Skip to main content
Qwen

Qwen Image Generation and Editing 3.0 API Reference

The Qwen Image Generation and Editing 3.0 model supports both text-to-image (T2I) and image-to-image/image editing (I2I). It can generate images directly from text prompts or edit images based on 1-3 reference images combined with editing instructions.

Model overview

Model

Description

Output image specifications

qwen-image-3.0-pro

Qwen Image Generation and Editing 3.0 model that supports both text-to-image (T2I) and image-to-image/image editing (I2I).

Image resolution:

  • Text-to-image (T2I): Total pixels must be between 512*512 and 2048*2048.

  • Image-to-image (I2I): Total pixels must be between 512*512 and 2048*2048.

  • Default: When size is not specified, the model automatically recommends a resolution based on the prompt.

Image format: PNG

qwen-image-3.0

Qwen Image Generation and Editing 3.0 standard model that supports both text-to-image (T2I) and image-to-image/image editing (I2I). Balances quality and speed.

Availability

The model, endpoint URL, and API key must belong to the same region. Cross-region calls fail.
The sample code in this topic applies to the Singapore region.
Alibaba Cloud Model Studio has released workspace-specific domains for the China (Beijing) and Singapore regions. The new dedicated domains deliver superior performance and higher stability for inference requests. We recommend migrating to the new domains:
  • China (Beijing): from https://dashscope.aliyuncs.com to https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com
  • Singapore: from https://dashscope-intl.aliyuncs.com to https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com
{WorkspaceId} is your workspace ID, which can be found on the Workspace Details page in the Alibaba Cloud Model Studio console. The existing domain remains fully functional.

HTTP

  • Singapore
  • China (Beijing)
  • China (Hong Kong)
  • Germany (Frankfurt)
  • Japan (Tokyo)
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
Replace {WorkspaceId} with your actual workspace ID.

Request parameters

Headers
Content-Type string (Required)The content type of the request. Must be application/json.Authorization string (Required)Authenticates the request with a Model Studio API key. Example: Bearer sk-xxxx.
Request body
model string (Required)The model name. Available values: qwen-image-3.0-pro and qwen-image-3.0.input object (Required)The input parameter object, which contains the following fields:

Properties

messages array (Required)The request content array. Only single-round conversations are supported, so the array must contain exactly one object with role and content properties.

Properties

rolestring (Required)The role of the message sender. Must be set to user.contentarray (Required)The message content array, with different combinations depending on the use case:
  • Text-to-image (T2I): Contains only one {"text": "..."} object.
  • Image-to-image (I2I): Contains 1-3 {"image": "..."} objects and 1 {"text": "..."} object.

Properties

image string (Required for I2I)The URL or Base64 encoded data of the input image. In I2I scenarios, 1-3 images are supported. When multiple images are provided, the order is defined by the array sequence.Image requirements:
  • Image format: JPG, JPEG, PNG, BMP, TIFF, WEBP, and GIF.
  • Image resolution: The width and height should be between 384 and 2048 pixels for best results.
  • Image size: Up to 10 MB.
Supported input formats
  1. Public URL: HTTP and HTTPS protocols are supported.
  2. Base64 encoding: Format is data:{MIME_type};base64,{base64_data}.
textstring(Required)The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported. Recommended maximum: 4,500 tokens.Note: Only one text object is allowed. Omitting it or providing multiple text objects will result in an error.
parameters object (Optional)Additional parameters to control image generation.

Properties

prompt_extend boolean (Optional)Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt using the method specified by prompt_extend_mode, which significantly improves results for simple descriptions.prompt_extend_mode string (Optional)The prompt rewriting method. Default: direct. Options:
  • direct: Direct Prompt Enhancement (DPE), suitable for most scenarios. Supported for both T2I and I2I.
  • agent: Agent Prompt Enhancement (APE), provides more refined rewriting. Only supports text-to-image (T2I). Passing agent for image-to-image (I2I) will return a 400 error.
enable_thinking boolean (Optional)Enables thinking mode. The default is true. This enhances model reasoning to improve image quality, but increases generation time. It requires prompt_extend=true. Supported for Direct T2I, Direct I2I, and Agent T2I. Not supported for I2I Agent.n integer (Optional)The number of output images.Value range: 1 to 6. Default: 1.size string (Optional)The output image resolution in the format width*height, for example "1024*1024". If not specified, the model automatically recommends a resolution based on the prompt.
  • Text-to-image (T2I): Pixel area from 512512 to 20482048. Aspect ratio: 1:8 to 8:1.
  • Image-to-image (I2I): Pixel area from 512512 to 20482048. Aspect ratio: 1:8 to 8:1.
negative_prompt string (Optional)The negative prompt that describes content you do not want to appear in the image.seed integer (Optional)The random seed. Value range: [0, 2147483647]. If omitted, the service generates a random seed. Use a fixed seed for reproducible results.watermark boolean (Optional)Whether to add a watermark. Default: false.
curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
--header 'Content-Type: application/json' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--data '{
    "model": "qwen-image-3.0-pro",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "text": "A vertical outdoor portrait photograph with a warm afternoon street atmosphere. Deep green vines and small orange flowers cascade from building eaves across the upper area. A dark blue sign reads '\''Il Messaggero'\'' in white Gothic lettering, partially obscured by foliage. Below, a newsstand displays newspapers behind black metal-framed glass, blurred by shallow depth of field. Strong backlight streams from the street'\''s end. Center-right, a young woman in a black spaghetti-strap backless dress looks back at the camera with a warm smile. Her long, thick wavy black hair is outlined by golden rim light. She has fair skin, bright eyes, soft coral-red lips, and holds a large bouquet of orange, apricot, pink and peach roses contrasting with her black dress. The sunlit city street stretches into the blurred background. Warm film-like tones with fine grain, soft contrast and pronounced backlit edge glow create a romantic, bright, urban strolling atmosphere."
                    }
                ]
            }
        ]
    },
    "parameters": {
        "prompt_extend": true
    }
}'

Response parameters

output objectContains the model generation results.

Properties

rewrite_status stringThe prompt rewriting status. The value depends on whether rewriting was enabled in the request and the result of the rewrite.choices arrayThe list of result options.

Properties

finish_reason stringThe reason why the task stopped. The value is stop when the task completes normally.message objectThe message returned by the model.

Properties

rolestringThe role of the message. Fixed as assistant.contentarrayThe message content containing the generated image information.

Properties

image stringThe URL of the generated image in PNG format. The link is valid for 24 hours. Please download and save the image promptly.
usage objectThe resource usage of this call. Only returned on success.

Properties

output_width integerThe width of the final output image in pixels.output_height integerThe height of the final output image in pixels.input_image_count integerThe number of input images in the request. Returns 0 for text-to-image (T2I), and the actual count for image-to-image (I2I).input_image_type stringThe input image billing tier. Determined by the output resolution pixel area: qima_input_1k if area ≤ 2,250,000, or qima_input_2k if area > 2,250,000.output_image_count integerThe actual number of output images returned.output_image_type stringThe output image billing tier. Determined by the output resolution pixel area: qima_output_1k if area ≤ 2,250,000, or qima_output_2k if area > 2,250,000.
request_id stringUnique request identifier for tracing and troubleshooting.code stringError code. Returned only for failed requests. See Error codes.message stringDetailed error message. Returned only for failed requests. See Error codes.
  • Success
  • Error
Task data (task status and image URLs) is retained for only 24 hours and then automatically purged. Save generated images promptly.
{
    "output": {
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "content": [
                        {
                            "image": "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx"
                        }
                    ],
                    "role": "assistant"
                }
            }
        ]
    },
    "usage": {
        "output_height": 1024,
        "output_width": 1024,
        "input_image_count": 1,
        "input_image_type": "qima_input_1k",
        "output_image_count": 1,
        "output_image_type": "qima_output_1k"
    },
    "request_id": "571ae02f-5c9d-436c-83c2-f221e6df0xxx"
}

SDK

The following examples demonstrate how to call the API using Python and Java SDKs for image-to-image / image editing (I2I).
Python
import os
import base64
import mimetypes
import dashscope
from dashscope import MultiModalConversation

dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

def encode_file(file_path):
    mime_type, _ = mimetypes.guess_type(file_path)
    if not mime_type or not mime_type.startswith("image/"):
        raise ValueError("Unsupported or unrecognized image format")
    with open(file_path, "rb") as image_file:
        encoded_string = base64.b64encode(image_file.read()).decode('utf-8')
    return f"data:{mime_type};base64,{encoded_string}"

# [Method 1] Use a public image URL
image_url = "https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/res/yBRq1ZPYEaXdyOdv/img/33a80a19-7ac7-4c64-b0fa-7d685b7046a0.png"

# [Method 2] Use a Base64-encoded image
# image_url = encode_file("./your_image.png")

response = MultiModalConversation.call(
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen-image-3.0-pro",
    messages=[{
        "role": "user",
        "content": [
            {"image": image_url},
            {"text": "Generate a sophisticated urban-style female portrait. Perfectly preserve the facial features and smooth black long hair of the young woman in the input image. Change her outfit to an elegant urban professional look. Set the scene in a modern minimalist upscale coffee shop."}
        ]
    }],
    prompt_extend=True
)

print(response)
if response.status_code == 200:
    url = response.output.choices[0].message.content[0]["image"]
    print(f"Generated image URL: {url}")
else:
    print(f"Error: {response.code} - {response.message}")

Asynchronous API

In addition to the synchronous call described above, Qwen Image Generation and Editing 3.0 also supports asynchronous calls. The asynchronous API shares the same request parameter structure as the synchronous API. You only need to add the X-DashScope-Async: enable header. After the service accepts the request, it returns a task ID (task_id), which you then use to poll the query API for the final result.
The endpoint for the asynchronous API differs from the synchronous API. Use the endpoints in this section instead of the synchronous endpoint.

HTTP

Asynchronous calls use a two-step workflow:
  1. Create a task to get a task ID: Send a request to create a task. The response contains a task ID (task_id).
  2. Poll for results using the task ID: Use the task_id to poll the task status until the task completes and the image URL is returned.

Step 1: Create a task to get a task ID

  • Singapore
  • China (Beijing)
  • China (Hong Kong)
  • Germany (Frankfurt)
  • Japan (Tokyo)
POST https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/services/aigc/image-generation/generation
Request parameters
Headers
Content-Type string (Required)The content type of the request. Must be application/json.Authorization string (Required)Authenticates the request with a Model Studio API key. Example: Bearer sk-xxxx.X-DashScope-Async string (Required)Enables asynchronous processing. HTTP requests support only asynchronous calls. Must be enable.
If this request header is missing, the error "current user api does not support synchronous calls" is returned.
Request body
model string (Required)The model name. Available values: qwen-image-3.0-pro and qwen-image-3.0.input object (Required)The input parameter object, which contains the following fields:

Properties

messages array (Required)The request content array. Only single-round conversations are supported, so the array must contain exactly one object with role and content properties.

Properties

rolestring (Required)The role of the message sender. Must be set to user.contentarray (Required)The message content array, with different combinations depending on the use case:
  • Text-to-image (T2I): Contains only one {"text": "..."} object.
  • Image-to-image (I2I): Contains 1-3 {"image": "..."} objects and 1 {"text": "..."} object.

Properties

image string (Required for I2I)The URL or Base64 encoded data of the input image. In I2I scenarios, 1-3 images are supported. When multiple images are provided, the order is defined by the array sequence.Image requirements:
  • Image format: JPG, JPEG, PNG, BMP, TIFF, WEBP, and GIF.
  • Image resolution: The width and height should be between 384 and 2048 pixels for best results.
  • Image size: Up to 10 MB.
Supported input formats
  1. Public URL: HTTP and HTTPS protocols are supported.
  2. Base64 encoding: Format is data:{MIME_type};base64,{base64_data}.
textstring(Required)The positive prompt that describes the image content, style, and composition you want to generate or edit. Both Chinese and English are supported. Recommended maximum: 4,500 tokens.Note: Only one text object is allowed. Omitting it or providing multiple text objects will result in an error.
parameters object (Optional)Additional parameters to control image generation.

Properties

prompt_extend boolean (Optional)Whether to enable intelligent prompt rewriting. Default: true (recommended). When enabled, the model optimizes the positive prompt using the method specified by prompt_extend_mode, which significantly improves results for simple descriptions.prompt_extend_mode string (Optional)The prompt rewriting method. Default: direct. Options:
  • direct: Direct Prompt Enhancement (DPE), suitable for most scenarios. Supported for both T2I and I2I.
  • agent: Agent Prompt Enhancement (APE), provides more refined rewriting. Only supports text-to-image (T2I). Passing agent for image-to-image (I2I) will return a 400 error.
enable_thinking boolean (Optional)Enables thinking mode. The default is true. This enhances model reasoning to improve image quality, but increases generation time. It requires prompt_extend=true. Supported for Direct T2I, Direct I2I, and Agent T2I. Not supported for I2I Agent.n integer (Optional)The number of output images.Value range: 1 to 6. Default: 1.size string (Optional)The output image resolution in the format width*height, for example "1024*1024". If not specified, the model automatically recommends a resolution based on the prompt.
  • Text-to-image (T2I): Pixel area from 512512 to 20482048. Aspect ratio: 1:8 to 8:1.
  • Image-to-image (I2I): Pixel area from 512512 to 20482048. Aspect ratio: 1:8 to 8:1.
negative_prompt string (Optional)The negative prompt that describes content you do not want to appear in the image.seed integer (Optional)The random seed. Value range: [0, 2147483647]. If omitted, the service generates a random seed. Use a fixed seed for reproducible results.watermark boolean (Optional)Whether to add a watermark. Default: false.
curl --location 'https://{WorkspaceId}.ap-southeast-1.maas.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": "qwen-image-3.0-pro",
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "text": "A vertical outdoor portrait photograph with a warm afternoon street atmosphere. Deep green vines and small orange flowers cascade from building eaves across the upper area. A dark blue sign reads '\''Il Messaggero'\'' in white Gothic lettering, partially obscured by foliage. Below, a newsstand displays newspapers behind black metal-framed glass, blurred by shallow depth of field. Strong backlight streams from the street'\''s end. Center-right, a young woman in a black spaghetti-strap backless dress looks back at the camera with a warm smile. Her long, thick wavy black hair is outlined by golden rim light. She has fair skin, bright eyes, soft coral-red lips, and holds a large bouquet of orange, apricot, pink and peach roses contrasting with her black dress. The sunlit city street stretches into the blurred background. Warm film-like tones with fine grain, soft contrast and pronounced backlit edge glow create a romantic, bright, urban strolling atmosphere."
                    }
                ]
            }
        ]
    },
    "parameters": {
        "prompt_extend": true
    }
}'
Response parameters
output objectThe task acceptance information.

Properties

task_id stringThe asynchronous task ID, used to query the task status and result. Make sure to save it.task_status stringThe task status. Usually PENDING when the task is submitted, indicating only that the task has been accepted, not that the image has been generated.
request_id stringUnique request identifier for tracing and troubleshooting.code stringError code. Returned only for failed requests. See Error codes.
  • Successful response
  • Error response
Save the task_id to query the task status and result.
{
    "output": {
        "task_status": "PENDING",
        "task_id": "0385dc79-5ff8-4d82-bcb6-xxxxxx"
    },
    "request_id": "4909100c-7b5a-9f92-bfe5-xxxxxx"
}

Step 2: Poll for results using the task ID

  • Singapore
  • China (Beijing)
  • China (Hong Kong)
  • Germany (Frankfurt)
  • Japan (Tokyo)
GET https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/tasks/{task_id}
You must use the same region, workspace, and API key as when you created the task. Cross-region or cross-workspace queries are not supported.
Request parameters
Headers
Authorization string (Required)Authenticates the request with a Model Studio API key. Example: Bearer sk-xxxx.
URL path parameters
task_id string (Required)The ID of the task.
  • Query task result
Replace {task_id} with the task_id value returned by the previous API call. The task_id is valid for queries for 24 hours, Replace {WorkspaceId} with your actual workspace ID.
curl -X GET https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1/tasks/{task_id} \
--header "Authorization: Bearer $DASHSCOPE_API_KEY"
Response parameters
output objectThe task output information.

Properties

task_id stringThe task ID. Valid for queries for 24 hours.task_status stringThe status of the task.

Enumeration values

  • PENDING
  • RUNNING
  • SUCCEEDED
  • FAILED
  • CANCELED
  • UNKNOWN: The task does not exist or its status is unknown.
State transitions during polling:
  • PENDING → RUNNING → SUCCEEDED or FAILED.
  • The initial query status is usually PENDING or RUNNING.
  • When the status changes to SUCCEEDED, the response contains the generated image URL.
  • If the status is FAILED, check the error message and retry the task.
submit_time stringThe time when the task was submitted. The time is in UTC+8 and the format is YYYY-MM-DD HH:mm:ss.SSS.scheduled_time stringThe time when the task was executed. The time is in UTC+8 and the format is YYYY-MM-DD HH:mm:ss.SSS.end_time stringThe time when the task was completed. The time is in UTC+8 and the format is YYYY-MM-DD HH:mm:ss.SSS.rewrite_status stringThe prompt rewriting status. The value depends on whether rewriting was enabled in the request and the result of the rewrite.choices arrayThe list of result options.

Properties

finish_reason stringThe reason why the task stopped. The value is stop when the task completes normally.message objectThe message returned by the model.

Properties

rolestringThe role of the message. Fixed as assistant.contentarrayThe message content containing the generated image information.

Properties

image stringThe URL of the generated image in PNG format. The link is valid for 24 hours. Please download and save the image promptly.
usage objectThe resource usage of this call. Only returned on success.

Properties

output_width integerThe width of the final output image in pixels.output_height integerThe height of the final output image in pixels.input_image_count integerThe number of input images in the request. Returns 0 for text-to-image (T2I), and the actual count for image-to-image (I2I).input_image_type stringThe input image billing tier. Determined by the output resolution pixel area: qima_input_1k if area ≤ 2,250,000, or qima_input_2k if area > 2,250,000.output_image_count integerThe actual number of output images returned.output_image_type stringThe output image billing tier. Determined by the output resolution pixel area: qima_output_1k if area ≤ 2,250,000, or qima_output_2k if area > 2,250,000.
request_id stringUnique request identifier for tracing and troubleshooting.code stringError code. Returned only for failed requests. See Error codes.message stringDetailed error message. Returned only for failed requests. See Error codes.
  • Task succeeded
  • Task failed
Task data (task status and image URLs) is retained for only 24 hours and then automatically purged. Save generated images promptly.
{
    "output": {
        "task_id": "17d7d840-82b9-485b-a954-724d06bc88d2",
        "task_status": "SUCCEEDED",
        "submit_time": "2026-08-07 15:50:14.837",
        "scheduled_time": "2026-08-07 15:50:14.884",
        "end_time": "2026-08-07 15:50:33.607",
        "rewrite_status": "not_use",
        "choices": [
            {
                "finish_reason": "stop",
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "image": "https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx",
                            "type": "image"
                        }
                    ]
                }
            }
        ]
    },
    "usage": {
        "output_height": 1024,
        "output_width": 1024,
        "input_image_count": 0,
        "input_image_type": "qima_input_1k",
        "output_image_count": 1,
        "output_image_type": "qima_output_1k"
    },
    "request_id": "2bd94002-5624-9129-916b-fbdde107b4ba"
}

Error codes

If the model call fails and returns an error message, see Error codes for resolution.