Qwen — Generate an image

POST

/services/aigc/text2image/image-synthesis

curl -X POST https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/text2image/image-synthesis \
  -H 'X-DashScope-Async: enable' \
  -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "qwen-image-plus",
  "input": {
    "prompt": "Healing-style hand-drawn poster featuring three puppies playing with a ball on lush green grass."
  },
  "parameters": {
    "negative_prompt": "",
    "size": "1664*928",
    "n": 1,
    "prompt_extend": true,
    "watermark": false
  }
}'

{
  "output": {
    "task_status": "PENDING",
    "task_id": "0385dc79-5ff8-4d82-bcb6-xxxxxx"
  },
  "request_id": "4909100c-7b5a-9f92-bfe5-xxxxxx"
}

Get an API key and set it as an environment variable. If using the SDK, install it. This async endpoint is supported only by qwen-image-plus and qwen-image. All other models use the synchronous API.

Workflow

Submit a task via POST /services/aigc/text2image/image-synthesis with the X-DashScope-Async: enable header.
Poll for results via GET /tasks/{task_id} until task_status reaches SUCCEEDED or FAILED. Poll every 10 seconds.

Authorizations

string

header

required

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

Header Parameters

enum<string>

required

Must be set to enable for asynchronous task submission.

Available options:enable

Body

application/json

enum<string>

required

Model name. Only qwen-image-plus and qwen-image are supported for asynchronous calls.

Available options:qwen-image-plus,qwen-image

Example:qwen-image-plus

object

required

Input data.

Show child attributes

string

required

Positive prompt describing the desired content, style, and composition. Max 800 characters.

Example:A cute orange cat sitting on a windowsill, realistic style

Required range:length <= 800

string

Elements to exclude from the generated image. Max 500 characters.

Required range:length <= 500

object

Generation parameters for Qwen-Image async calls.

Show child attributes

enum<string>

default"1664*928"

Output resolution as width*height. Available sizes: 1664*928 (16:9, default), 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

Example:1664*928

enum<integer>

default1

Number of images. Fixed at 1. Other values cause an error.

Available options:1

boolean

defaulttrue

Enable smart prompt rewriting. true (default): model optimizes your prompt. false: use your prompt as-is.

boolean

defaultfalse

Add a "Qwen-Image" watermark to the bottom-right corner. Default: false.

integer

Random number seed. Range: [0, 2147483647]. Same seed produces more consistent (but not identical) results.

Required range:0 <= x <= 2147483647

Response

200-application/json

string

default"4909100c-7b5a-9f92-bfe5-xxxxxx"

Unique request identifier.

object

Show child attributes

string

Task ID for polling status. Use with GET /tasks/{task_id}.

enum<string>

Initial task status, typically PENDING.

Available options:PENDING,RUNNING,SUCCEEDED,FAILED

​Workflow

Authorizations

Header Parameters

Body

Response

Workflow