Wan v2 - Gere uma imagem

Assíncrono Wan geração de imagem

Obtenha uma chave de API e defini-lo como uma variável de ambiente. Se estiver usando o SDK, instale-o.

Modelos suportados

O Wan A família de texto para imagem usa diferentes endpoints e formatos de solicitação por versão:

wan2.6-t2i também suporta um endpoint síncrono (solicitação única, resposta imediata).

Requisitos de versão do SDK

• wan2.6-t2i: SDK Python do DashScope 1.25.7+, SDK Java 2.22.6+
• wan2.5 e anteriores: DashScope Python SDK 1.25.2+, Java SDK 2.22.2+

OpenAPI

openapi: 3.1.0
info:
  title: Wan Text-to-Image V2 API
  description: "Generate images from text prompts using the Wan text-to-image model family. Supports various artistic styles and realistic photographic effects to meet diverse creative needs. This API uses an asynchronous task pattern: submit a task with POST, then poll for results with GET."
  version: 1.0.0
servers:
  - url: https://maas.qwencloudapi.com/api/v1
    description: Singapore
security:
  - BearerAuth: []
paths:
  /services/aigc/image-generation/generation:
    post:
      operationId: createWanTextToImage
      summary: Create text-to-image task
      description: Create a text-to-image generation task.
      parameters:
        - name: X-DashScope-Async
          in: header
          required: true
          description: Must be `enable` to create an asynchronous task.
          schema:
            type: string
            enum:
              - enable
      requestBody:
        required: true
        content:
          application/json:
            schema:
              oneOf:
                - $ref: "#/components/schemas/Wan26TextToImageRequest"
                - $ref: "#/components/schemas/WanLegacyTextToImageRequest"
      responses:
        "200":
          description: Task created successfully.
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/AsyncTaskSubmitResponse"
        "400":
          description: Invalid request parameters.
          content:
            application/json:
              schema:
                $ref: "#/components/schemas/DashScopeErrorResponse"
      x-codeSamples:
        - lang: curl
          label: cURL - wan2.6-t2i (async)
          source: |-
            curl --location 'https://maas.qwencloudapi.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"
              }
            }'
        - lang: curl
          label: cURL - wan2.5-t2i-preview (async, legacy endpoint)
          source: |-
            # Note: wan2.5 and earlier models use a different endpoint path:
            # POST /services/aigc/text2image/image-synthesis
            curl -X POST https://maas.qwencloudapi.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": "wan2.5-t2i-preview",
              "input": {
                "prompt": "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display"
              },
              "parameters": {
                "size": "1280*1280",
                "n": 1
              }
            }'
        - lang: curl
          label: cURL - wan2.2-t2i-flash with negative prompt (async, legacy endpoint)
          source: |-
            # Note: wan2.2 and earlier models use a different endpoint path:
            # POST /services/aigc/text2image/image-synthesis
            curl -X POST https://maas.qwencloudapi.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": "wan2.2-t2i-flash",
              "input": {
                "prompt": "Snowy ground, a small white chapel, aurora borealis, winter scene, soft light.",
                "negative_prompt": "person"
              },
              "parameters": {
                "size": "1024*1024",
                "n": 1
              }
            }'
        - lang: python
          label: Python - wan2.6-t2i (async, DashScope SDK)
          source: |-
            import os
            import dashscope
            from dashscope.aigc.image_generation import ImageGeneration
            from dashscope.api_entities.dashscope_response import Role, Message
            from http import HTTPStatus

            # SDK version 1.25.7 or later is required for wan2.6-t2i
            dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
            api_key = os.getenv("DASHSCOPE_API_KEY")

            # Create an asynchronous task
            def create_async_task():
              print("Creating async task...")
              message = Message(
                role="user",
                content=[{'text': 'A flower shop with exquisite windows, a beautiful wooden door, and flowers on display'}]
              )
              response = ImageGeneration.async_call(
                model="wan2.6-t2i",
                api_key=api_key,
                messages=[message],
                negative_prompt="",
                prompt_extend=True,
                watermark=False,
                n=1,
                size="1280*1280"
              )

              if response.status_code == 200:
                print("Task created successfully:", response)
                return response
              else:
                raise Exception(f"Failed to create task: {response.code} - {response.message}")

            # Wait for the task to complete
            def wait_for_completion(task_response):
              print("Waiting for task completion...")
              status = ImageGeneration.wait(task=task_response, api_key=api_key)

              if status.output.task_status == "SUCCEEDED":
                print("Task succeeded!")
                print("Response:", status)
              else:
                raise Exception(f"Task failed with status: {status.output.task_status}")

            # Get asynchronous task information
            def fetch_task_status(task):
              print("Fetching task status...")
              status = ImageGeneration.fetch(task=task, api_key=api_key)

              if status.status_code == HTTPStatus.OK:
                print("Task status:", status.output.task_status)
                print("Response details:", status)
              else:
                print(f"Failed to fetch status: {status.code} - {status.message}")

            # Cancel the asynchronous task
            def cancel_task(task):
              print("Canceling task...")
              response = ImageGeneration.cancel(task=task, api_key=api_key)

              if response.status_code == HTTPStatus.OK:
                print("Task canceled successfully:", response.output.task_status)
              else:
                print(f"Failed to cancel task: {response.code} - {response.message}")

            # Main execution flow
            if __name__ == "__main__":
              task = create_async_task()
              wait_for_completion(task)
        - lang: python
          label: Python - wan2.5 and earlier (sync, DashScope SDK)
          source: |-
            from http import HTTPStatus
            from urllib.parse import urlparse, unquote
            from pathlib import PurePosixPath
            import requests
            from dashscope import ImageSynthesis
            import os
            import dashscope

            # SDK version 1.25.2 or later is required for wan2.5 and earlier models
            dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
            api_key = os.getenv("DASHSCOPE_API_KEY")

            print('----sync call, please wait a moment----')
            rsp = ImageSynthesis.call(api_key=api_key,
                                      model="wan2.5-t2i-preview",
                                      prompt="A flower shop with exquisite windows, a beautiful wooden door, and flowers on display",
                                      negative_prompt="",
                                      n=1,
                                      size='1280*1280',
                                      prompt_extend=True,
                                      watermark=False,
                                      seed=12345)
            print('response: %s' % rsp)
            if rsp.status_code == HTTPStatus.OK:
              # Save the image to the current directory
              for result in rsp.output.results:
                file_name = PurePosixPath(unquote(urlparse(result.url).path)).parts[-1]
                with open('./%s' % file_name, 'wb+') as f:
                  f.write(requests.get(result.url).content)
            else:
              print('sync_call Failed, status_code: %s, code: %s, message: %s' %
                      (rsp.status_code, rsp.code, rsp.message))
        - lang: python
          label: Python - wan2.5 and earlier (async, DashScope SDK)
          source: |-
            from http import HTTPStatus
            from urllib.parse import urlparse, unquote
            from pathlib import PurePosixPath
            import requests
            from dashscope import ImageSynthesis
            import os
            import dashscope

            # SDK version 1.25.2 or later is required for wan2.5 and earlier models
            dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
            api_key = os.getenv("DASHSCOPE_API_KEY")

            def async_call():
              print('----create task----')
              task_info = create_async_task()
              print('----wait task done then save image----')
              wait_async_task(task_info)

            # Create an asynchronous task
            def create_async_task():
              rsp = ImageSynthesis.async_call(api_key=api_key,
                              model="wan2.5-t2i-preview",
                              prompt="A flower shop with exquisite windows, a beautiful wooden door, and flowers on display",
                              negative_prompt="",
                              n=1,
                              size='1280*1280',
                              prompt_extend=True,
                              watermark=False,
                              seed=12345)
              print(rsp)
              if rsp.status_code == HTTPStatus.OK:
                print(rsp.output)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                          (rsp.status_code, rsp.code, rsp.message))
              return rsp

            # Wait for the asynchronous task to complete
            def wait_async_task(task):
              rsp = ImageSynthesis.wait(task=task, api_key=api_key)
              print(rsp)
              if rsp.status_code == HTTPStatus.OK:
                print(rsp.output)
                # save file to current directory
                for result in rsp.output.results:
                  file_name = PurePosixPath(unquote(urlparse(result.url).path)).parts[-1]
                  with open('./%s' % file_name, 'wb+') as f:
                    f.write(requests.get(result.url).content)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                          (rsp.status_code, rsp.code, rsp.message))

            # Get asynchronous task information
            def fetch_task_status(task):
              status = ImageSynthesis.fetch(task=task, api_key=api_key)
              print(status)
              if status.status_code == HTTPStatus.OK:
                print(status.output.task_status)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                          (status.status_code, status.code, status.message))

            # Cancel the asynchronous task. Only tasks in the PENDING state can be canceled.
            def cancel_task(task):
              rsp = ImageSynthesis.cancel(task=task, api_key=api_key)
              print(rsp)
              if rsp.status_code == HTTPStatus.OK:
                print(rsp.output.task_status)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                          (rsp.status_code, rsp.code, rsp.message))

            if __name__ == '__main__':
              async_call()
        - lang: java
          label: Java - wan2.6-t2i (async, DashScope SDK)
          source: |-
            import com.alibaba.dashscope.aigc.imagegeneration.*;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.exception.UploadFileException;
            import com.alibaba.dashscope.utils.Constants;
            import com.alibaba.dashscope.utils.JsonUtils;
            import java.util.Collections;

            public class Main {

              static {
                    Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
              }

              // SDK version 2.22.6 or later is required for wan2.6-t2i
              static String apiKey = System.getenv("DASHSCOPE_API_KEY");

              public static void asyncCall() throws ApiException, NoApiKeyException, UploadFileException {
                ImageGenerationMessage message = ImageGenerationMessage.builder()
                    .role("user")
                    .content(Collections.singletonList(
                        Collections.singletonMap("text", "A flower shop with exquisite windows, a beautiful wooden door, and flowers on display")
                    )).build();

                ImageGenerationParam param = ImageGenerationParam.builder()
                    .apiKey(apiKey)
                    .model("wan2.6-t2i")
                    .n(1)
                    .size("1280*1280")
                    .negativePrompt("")
                    .promptExtend(true)
                    .watermark(false)
                    .messages(Collections.singletonList(message))
                    .build();

                ImageGeneration imageGeneration = new ImageGeneration();
                ImageGenerationResult result = null;
                try {
                  System.out.println("---async call, creating task----");
                  result = imageGeneration.asyncCall(param);
                } catch (ApiException | NoApiKeyException | UploadFileException e) {
                  throw new RuntimeException(e.getMessage());
                }
                System.out.println(JsonUtils.toJson(result));

                String taskId = result.getOutput().getTaskId();
                // Wait for the task to complete
                waitTask(taskId);
              }

              public static void waitTask(String taskId) throws ApiException, NoApiKeyException {
                ImageGeneration imageGeneration = new ImageGeneration();
                ImageGenerationResult result = imageGeneration.wait(taskId, apiKey);
                System.out.println(JsonUtils.toJson(result));
              }

              public static void main(String[] args) {
                try {
                  asyncCall();
                } catch (ApiException | NoApiKeyException | UploadFileException e) {
                  System.out.println(e.getMessage());
                }
              }
            }
        - lang: java
          label: Java - wan2.5 and earlier (sync, DashScope SDK)
          source: |-
            // Copyright (c) Alibaba, Inc. and its affiliates.

            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesis;
            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesisListResult;
            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesisParam;
            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesisResult;
            import com.alibaba.dashscope.task.AsyncTaskListParam;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.utils.Constants;
            import com.alibaba.dashscope.utils.JsonUtils;

            import java.util.HashMap;
            import java.util.Map;

            public class Main {

              static {
                 // SDK version 2.22.2 or later is required for wan2.5 and earlier models.
                 Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
              }

              static String apiKey = System.getenv("DASHSCOPE_API_KEY");

              public static void basicCall() throws ApiException, NoApiKeyException {
                    // Set parameters
                    Map<String, Object> parameters = new HashMap<>();
                    parameters.put("prompt_extend", true);
                    parameters.put("watermark", false);
                    parameters.put("seed", 12345);

                    ImageSynthesisParam param =
                            ImageSynthesisParam.builder()
                                    .apiKey(apiKey)
                                    .model("wan2.5-t2i-preview")
                                    .prompt("A flower shop with exquisite windows, a beautiful wooden door, and flowers on display")
                                    .n(1)
                                    .size("1280*1280")
                                    .negativePrompt("")
                                    .parameters(parameters)
                                    .build();

                    ImageSynthesis imageSynthesis = new ImageSynthesis();
                    ImageSynthesisResult result = null;
                    try {
                        System.out.println("---sync call, please wait a moment----");
                        result = imageSynthesis.call(param);
                    } catch (ApiException | NoApiKeyException e){
                        throw new RuntimeException(e.getMessage());
                    }
                    System.out.println(JsonUtils.toJson(result));
                }

                public static void main(String[] args){
                    try{
                        basicCall();
                    }catch(ApiException|NoApiKeyException e){
                        System.out.println(e.getMessage());
                    }
                }
            }
        - lang: java
          label: Java - wan2.5 and earlier (async, DashScope SDK)
          source: |-
            // Copyright (c) Alibaba, Inc. and its affiliates.

            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesis;
            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesisParam;
            import com.alibaba.dashscope.aigc.imagesynthesis.ImageSynthesisResult;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.utils.Constants;
            import com.alibaba.dashscope.utils.JsonUtils;

            import java.util.HashMap;
            import java.util.Map;

            public class Main {
              static {
                // SDK version 2.22.2 or later is required for wan2.5 and earlier models.
                Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
              }

              static String apiKey = System.getenv("DASHSCOPE_API_KEY");

              public void asyncCall() {
                System.out.println("---create task----");
                String taskId = this.createAsyncTask();
                System.out.println("---wait task done then return image url----");
                this.waitAsyncTask(taskId);
              }

              /**
                 * Create an asynchronous task
                 * @return taskId
                 */
              public String createAsyncTask() {
                // Set parameters
                Map<String, Object> parameters = new HashMap<>();
                parameters.put("prompt_extend", true);
                parameters.put("watermark", false);
                parameters.put("seed", 12345);

                ImageSynthesisParam param =
                    ImageSynthesisParam.builder()
                        .apiKey(apiKey)
                        .model("wan2.5-t2i-preview")
                        .prompt("A flower shop with exquisite windows, a beautiful wooden door, and flowers on display")
                        .n(1)
                        .size("1280*1280")
                        .negativePrompt("")
                        .parameters(parameters)
                        .build();

                ImageSynthesis imageSynthesis = new ImageSynthesis();
                ImageSynthesisResult result = null;
                try {
                  result = imageSynthesis.asyncCall(param);
                } catch (Exception e){
                  throw new RuntimeException(e.getMessage());
                }
                System.out.println(JsonUtils.toJson(result));
                String taskId = result.getOutput().getTaskId();
                System.out.println("taskId=" + taskId);
                return taskId;
              }

              /**
                 * Wait for the asynchronous task to complete
                 * @param taskId The task ID
                 */
              public void waitAsyncTask(String taskId) {
                ImageSynthesis imageSynthesis = new ImageSynthesis();
                ImageSynthesisResult result = null;
                try {
                  result = imageSynthesis.wait(taskId, apiKey);
                } catch (ApiException | NoApiKeyException e){
                  throw new RuntimeException(e.getMessage());
                }
                System.out.println(JsonUtils.toJson(result));
                System.out.println(JsonUtils.toJson(result.getOutput()));
              }

              public static void main(String[] args){
                Main main = new Main();
                main.asyncCall();
              }
            }
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: DashScope API Key. Create one in the [QwenCloud console](https://home.qwencloud.com/api-keys).
  schemas:
    Wan26TextToImageRequest:
      type: object
      description: Request body for wan2.6-t2i model. Uses the `messages` format in the `input` object.
      required:
        - model
        - input
      properties:
        model:
          type: string
          description: The model name. For the wan2.6-t2i model, use `wan2.6-t2i`.
          enum:
            - wan2.6-t2i
          example: wan2.6-t2i
        input:
          type: object
          description: The input object containing the message array.
          required:
            - messages
          properties:
            messages:
              type: array
              description: An array for the request content. Only single-turn conversations are supported (one set of role and content).
              items:
                type: object
                required:
                  - role
                  - content
                properties:
                  role:
                    type: string
                    description: The role of the message. Must be `user`.
                    enum:
                      - user
                  content:
                    type: array
                    description: An array for the message content.
                    items:
                      type: object
                      required:
                        - text
                      properties:
                        text:
                          type: string
                          description: 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
        parameters:
          $ref: "#/components/schemas/Wan26Parameters"
    WanLegacyTextToImageRequest:
      type: object
      description: "Request body for wan2.5 and earlier models. Uses the `prompt` format in the `input` object. **Note**: These models use the endpoint `POST /services/aigc/text2image/image-synthesis` instead of the main endpoint."
      required:
        - model
        - input
      properties:
        model:
          type: string
          description: "The model name. Supported models: `wan2.5-t2i-preview`, `wan2.2-t2i-plus`, `wan2.2-t2i-flash`, `wan2.1-t2i-plus`, `wan2.1-t2i-turbo`."
          enum:
            - wan2.5-t2i-preview
            - wan2.2-t2i-plus
            - wan2.2-t2i-flash
            - wan2.1-t2i-plus
            - wan2.1-t2i-turbo
          example: wan2.5-t2i-preview
        input:
          type: object
          description: The input object containing the prompt string.
          required:
            - prompt
          properties:
            prompt:
              type: string
              description: "The positive prompt describing the desired image content. Chinese and English are supported. Maximum length varies by model: wan2.5-t2i-preview (2,000 chars), wan2.2, wan2.1 series (500 chars)."
              example: A flower shop with exquisite windows, a beautiful wooden door, and flowers on display
            negative_prompt:
              type: string
              description: Optional. Describes content you do not want in the image. Maximum 500 characters. Chinese and English supported.
              example: low resolution, low quality, deformed limbs
        parameters:
          $ref: "#/components/schemas/WanLegacyParameters"
    Wan26Parameters:
      type: object
      description: Parameters for wan2.6-t2i model.
      properties:
        negative_prompt:
          type: string
          description: "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."
        size:
          type: string
          description: "The resolution of the output image in `width*height` format. Default: `1280*1280`. The total number of pixels must be between `1280*1280` and `1440*1440`, and the aspect ratio must be between 1:4 and 4:1. Recommended resolutions: 1:1 (`1280*1280`), 3:4 (`1104*1472`), 4:3 (`1472*1104`), 9:16 (`960*1696`), 16:9 (`1696*960`)."
          default: 1280*1280
          example: 1280*1280
        n:
          type: integer
          description: "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."
          minimum: 1
          maximum: 4
          default: 4
        prompt_extend:
          type: boolean
          description: "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`. When prompt rewriting is enabled, the rewritten prompt may introduce copyrighted content and trigger content moderation, which returns an `IPInfringementSuspect` or `DataInspectionFailed` error. If you receive either error, set `prompt_extend` to `false` and try again. If the prompt itself explicitly names a copyrighted character or work, disabling prompt rewriting does not resolve the issue and you must revise the prompt."
          default: true
        watermark:
          type: boolean
          description: 'Whether to add a watermark in the lower-right corner of the image with the text "AI-generated". Default: `false`.'
          default: false
        seed:
          type: integer
          description: "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."
          minimum: 0
          maximum: 2147483647
    WanLegacyParameters:
      type: object
      description: Parameters for wan2.5 and earlier models.
      properties:
        size:
          type: string
          description: "The resolution of the output image in `width*height` format. Model wan2.5-t2i-preview defaults to `1280*1280` (total pixels `1280*1280`–`1440*1440`, aspect ratio 1:4–4:1). Models wan2.2 and earlier default to `1024*1024` (dimensions 512–1440, max `1440*1440`). Recommended resolutions for wan2.5 include: 1:1 (`1280*1280`), 3:4 (`1104*1472`), 4:3 (`1472*1104`), 9:16 (`960*1696`), 16:9 (`1696*960`)."
          example: 1280*1280
        n:
          type: integer
          description: "The number of images to generate. Value: 1 to 4. Default: `4`. Billing is per image."
          minimum: 1
          maximum: 4
          default: 4
        prompt_extend:
          type: boolean
          description: "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`. When prompt rewriting is enabled, the rewritten prompt may introduce copyrighted content and trigger content moderation, which returns an `IPInfringementSuspect` or `DataInspectionFailed` error. If you receive either error, set `prompt_extend` to `false` and try again. If the prompt itself explicitly names a copyrighted character or work, disabling prompt rewriting does not resolve the issue and you must revise the prompt."
          default: true
        watermark:
          type: boolean
          description: 'Whether to add a watermark in the lower-right corner of the image with the text "AI-generated". Default: `false`.'
          default: false
        seed:
          type: integer
          description: "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."
          minimum: 0
          maximum: 2147483647
    Wan26SyncResponse:
      type: object
      description: Synchronous response for wan2.6-t2i model.
      example:
        output:
          choices:
            - finish_reason: stop
              message:
                content:
                  - image: https://dashscope-463f.oss-accelerate.aliyuncs.com/xxxx.png?Expires=xxx
                    type: image
                role: assistant
          finished: true
        usage:
          image_count: 1
          input_tokens: 0
          output_tokens: 0
          size: 1280*1280
          total_tokens: 0
        request_id: 815505c6-7c3d-49d7-b197-xxxxxx
      properties:
        output:
          type: object
          properties:
            choices:
              type: array
              description: List of generated results.
              items:
                type: object
                properties:
                  finish_reason:
                    type: string
                    description: "`stop` indicates normal completion."
                    example: stop
                  message:
                    type: object
                    properties:
                      role:
                        type: string
                        description: Always `assistant`.
                        enum:
                          - assistant
                      content:
                        type: array
                        description: Response content array containing generated image URLs.
                        items:
                          type: object
                          properties:
                            image:
                              type: string
                              description: URL of the generated image (PNG). **Valid for 24 hours.** Download promptly.
                            type:
                              type: string
                              description: Content type. Always `image`.
                              enum:
                                - image
            finished:
              type: boolean
              description: Whether the generation has completed.
        usage:
          type: object
          description: Usage statistics.
          properties:
            image_count:
              type: integer
              description: Number of images generated.
            input_tokens:
              type: integer
              description: Number of input tokens. Currently fixed at 0.
            output_tokens:
              type: integer
              description: Number of output tokens. Currently fixed at 0.
            size:
              type: string
              description: Resolution of the generated image(s).
            total_tokens:
              type: integer
              description: Total tokens consumed. Currently fixed at 0.
        request_id:
          type: string
          description: Unique request identifier for tracing and troubleshooting.
    AsyncTaskSubmitResponse:
      type: object
      description: Response returned when an asynchronous task is created successfully.
      properties:
        request_id:
          type: string
          description: Unique request identifier for troubleshooting.
        output:
          type: object
          properties:
            task_id:
              type: string
              description: The task identifier. Use this to query the task status via `GET /tasks/{task_id}`. Valid for 24 hours.
            task_status:
              type: string
              description: The initial task status. Typically `PENDING`.
              enum:
                - PENDING
    TaskStatusResponse:
      type: object
      description: Response returned when querying task status. The output format depends on the model used.
      properties:
        request_id:
          type: string
          description: Unique request identifier for troubleshooting.
        output:
          type: object
          description: Task output information.
          properties:
            task_id:
              type: string
              description: The task identifier.
            task_status:
              type: string
              description: The current task status.
              enum:
                - PENDING
                - RUNNING
                - SUCCEEDED
                - FAILED
                - CANCELLED
            choices:
              type: array
              description: Output content (wan2.6-t2i format). Returned when task_status is SUCCEEDED.
              items:
                type: object
                properties:
                  finish_reason:
                    type: string
                    description: The reason the task stopped. `stop` indicates normal completion.
                  message:
                    type: object
                    properties:
                      role:
                        type: string
                        description: The role. Always `assistant`.
                      content:
                        type: array
                        items:
                          type: object
                          properties:
                            image:
                              type: string
                              description: The generated image URL. Valid for 24 hours.
                            type:
                              type: string
                              description: Content type. Always `image`.
            results:
              type: array
              description: Output content (wan2.5 and earlier format). Returned when task_status is SUCCEEDED.
              items:
                type: object
                properties:
                  url:
                    type: string
                    description: The generated image URL. Valid for 24 hours.
                  orig_prompt:
                    type: string
                    description: The original input prompt.
                  actual_prompt:
                    type: string
                    description: The optimized prompt used for generation (returned only when prompt rewriting is enabled).
                  code:
                    type: string
                    description: Error code (returned only for failed individual results).
                  message:
                    type: string
                    description: Error message (returned only for failed individual results).
            finished:
              type: boolean
              description: Whether the task has finished (wan2.6 format).
            submit_time:
              type: string
              description: Task submission time.
            scheduled_time:
              type: string
              description: Task scheduled time.
            end_time:
              type: string
              description: Task completion time.
            task_metrics:
              type: object
              description: Statistics for the task results.
              properties:
                TOTAL:
                  type: integer
                  description: The total number of tasks.
                SUCCEEDED:
                  type: integer
                  description: The number of successful tasks.
                FAILED:
                  type: integer
                  description: The number of failed tasks.
            code:
              type: string
              description: Error code (returned only when the task fails).
            message:
              type: string
              description: Error message (returned only when the task fails).
        usage:
          type: object
          description: Usage statistics. Only successful results are counted.
          properties:
            image_count:
              type: integer
              description: "The number of images successfully generated. Billing formula: Fee = Number of images x Unit price."
            size:
              type: string
              description: The resolution of the generated images.
            input_tokens:
              type: integer
              description: Number of input tokens (wan2.6 format).
            output_tokens:
              type: integer
              description: Number of output tokens (wan2.6 format).
            total_tokens:
              type: integer
              description: Total number of tokens (wan2.6 format).
    DashScopeErrorResponse:
      type: object
      description: Error response returned when a request fails.
      properties:
        code:
          type: string
          description: The error code.
        message:
          type: string
          description: A detailed error message.
        request_id:
          type: string
          description: The unique request ID for troubleshooting.