> ## 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 2.7 First-Last Frame to Video > Submit an asynchronous Ali `wan2.7-i2v` first-and-last-frame video generation task. Use `first_frame` to specify the start frame, `last_frame` to specify the end frame, optionally paired with `driving_audio` for audio-driven generation. Supported `media` combinations: - `first_frame + last_frame` - `first_frame + last_frame + driving_audio` The `prompt` field is optional for this capability. `size` only supports `720P` and `1080P`. `seconds` only supports integer strings from `2` to `15`. Also supports official fields `negative_prompt`, `prompt_extend`, `watermark`, and `seed`. ## OpenAPI ````yaml api-reference/en/zmodelVideo/ali/wan2.7-i2v-first-last-frame.json POST /v1/videos openapi: 3.0.1 info: title: Wan 2.7 First & Last Frame version: 1.0.0 description: >- Ali `wan2.7-i2v` first and last frame video generation capability documentation. The unified API endpoint is `/v1/videos`. This document covers the first-and-last-frame video generation scenario and uses the top-level `media` array to express the upstream provider's new `input.media` protocol. Supported `media.type` values for this scenario are `first_frame`, `last_frame`, and `driving_audio`. Supported `media` combinations: - `first_frame + last_frame` - `first_frame + last_frame + driving_audio` The `prompt` field is optional for this capability. `size` only supports `720P` and `1080P`. `seconds` only supports integer strings from `2` to `15`. Also supports official fields `negative_prompt`, `prompt_extend`, `watermark`, and `seed`. 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 2.7 Video description: Ali wan2.7-i2v first and last frame video generation capability paths: /v1/videos: post: tags: - Wan 2.7 Video summary: Create Wan 2.7 First & Last Frame task description: >- Submit an asynchronous Ali `wan2.7-i2v` first-and-last-frame video generation task. Use `first_frame` to specify the start frame, `last_frame` to specify the end frame, optionally paired with `driving_audio` for audio-driven generation. Supported `media` combinations: - `first_frame + last_frame` - `first_frame + last_frame + driving_audio` The `prompt` field is optional for this capability. `size` only supports `720P` and `1080P`. `seconds` only supports integer strings from `2` to `15`. Also supports official fields `negative_prompt`, `prompt_extend`, `watermark`, and `seed`. operationId: aliWan27I2VFirstLastFrame requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Wan27FirstLastFrameRequest' examples: first_last_frame: summary: First frame + Last frame value: model: wan2.7-i2v prompt: A cat walking from one end of the hallway to the other. media: - type: first_frame url: https://example.com/assets/start.png - type: last_frame url: https://example.com/assets/end.png seconds: '5' size: 1080P first_last_frame_with_audio: summary: First frame + Last frame + Driving audio value: model: wan2.7-i2v prompt: >- A person slowly lifts their head and smiles, accompanied by a narration. negative_prompt: blurry, low quality prompt_extend: true watermark: false seed: 42 media: - type: first_frame url: https://example.com/assets/portrait-start.png - type: last_frame url: https://example.com/assets/portrait-end.png - type: driving_audio url: https://example.com/assets/narration.mp3 seconds: '8' size: 720P responses: '200': description: >- Submitted successfully. Returns an OpenAI-compatible video task object. content: application/json: schema: $ref: '#/components/schemas/VideoTaskResponse' '400': description: >- Invalid request parameters, e.g. unsupported `media` combination, or `size` / `seconds` out of supported range. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: invalid_request: summary: Invalid request value: error: message: unsupported wan2.7-i2v media combination type: invalid_request_error code: invalid_request '401': description: Authentication failed. 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: Wan27FirstLastFrameRequest: type: object required: - model - media properties: model: type: string enum: - wan2.7-i2v description: 'Model name. Available value: `wan2.7-i2v`.' prompt: type: string description: >- Text prompt describing the desired video content and visual characteristics. Supports Chinese and English, up to 5000 characters (each character or letter counts as one). Excess characters will be automatically truncated. size: type: string enum: - 720P - 1080P description: >- Specifies the output resolution tier for controlling video clarity (total pixels). The model automatically scales to a similar total pixel count based on the selected resolution tier. The video aspect ratio will attempt to stay consistent with the input material (first frame or first clip). default: 1080P seconds: type: string description: >- Video duration as a string. Supports integer strings from `2` to `15`. default: '5' enum: - '2' - '3' - '4' - '5' - '6' - '7' - '8' - '9' - '10' - '11' - '12' - '13' - '14' - '15' negative_prompt: type: string description: >- Negative prompt describing content you do not want in the video. Supports Chinese and English, up to 500 characters. Excess characters will be automatically truncated. Example: `low resolution, worst quality, deformed, extra fingers, bad proportions`. prompt_extend: type: boolean description: >- Whether to enable intelligent prompt rewriting. When enabled, a large language model rewrites the input prompt intelligently, significantly improving results for short prompts but increasing processing time. `true` (default): enable. `false`: disable. watermark: type: boolean description: >- Whether to add a watermark. The watermark is positioned at the bottom-right corner with the text 'AI生成'. `false` (default): no watermark. `true`: add watermark. default: false seed: type: integer minimum: 0 maximum: 2147483647 description: >- Random seed, range [0, 2147483647]. When unspecified, the system auto-generates a random seed. For better reproducibility, set a fixed seed. Note: due to the probabilistic nature of model generation, the same seed does not guarantee identical results every time. media: type: array description: >- List of media assets (images, audio) for video generation. Each element is a media object with `type` and `url`. Supported combinations (invalid combinations will return an error): - **First & last frame**: `first_frame` + `last_frame` - **First & last frame + audio**: `first_frame` + `last_frame` + `driving_audio` Each `type` can appear at most once in the array. items: $ref: '#/components/schemas/Wan27MediaInput' VideoTaskResponse: type: object properties: id: type: string description: Public task ID. task_id: type: string description: Backward-compatible alias for the public task ID. object: type: string example: video model: type: string description: Model name. status: type: string enum: - queued - in_progress - completed - failed - unknown description: Unified video task status. progress: type: integer description: Task progress percentage. created_at: type: integer format: int64 description: Creation time as a Unix timestamp (seconds). ErrorResponse: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string Wan27MediaInput: type: object required: - type - url properties: type: type: string enum: - first_frame - last_frame - driving_audio description: >- Media asset type. - `first_frame`: First frame image. - `last_frame`: Last frame image. - `driving_audio`: Driving audio. Each type can appear at most once per request (e.g. cannot include two `first_frame` entries). url: type: string description: >- Media asset URL. Supports images and audio. **Audio** (type=`driving_audio`) Audio file URL. - **With audio provided**: The model uses this audio as the driving source to generate the video (e.g., lip sync, action cues, etc.). - **Without audio provided**: The model automatically generates matching background music or sound effects based on the video content. Audio restrictions: - Formats: WAV, MP3. - Duration: 2~30s. - File size: up to 15MB. - Truncation handling: If the audio length exceeds the `duration` value (e.g., 5 seconds), the first 5 seconds are automatically kept and the rest is discarded. If the audio is shorter than the video duration, the part beyond the audio length is a silent video. For example, audio is 3 seconds, video duration is 5 seconds, the output video has audio in the first 3 seconds and is silent in the last 2 seconds. Supported input formats: Public URL: Supports HTTP and HTTPS protocols. Example: `https://xxx/xxx.mp3`. Temporary URL: Supports OSS protocol. Must obtain the temporary URL via file upload. Example: `oss://dashscope-instant/xxx/xxx.mp3`. **Image** (type=`first_frame` or `last_frame`): First or last frame URL, or Base64 encoded data. Image restrictions: - Formats: JPEG, JPG, PNG (no alpha channel), BMP, WEBP. - Resolution: width and height range [240, 8000] pixels. - Aspect ratio: 1:8 ~ 8:1. - File size: up to 20MB. Supported input formats: Public URL: Supports HTTP or HTTPS protocols. Example: `https://xxx/xxx.png`. Temporary URL: Supports OSS protocol. Must obtain the temporary URL via file upload. Example: `oss://dashscope-instant/xxx/xxx.png`. Base64 encoded image string: Data format: data:{MIME_type};base64,{base64_data}. Example: data:image/png;base64,GDU7MtCZzEbTbmRZ...... (truncated for demonstration). Base64 encoded data format Format: data:{MIME_type};base64,{base64_data}. {base64_data}: The Base64 encoded string of the image file. {MIME_type}: The media type of the image, corresponding to the file format. Image format to MIME Type mapping: | Image Format | MIME Type | | --- | --- | | JPEG | image/jpeg | | JPG | image/jpeg | | PNG | image/png | | BMP | image/bmp | | WEBP | image/webp | securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Pass `Authorization: Bearer ` in the request header.' ````