Wan — Animar uma imagem

Enviar tarefa de animação

Anime a imagem de um personagem transferindo ações e expressões de um vídeo de referência. Use-o para replicar danças, movimentos corporais e expressões faciais — uma alternativa de baixo custo à captura de movimento.

Modos de serviço

wan2.2-animate-move oferece dois modos de serviço:

Requisitos de entrada

Imagem do personagem (image_url):

• Uma única pessoa voltada para a frente e com o rosto desobstruído
• A pessoa deve ocupar uma porção moderada do quadro
• Formato: JPG, JPEG, PNG, BMP ou WEBP
• Dimensões: 200–4096 px (largura e altura), proporção de 1:3 a 3:1
• Tamanho do arquivo: até 5 MB

Vídeo de referência (video_url):

• Uma única pessoa voltada para a frente e com o rosto desobstruído
• Resolução e taxa de quadros mais altas produzem melhores resultados
• Formato: MP4, AVI ou MOV
• Duração: 2–30 segundos
• Dimensões: 200–2048 px (largura e altura), proporção de 1:3 a 3:1
• Tamanho do arquivo: até 200 MB

OpenAPI

openapi: 3.1.0
info:
  title: Wan Image-to-Animation API
  description: Animate a character image by transferring actions and expressions from a reference video using the wan2.2-animate-move model.
  version: 1.0.0
servers:
  - url: https://maas.qwencloudapi.com/api/v1
    description: Singapore
security:
  - BearerAuth: []
paths:
  /services/aigc/image2video/video-synthesis:
    post:
      operationId: createImageToAnimationTask
      summary: Create image-to-animation task
      description: Create an image-to-animation task.
      parameters:
        - name: X-DashScope-Async
          in: header
          required: true
          description: Must be set to `enable`. HTTP requests support only asynchronous processing. Omitting this header returns a "current user api does not support synchronous calls" error.
          schema:
            type: string
            enum:
              - enable
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: "#/components/schemas/ImageToAnimationRequest"
      responses:
        "200":
          description: Task submitted 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 - Image to animation
          source: |-
            curl --location 'https://maas.qwencloudapi.com/api/v1/services/aigc/image2video/video-synthesis' \
              -H 'X-DashScope-Async: enable' \
              -H "Authorization: Bearer $DASHSCOPE_API_KEY" \
              -H 'Content-Type: application/json' \
              -d '{
              "model": "wan2.2-animate-move",
              "input": {
                "image_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg",
                "video_url": "https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4",
                "watermark": true
              },
              "parameters": {
                "mode": "wan-std"
              }
            }'
        - lang: python
          label: Python - Synchronous call
          source: |-
            import os
            from http import HTTPStatus
            from dashscope import VideoSynthesis
            import dashscope

            dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
            api_key = os.getenv("DASHSCOPE_API_KEY")

            def sample_sync_call():
              print('Please wait...')
              rsp = VideoSynthesis.call(
                api_key=api_key,
                model='wan2.2-animate-move',
                image_url='https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg',
                video_url='https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4',
                watermark=True,
                mode='wan-std')
              print(rsp)
              if rsp.status_code == HTTPStatus.OK:
                print(rsp.output.video_url)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                      (rsp.status_code, rsp.code, rsp.message))

            if __name__ == '__main__':
              sample_sync_call()
        - lang: python
          label: Python - Asynchronous call
          source: |-
            import os
            from http import HTTPStatus
            from dashscope import VideoSynthesis
            import dashscope

            dashscope.base_http_api_url = 'https://maas.qwencloudapi.com/api/v1'
            api_key = os.getenv("DASHSCOPE_API_KEY")

            def sample_async_call():
              rsp = VideoSynthesis.async_call(
                api_key=api_key,
                model='wan2.2-animate-move',
                image_url='https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg',
                video_url='https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4',
                watermark=True,
                mode='wan-std')
              print(rsp)
              if rsp.status_code == HTTPStatus.OK:
                print("task_id: %s" % rsp.output.task_id)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                      (rsp.status_code, rsp.code, rsp.message))
              rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
              print(rsp)
              if rsp.status_code == HTTPStatus.OK:
                print(rsp.output.video_url)
              else:
                print('Failed, status_code: %s, code: %s, message: %s' %
                      (rsp.status_code, rsp.code, rsp.message))

            if __name__ == '__main__':
              sample_async_call()
        - lang: java
          label: Java - Synchronous call
          source: |-
            import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
            import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
            import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.InputRequiredException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.utils.JsonUtils;
            import com.alibaba.dashscope.utils.Constants;
            import java.util.*;

            public class WanImageToAnimation {
              static {
                Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
              }
              public static void main(String[] args) {
                try {
                  VideoSynthesis vs = new VideoSynthesis();
                  Map<String, Object> parameters = new HashMap<>();
                  parameters.put("mode", "wan-std");
                  VideoSynthesisParam param = VideoSynthesisParam.builder()
                    .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                    .model("wan2.2-animate-move")
                    .parameters(parameters)
                    .imageUrl("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg")
                    .videoUrl("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4")
                    .watermark(true)
                    .build();
                  System.out.println("Please wait...");
                  VideoSynthesisResult result = vs.call(param);
                  System.out.println(JsonUtils.toJson(result));
                } catch (ApiException | NoApiKeyException | InputRequiredException e) {
                  System.out.println(e.getMessage());
                }
              }
            }
        - lang: java
          label: Java - Asynchronous call
          source: |-
            import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesis;
            import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisParam;
            import com.alibaba.dashscope.aigc.videosynthesis.VideoSynthesisResult;
            import com.alibaba.dashscope.exception.ApiException;
            import com.alibaba.dashscope.exception.InputRequiredException;
            import com.alibaba.dashscope.exception.NoApiKeyException;
            import com.alibaba.dashscope.utils.JsonUtils;
            import com.alibaba.dashscope.utils.Constants;
            import java.util.*;

            public class WanImageToAnimation {
              static {
                Constants.baseHttpApiUrl = "https://maas.qwencloudapi.com/api/v1";
              }
              public static void main(String[] args) {
                try {
                  String apiKey = System.getenv("DASHSCOPE_API_KEY");
                  VideoSynthesis vs = new VideoSynthesis();
                  Map<String, Object> parameters = new HashMap<>();
                  parameters.put("mode", "wan-std");
                  VideoSynthesisParam param = VideoSynthesisParam.builder()
                    .apiKey(apiKey)
                    .model("wan2.2-animate-move")
                    .parameters(parameters)
                    .imageUrl("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg")
                    .videoUrl("https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4")
                    .watermark(true)
                    .build();
                  VideoSynthesisResult task = vs.asyncCall(param);
                  System.out.println(JsonUtils.toJson(task));
                  System.out.println("Please wait...");
                  VideoSynthesisResult result = vs.wait(task, apiKey);
                  System.out.println(JsonUtils.toJson(result));
                } catch (ApiException | NoApiKeyException | InputRequiredException e) {
                  System.out.println(e.getMessage());
                }
              }
            }
components:
  securitySchemes:
    BearerAuth:
      type: http
      scheme: bearer
      description: DashScope API Key. Create one in the [QwenCloud console](https://home.qwencloud.com/api-keys).
  schemas:
    ImageToAnimationRequest:
      type: object
      required:
        - model
        - input
        - parameters
      properties:
        model:
          type: string
          description: Model name. Must be `wan2.2-animate-move`.
          enum:
            - wan2.2-animate-move
          example: wan2.2-animate-move
        input:
          type: object
          required:
            - image_url
            - video_url
          description: Input data including the character image and reference video.
          properties:
            image_url:
              type: string
              description: |-
                A publicly accessible URL of the input character image.

                **Image constraints:**
                - Format: JPG, JPEG, PNG, BMP, or WEBP.
                - Dimensions: Width and height must both be in the range of [200, 4096] pixels. The aspect ratio must be between 1:3 and 3:1.
                - File size: Up to 5 MB.
                - Content: The image must show a single front-facing person with an unobstructed face, occupying a moderate portion of the frame.

                URLs containing non-ASCII characters (such as Chinese characters) must be URL-encoded.
              example: https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/adsyrp/move_input_image.jpeg
            video_url:
              type: string
              description: |-
                A publicly accessible URL of the reference video. The model transfers actions and expressions from this video to the character image.

                **Video constraints:**
                - Format: MP4, AVI, or MOV.
                - Duration: 2 to 30 seconds.
                - Dimensions: Width and height must both be in the range of [200, 2048] pixels. The aspect ratio must be between 1:3 and 3:1.
                - File size: Up to 200 MB.
                - Content: The video must show a single front-facing person with an unobstructed face, occupying a moderate portion of the frame.

                For better results, use a reference video with higher resolution and frame rate. URLs containing non-ASCII characters must be URL-encoded.
              example: https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250919/kaakcn/move_input_video.mp4
            watermark:
              type: boolean
              description: Whether to add a "Generated by Qwen AI" watermark in the lower-right corner of the video.
              default: false
              example: true
        parameters:
          $ref: "#/components/schemas/ImageToAnimationParameters"
    ImageToAnimationParameters:
      type: object
      required:
        - mode
      description: Video generation parameters.
      properties:
        mode:
          type: string
          description: |-
            The service mode.
            - `wan-std`: Standard mode. Faster generation at lower cost. Suitable for quick previews and basic animation.
            - `wan-pro`: Professional mode. Smoother animation and higher quality, with longer processing time and higher cost.
          enum:
            - wan-std
            - wan-pro
          example: wan-std
        check_image:
          type: boolean
          description: Whether to validate the input image.
          default: true
          example: true
    AsyncTaskSubmitResponse:
      type: object
      description: Response from an asynchronous task submission.
      properties:
        request_id:
          type: string
          description: Unique request identifier for tracing and troubleshooting.
          example: 4909100c-7b5a-9f92-bfe5-xxxxxx
        output:
          type: object
          properties:
            task_id:
              type: string
              description: Task ID for polling status. Use with `GET /tasks/{task_id}`. Valid for 24 hours.
              example: 0385dc79-5ff8-4d82-bcb6-xxxxxx
            task_status:
              type: string
              description: Initial task status, typically `PENDING`.
              enum:
                - PENDING
                - RUNNING
                - SUCCEEDED
                - FAILED
                - CANCELED
                - UNKNOWN
              example: PENDING
    TaskStatusResponse:
      type: object
      description: Response from polling a task's status.
      properties:
        request_id:
          type: string
          description: Unique request identifier.
          example: a67f8716-18ef-447c-a286-xxxxxx
        output:
          type: object
          properties:
            task_id:
              type: string
              description: The task ID.
              example: 0385dc79-5ff8-4d82-bcb6-xxxxxx
            task_status:
              type: string
              description: "Current task status. Transitions: PENDING → RUNNING → SUCCEEDED or FAILED. UNKNOWN means the task does not exist or has expired."
              enum:
                - PENDING
                - RUNNING
                - SUCCEEDED
                - FAILED
                - CANCELED
                - UNKNOWN
            submit_time:
              type: string
              description: "Time when the task was submitted. UTC+8 format: YYYY-MM-DD HH:mm:ss.SSS."
              example: 2025-09-18 15:32:00.105
            scheduled_time:
              type: string
              description: "Time when the task started running. UTC+8 format: YYYY-MM-DD HH:mm:ss.SSS."
              example: 2025-09-18 15:32:15.066
            end_time:
              type: string
              description: "Time when the task completed. UTC+8 format: YYYY-MM-DD HH:mm:ss.SSS."
              example: 2025-09-18 15:34:41.898
            results:
              type: object
              description: Task results. Returned only when `task_status` is `SUCCEEDED`.
              properties:
                video_url:
                  type: string
                  description: URL of the generated video. Valid for 24 hours. Download promptly. MP4 format with H.264 encoding.
                  example: https://dashscope-result-sh.oss-accelerate.aliyuncs.com/xxxxx.mp4?Expires=xxxxxx
            code:
              type: string
              description: Error code. Returned only when the task fails.
            message:
              type: string
              description: Detailed error message. Returned only when the task fails.
        usage:
          type: object
          description: Output statistics. Returned only for successful tasks.
          properties:
            video_duration:
              type: number
              description: Duration of the generated video in seconds.
              example: 5.2
            video_ratio:
              type: string
              description: The service mode used. `standard` for `wan-std`, `pro` for `wan-pro`.
              enum:
                - standard
                - pro
              example: standard
    DashScopeErrorResponse:
      type: object
      description: DashScope API error response.
      properties:
        request_id:
          type: string
          description: Unique request identifier.
        code:
          type: string
          description: Error code (e.g., `InvalidApiKey`, `InvalidParameter`, `Throttling`).
          example: InvalidApiKey
        message:
          type: string
          description: Human-readable error message.
          example: No API-key provided.