> ## 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 First-Last Frame to Video > wan2.2-kf2v-flash Applies to Wan series first-last-frame image-to-video models. After submitting a task, query its status via `GET /v1/videos/{task_id}`. Public fields: `model`, `images`, `prompt`, `seconds`, `size`, `prompt_extend`, `watermark`, `seed`, and `negative_prompt`. The `images` array must contain exactly 2 images in order: `images[0]` is the first frame and `images[1]` is the last frame. The first frame determines the base composition, while the last frame controls the closing scene. ## OpenAPI ````yaml api-reference/en/zmodelVideo/ali/video-first-last-frame.json POST /v1/videos openapi: 3.0.1 info: title: Wan first-last-frame image-to-video version: 1.0.0 description: >- Wan series first-last-frame image-to-video capability documentation. The unified API endpoint is `/v1/videos`, used to create asynchronous video generation tasks. This scenario uses a first frame and a last frame image to drive the generated video. 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 Video description: Wan first-last-frame video capability paths: /v1/videos: post: tags: - Wan Video summary: Wan first-last-frame image-to-video description: >- wan2.2-kf2v-flash Applies to Wan series first-last-frame image-to-video models. After submitting a task, query its status via `GET /v1/videos/{task_id}`. Public fields: `model`, `images`, `prompt`, `seconds`, `size`, `prompt_extend`, `watermark`, `seed`, and `negative_prompt`. The `images` array must contain exactly 2 images in order: `images[0]` is the first frame and `images[1]` is the last frame. The first frame determines the base composition, while the last frame controls the closing scene. operationId: aliFirstLastFrameToVideo requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/FirstLastFrameVideoRequest' examples: first_last_frame_video: summary: First-last-frame image-to-video value: model: wan2.2-kf2v-flash images: - https://example.com/first-frame.png - https://example.com/last-frame.png prompt: >- Realistic style, a black kitten curiously looks up at the sky, the camera gradually rises from eye level, ending with a top-down shot of its curious eyes. seconds: '5' size: 720P prompt_extend: true with_negative_prompt: summary: With negative prompt value: model: wan2.2-kf2v-flash images: - https://example.com/first-frame.png - https://example.com/last-frame.png prompt: Realistic style, a kitten runs from the grass to the garden negative_prompt: human figures size: 720P prompt_extend: true responses: '200': description: Submitted successfully. Returns a video task object. content: application/json: schema: $ref: '#/components/schemas/VideoTaskResponse' '400': description: Invalid request parameters. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: invalid_request: summary: Parameter error value: error: message: Malformed request body or invalid field value type: invalid_request_error code: bad_request_body param: '' '401': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unauthorized: summary: Unauthorized value: error: message: Invalid token type: api_error code: access_denied param: '' description: Authentication failed, e.g. missing or invalid token. '413': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: request_too_large: summary: Request body too large value: error: message: >- Request body too large, please reduce the input and retry type: api_error code: read_request_body_failed param: '' description: Request body too large. '429': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: quota_exceeded: summary: Insufficient quota or rate limited value: error: message: Insufficient account quota, please try again later type: api_error code: insufficient_user_quota param: '' description: Rate limit triggered or insufficient account quota. '500': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: internal_error: summary: Internal processing failure value: error: message: Internal processing failed, please try again later type: api_error code: gen_relay_info_failed param: '' description: An internal error occurred while processing the request. '502': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: bad_gateway: summary: Upstream provider response error value: error: message: The upstream provider returned an invalid response type: api_error code: bad_response_status_code param: '' description: The upstream provider returned an abnormal response. '503': content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: service_unavailable: summary: Service temporarily unavailable value: error: message: >- No available channel for the current model, please try again later type: api_error code: get_channel_failed param: '' description: >- The upstream provider is temporarily unavailable, or no channel is currently available for this model. security: - BearerAuth: [] components: schemas: FirstLastFrameVideoRequest: type: object required: - model - prompt - images properties: model: type: string enum: - wan2.2-kf2v-flash description: 'Model name. ' images: type: array minItems: 2 maxItems: 2 items: type: string description: >- First-last-frame image URL array. Must contain exactly 2 images in order: `images[0]` is the first frame, `images[1]` is the last frame. The output video aspect ratio matches the first frame image; the last frame is cropped to fit the first frame aspect ratio. 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. seconds: type: string description: Video duration (seconds) as a string. Currently fixed at `"5"`. enum: - '5' default: '5' size: type: string enum: - 480P - 720P - 1080P description: >- Output video resolution tier. wan2.2-kf2v-flash supports 480P/720P/1080P, wan2.1-kf2v-plus supports 720P. default: 720P 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. 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. VideoTaskResponse: type: object properties: id: type: string task_id: type: string object: type: string example: video model: type: string status: type: string enum: - pending - queued - running - succeeded - failed - cancelled progress: type: integer created_at: type: integer format: int64 ErrorResponse: type: object properties: error: type: object properties: message: type: string type: type: string description: >- Error type, e.g. `invalid_request_error`, `api_error`, or upstream-compatible error types. code: type: string securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ````