Wan v2 — Generate an image

POST

/services/aigc/image-generation/generation

curl --location 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/image-generation/generation' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header 'X-DashScope-Async: enable' \
--data '{
  "model": "wan2.6-t2i",
  "input": {
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "text": "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display"
          }
        ]
      }
    ]
  },
  "parameters": {
    "prompt_extend": true,
    "watermark": false,
    "n": 1,
    "negative_prompt": "",
    "size": "1280*1280"
  }
}'

{
  "request_id": "<string>",
  "output": {
    "task_id": "<string>",
    "task_status": "PENDING"
  }
}

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

Supported models

The Wan text-to-image family uses different endpoints and request formats by version:

Model	Endpoint	Input format	Resolution	Max prompt length
`wan2.6-t2i`	`/services/aigc/image-generation/generation`	`messages` array	12801280 to 14401440, ratio 1:4 to 4:1	2,100 chars
`wan2.5-t2i-preview`	`/services/aigc/text2image/image-synthesis`	`prompt` string	12801280 to 14401440, ratio 1:4 to 4:1	2,000 chars
`wan2.2-t2i-plus`	`/services/aigc/text2image/image-synthesis`	`prompt` string	512–1440 per side, max 1440*1440	500 chars
`wan2.2-t2i-flash`	`/services/aigc/text2image/image-synthesis`	`prompt` string	512–1440 per side, max 1440*1440	500 chars
`wan2.1-t2i-plus`	`/services/aigc/text2image/image-synthesis`	`prompt` string	512–1440 per side, max 1440*1440	500 chars
`wan2.1-t2i-turbo`	`/services/aigc/text2image/image-synthesis`	`prompt` string	512–1440 per side, max 1440*1440	500 chars
`wanx2.0-t2i-turbo`	`/services/aigc/text2image/image-synthesis`	`prompt` string	512–1440 per side, max 1440*1440	800 chars

wan2.6-t2i also supports a synchronous endpoint (single-request, immediate response).

SDK version requirements

wan2.6-t2i: DashScope Python SDK 1.25.7+, Java SDK 2.22.6+
wan2.5 and earlier: DashScope Python SDK 1.25.2+, Java SDK 2.22.2+

Authorizations

string

header

required

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

Header Parameters

enum<string>

required

Must be enable to create an asynchronous task.

Available options:enable

Body

application/json

object

enum<string>

required

The model name. For the wan2.6-t2i model, use wan2.6-t2i.

Available options:wan2.6-t2i

Example:wan2.6-t2i

object

required

The input object containing the message array.

Show child attributes

object[]

required

An array for the request content. Only single-turn conversations are supported (one set of role and content).

Show child attributes

enum<string>

required

The role of the message. Must be user.

Available options:user

object[]

required

An array for the message content.

Show child attributes

string

required

The positive prompt describing the content, style, and composition of the image to generate. Chinese and English are supported. Maximum 2,100 characters. Only one text is allowed per request.

Example:A flower shop with exquisite windows, a beautiful wooden door, and flowers on display

object

Parameters for wan2.6-t2i model.

Show child attributes

string

Optional. Describes content you do not want in the image. Maximum 500 characters. Chinese and English supported. Example: low resolution, low quality, deformed limbs, deformed fingers, oversaturated, waxy, no facial details, overly smooth, AI-like, chaotic composition, blurry text, distorted text.

string

default"1280*1280"

The resolution of the output image in width*height format. Default: 1280*1280. The total number of pixels must be between 12801280 and 14401440, and the aspect ratio must be between 1:4 and 4:1. Recommended resolutions: 1:1 (12801280), 3:4 (11041472), 4:3 (14721104), 9:16 (9601696), 16:9 (1696*960).

Example:1280*1280

integer

default4

The number of images to generate. Value: 1 to 4. Default: 4. Note: billing is per image (Cost = Unit price x Number of images). Set to 1 for testing.

Required range:1 <= x <= 4

boolean

defaulttrue

Whether to enable prompt rewriting. When enabled, this feature uses an LLM to optimize the positive prompt, significantly improving results for shorter prompts but adding a few seconds to processing time. Default: true.

boolean

defaultfalse

Whether to add a watermark in the lower-right corner of the image with the text "AI-generated". Default: false.

integer

Optional. Random number seed. Range: [0, 2147483647]. Using the same seed produces more consistent results, but identical results are not guaranteed. If not provided, the system uses a random number.

Required range:0 <= x <= 2147483647

Response

200-application/json

string

Unique request identifier for troubleshooting.

object

Show child attributes

string

The task identifier. Use this to query the task status via GET /tasks/{task_id}. Valid for 24 hours.

enum<string>

The initial task status. Typically PENDING.

Available options:PENDING

​Supported models

​SDK version requirements

Authorizations

Header Parameters

Body

Response

Supported models

SDK version requirements