of the generated image. URLs expire in 24 hours. Download and save promptly.

Example:https://dashscope-result-intl.oss-cn-singapore.aliyuncs.com/xxx.png?Expires=xxx

string

Example:image

boolean

Whether the generation has completed.

object

Usage statistics.

Show child attributes

integer

Number of images generated.

integer

Number of input tokens consumed.

integer

Number of output tokens consumed.

integer

Total tokens consumed.

string

Actual output image dimensions (width×height).

Example:2985*1405

string

default"a3f4befe-cacd-49c9-8298-xxxxxx"

Unique request identifier.

Example:a3f4befe-cacd-49c9-8298-xxxxxx