> ## Documentation Index > Fetch the complete documentation index at: https://docs.powertokens.ai/llms.txt > Use this file to discover all available pages before exploring further. # Wan Image to Video (First and Last Frame) > Submit an asynchronous Wan 2.2 image-to-video task, generating a video based on a first frame (and optional last frame) image. After submitting a task, query its status via `GET /ali/api/v1/tasks/{task_id}`. ## OpenAPI ````yaml api-reference/en/zmodelVideo/ali/api/legacy-i2v-first-last-frame.json POST /ali/api/v1/services/aigc/image2video/video-synthesis openapi: 3.0.1 info: title: Wan Image to Video (First and Last Frame) version: 1.0.0 description: >- Aliyun Wan 2.2 series first-and-last-frame image-to-video capability documentation. The unified API endpoint is `/ali/api/v1/services/aigc/image2video/video-synthesis`, used to create asynchronous video generation tasks. Supported models: `wan2.2-kf2v-flash`, `wan2.1-kf2v-plus`. license: name: Project License url: https://github.com/QuantumNous/new-api/blob/main/LICENSE servers: - url: https://api.powertokens.ai description: Baze API server endpoint security: [] tags: - name: Wan Legacy Video description: Ali wan 2.2 image-to-video capability paths: /ali/api/v1/services/aigc/image2video/video-synthesis: post: tags: - Wan Legacy Video summary: Create Wan image-to-video task (first and last frame) description: >- Submit an asynchronous Wan 2.2 image-to-video task, generating a video based on a first frame (and optional last frame) image. After submitting a task, query its status via `GET /ali/api/v1/tasks/{task_id}`. operationId: aliLegacyI2VFirstLastFrameCreate parameters: - name: Content-Type in: header required: true schema: type: string description: Request content type. Must be set to `application/json`. - name: X-DashScope-Async in: header required: true schema: type: string description: >- Async processing configuration. HTTP requests only support async mode. Must be set to `enable`. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/LegacyKf2VRequest' examples: first_last_frame: summary: First and last frame (URL) value: model: wan2.2-kf2v-flash input: first_frame_url: https://wanx.alicdn.com/material/20250318/first_frame.png last_frame_url: https://wanx.alicdn.com/material/20250318/last_frame.png prompt: >- Realistic style, a small black cat curiously looks up at the sky, the camera gradually rises from eye level, finally looking down at its curious eyes. parameters: resolution: 480P prompt_extend: true base64: summary: Using Base64 value: model: wan2.1-kf2v-plus input: first_frame_url: data:image/png;base64,GDU7MtCZzEbTbmRZ...... last_frame_url: data:image/png;base64,VBORw0KGgoAAAANSUh...... prompt: >- Realistic style, a small black cat curiously looks up at the sky, the camera gradually rises from eye level, finally looking down at its curious eyes. parameters: resolution: 720P prompt_extend: true template: summary: Using video effect template value: model: wan2.1-kf2v-plus input: first_frame_url: >- https://ty-yuanfang.oss-cn-hangzhou.aliyuncs.com/lizhengjia.lzj/tmp/11.png template: hanfu-1 parameters: resolution: 720P prompt_extend: true negative_prompt: summary: Using negative prompt value: model: wan2.1-kf2v-plus input: first_frame_url: https://wanx.alicdn.com/material/20250318/first_frame.png last_frame_url: https://wanx.alicdn.com/material/20250318/last_frame.png prompt: >- Realistic style, a small black cat curiously looks up at the sky, the camera gradually rises from eye level, finally looking down at its curious eyes. negative_prompt: Human figures parameters: resolution: 720P prompt_extend: true responses: '200': description: >- Submitted successfully. Returns a video task object. Save the task_id to query task status and results. content: application/json: schema: $ref: '#/components/schemas/VideoTaskResponse' example: output: task_status: PENDING task_id: 0385dc79-5ff8-4d82-bcb6-xxxxxx request_id: 4909100c-7b5a-9f92-bfe5-xxxxxx '400': description: Invalid request parameters. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Authentication failed, e.g. missing or invalid token. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '429': description: Rate limit triggered or insufficient account quota. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: An internal error occurred while processing the request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - BearerAuth: [] components: schemas: LegacyKf2VRequest: type: object required: - model - input properties: model: type: string enum: - wan2.2-kf2v-flash - wan2.1-kf2v-plus description: >- Model name. Example: `wan2.2-kf2v-flash`. See the Bailian console for details. input: $ref: '#/components/schemas/LegacyKf2VInput' parameters: $ref: '#/components/schemas/LegacyKf2VParameters' VideoTaskResponse: type: object properties: output: type: object properties: task_id: type: string description: Task ID. Valid for querying for 24 hours. task_status: type: string description: |- Task status. Enum values: - `PENDING`: Task is queued - `RUNNING`: Task is processing - `SUCCEEDED`: Task completed successfully - `FAILED`: Task failed - `CANCELED`: Task canceled - `UNKNOWN`: Task does not exist or status is unknown code: type: string description: Error code for failed requests. Not returned on success. message: type: string description: >- Detailed error message for failed requests. Not returned on success. request_id: type: string description: >- Unique request identifier. Can be used for request tracing and issue investigation. ErrorResponse: type: object properties: code: type: string description: Error code. message: type: string description: Error message. request_id: type: string description: Request ID. LegacyKf2VInput: type: object required: - first_frame_url properties: prompt: type: string description: >- Text prompt. Supports Chinese and English, up to 800 characters (each Chinese character or letter counts as one character). Excess characters will be automatically truncated. If the subject and scene change significantly between the first and last frames, it is recommended to describe the transition, such as camera movement (e.g., camera panning left) or subject motion (e.g., a person running forward). Example: A small black cat curiously looks up at the sky, the camera gradually rises from eye level, finally looking down at its curious eyes. maxLength: 800 negative_prompt: type: string description: >- Negative prompt describing content you do not want in the video, used to restrict the video output. Supports Chinese and English, up to 500 characters. Excess characters will be automatically truncated. Example: Low resolution, error, worst quality, low quality, disfigured, extra fingers, bad proportions, etc. maxLength: 500 first_frame_url: type: string description: >- The URL or Base64-encoded data of the first frame image. The output video's aspect ratio will follow this image. Image restrictions: - Image formats: JPEG, JPG, PNG (no alpha channel), BMP, WEBP. - Image resolution: width and height range [240, 8000] pixels. - File size: up to 10MB. Supported input formats: - **Public URL**: HTTP or HTTPS protocol. Example: `https://wanx.alicdn.com/xxx/first_frame.png`. - **Temporary URL**: OSS protocol, must obtain via file upload. Example: `oss://dashscope-instant/xxx/xxx.png`. - **Base64-encoded image string**: Format: `data:{MIME_type};base64,{base64_data}`. Example: `data:image/png;base64,GDU7MtCZzEbTbmRZ......` (truncated for brevity). last_frame_url: type: string description: >- The URL or Base64-encoded data of the last frame image. Image restrictions: - Image formats: JPEG, JPG, PNG (no alpha channel), BMP, WEBP. - Image resolution: width and height range [240, 8000] pixels. The last frame resolution can differ from the first frame; no forced alignment required. - File size: up to 10MB. Supported input formats: - **Public URL**: HTTP or HTTPS protocol. Example: `https://wanx.alicdn.com/xxxx/last_frame.png`. - **Temporary URL**: OSS protocol, must obtain via file upload. Example: `oss://dashscope-instant/xxx/xxx.png`. - **Base64-encoded image string**: Format: `data:{MIME_type};base64,{base64_data}`. Example: `data:image/png;base64,GDU7MtCZ......` (truncated for brevity). template: type: string description: >- Name of the video effect template. When using this parameter, only first_frame_url is required. Different models support different effect templates. Refer to Wan Image-to-Video Video Effects before calling to avoid failures. Example: `hufu-1`, representing the "Tang Yun Pian Ran" effect. LegacyKf2VParameters: type: object properties: resolution: type: string enum: - 480P - 720P - 1080P description: >- **Important**: resolution directly affects cost. For the same model: 1080P > 720P > 480P. The resolution tier for the generated video. Used to adjust video sharpness (total pixels) without changing the aspect ratio. The video aspect ratio will match that of the first frame image (first_frame_url). Default values and available options depend on the model parameter: - `wan2.2-kf2v-flash`: Available values: 480P, 720P, 1080P. Default: 720P. - `wan2.1-kf2v-plus`: Available values: 720P. Default: 720P. Example: 720P. duration: type: integer description: >- **Important**: duration directly affects cost (billed per second). Video duration in seconds. Currently fixed at 5 and cannot be changed. The model will always generate a 5-second video. default: 5 prompt_extend: type: boolean description: >- Whether to enable intelligent prompt rewriting. When enabled, a large language model rewrites the input prompt intelligently. Significantly improves results for short prompts, but increases processing time. - `true`: Default, enable intelligent rewriting. - `false`: Disable intelligent rewriting. Example: true. default: true watermark: type: boolean description: >- Whether to add a watermark. The watermark appears at the bottom-right corner with the text "AI Generated". - `false`: Default, no watermark. - `true`: Add watermark. Example: false. default: false seed: type: integer description: >- Random seed, range [0, 2147483647]. When not specified, a random seed is automatically generated. To improve reproducibility of results, it is recommended to fix the seed value. Note: Due to the probabilistic nature of model generation, even with the same seed, results may not be identical every time. minimum: 0 maximum: 2147483647 securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ````