> ## 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 Reference to Video > Submit an asynchronous Ali `wan2.7-r2v` reference-to-video generation task. This capability uses the top-level `media` array as the public multimodal input. Supported `media.type` values are `reference_image`, `reference_video`, and `first_frame`. Current public rules: - `prompt` is required; - include at least one `reference_image` or `reference_video` item; - you may provide at most five `reference_image` / `reference_video` items in total; - `first_frame` is optional and can appear at most once; - `size` supports only `720P` and `1080P`; - `ratio` supports `16:9`, `9:16`, `1:1`, `4:3`, and `3:4`; - `seconds` accepts integer strings from `2` to `15`, but when any `reference_video` is included the allowed range is `2` to `10`. Prompt referencing follows the submitted `media` order. Refer to image references as `Image 1`, `Image 2`, and to video references as `Video 1`, `Video 2`, counting separately within each media type. If only one reference image or video is provided, you can simply use "reference image" or "reference video" in the prompt. ## OpenAPI ````yaml api-reference/en/zmodelVideo/ali/reference-to-video.json POST /v1/videos openapi: 3.0.1 info: title: Wan Reference-to-Video version: 1.0.0 description: >- Customer-facing channel document for Ali `wan2.7-r2v`. The public unified endpoint is `/v1/videos`. license: name: Project License url: https://github.com/QuantumNous/new-api/blob/main/LICENSE servers: - url: https://api.powertokens.ai description: Baze API service endpoint security: [] tags: - name: Wan 2.7 Video description: Ali wan2.7-r2v reference-to-video capability paths: /v1/videos: post: tags: - Wan 2.7 Video summary: Create Wan Reference-to-Video Task description: >- Submit an asynchronous Ali `wan2.7-r2v` reference-to-video generation task. This capability uses the top-level `media` array as the public multimodal input. Supported `media.type` values are `reference_image`, `reference_video`, and `first_frame`. Current public rules: - `prompt` is required; - include at least one `reference_image` or `reference_video` item; - you may provide at most five `reference_image` / `reference_video` items in total; - `first_frame` is optional and can appear at most once; - `size` supports only `720P` and `1080P`; - `ratio` supports `16:9`, `9:16`, `1:1`, `4:3`, and `3:4`; - `seconds` accepts integer strings from `2` to `15`, but when any `reference_video` is included the allowed range is `2` to `10`. Prompt referencing follows the submitted `media` order. Refer to image references as `Image 1`, `Image 2`, and to video references as `Video 1`, `Video 2`, counting separately within each media type. If only one reference image or video is provided, you can simply use "reference image" or "reference video" in the prompt. operationId: aliReferenceToVideoCreate requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ReferenceToVideoRequest' examples: reference_to_video: summary: Single image reference value: model: wan2.7-r2v prompt: >- Image 1 walks toward the camera and waves with a relaxed smile. media: - type: reference_image url: https://example.com/assets/subject-reference.png seconds: '5' size: 1080P ratio: '16:9' prompt_extend: true watermark: false reference_to_video_multimodal: summary: Mixed image, video, voice, and first frame references value: model: wan2.7-r2v prompt: >- Video 1 sits at the table and starts speaking. Image 1 walks into frame from the left, while the first frame keeps the opening composition stable. negative_prompt: blurry, distorted hands, low quality prompt_extend: false watermark: true seed: 42 media: - type: reference_image url: https://example.com/assets/character-a.png reference_voice: https://example.com/assets/character-a-voice.mp3 - type: reference_video url: https://example.com/assets/character-b.mp4 - type: first_frame url: https://example.com/assets/opening-frame.png seconds: '8' size: 720P ratio: '9:16' responses: '200': description: >- Submission successful. Returns the unified OpenAI-style video task object. content: application/json: schema: $ref: '#/components/schemas/VideoTaskResponse' '400': description: >- Invalid request parameters, such as missing reference media, unsupported `media.type`, invalid `size` / `ratio` / `seconds`, or incompatible field combinations. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: invalid_request: summary: Invalid request value: code: invalid_request message: >- wan2.7-r2v requires at least one reference_image or reference_video data: null '401': description: Authentication failed, e.g. missing or invalid token. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: unauthorized: summary: Unauthorized value: code: access_denied message: Invalid token data: null '413': description: Request body too large. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: request_too_large: summary: Request body too large value: code: read_request_body_failed message: Request body too large, please reduce the input and retry data: null '429': description: Rate limit triggered or insufficient account quota. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: quota_exceeded: summary: Insufficient quota or rate limited value: code: insufficient_user_quota message: Insufficient account quota, please try again later data: null '500': description: An internal error occurred while processing the request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: internal_error: summary: Internal processing failure value: code: gen_relay_info_failed message: Internal processing failed, please try again later data: null '502': description: The upstream provider returned an abnormal response. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: bad_gateway: summary: Upstream provider response error value: code: bad_response_status_code message: The upstream provider returned an invalid response data: null '503': description: >- The upstream provider is temporarily unavailable, or no channel is currently available for this model. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: service_unavailable: summary: Service temporarily unavailable value: code: get_channel_failed message: >- No available channel for the current model, please try again later data: null security: - BearerAuth: [] components: schemas: ReferenceToVideoRequest: type: object required: - model - prompt - media properties: model: type: string enum: - wan2.7-r2v description: 'Ali wan2.7-r2v model. Available value: `wan2.7-r2v`.' prompt: type: string description: >- Text prompt describing the desired video content and visual characteristics. Supports Chinese and English; each character, letter, or punctuation mark counts as one character. Excess characters are automatically truncated. - `wan2.7-r2v`: up to 5000 characters. Reference naming conventions: - For Chinese prompts, reference images with markers like "图1", "图2" and reference videos with markers like "视频1", "视频2". - For English prompts, use markers like "Image 1", "Video 1" (capitalized first letter, space between letter and number). - The order matches the `media` array order. Images and videos are counted separately, e.g. "图1" and "视频1" can exist simultaneously. - If only one reference image or video is provided, you can simply use "reference image" or "reference video". Scene description examples: - Direct reference: "图1 in 图2" (Image 1 is playing in Image 2). - Combined description: "The cat from Image 1 plays in the room from Image 2". Multi-panel/storyboard images: When the reference image is a multi-panel (storyboard) image, describe the content in a multi-shot narrative format. You do not need to describe every panel; provide key shot content and the model will automatically identify the panel logic and intelligently fill in the details. For best results, it is recommended to provide only one multi-panel image per request. size: type: string enum: - 720P - 1080P description: >- Important: `size` directly affects cost. Confirm the model pricing before calling. Output video resolution tier, controlling video clarity (total pixels). `wan2.7-r2v`: available values `720P`, `1080P`. Default: `1080P`. default: 1080P seconds: type: string description: >- Important: `seconds` directly affects cost. Confirm the model pricing before calling. Video duration in seconds. - `wan2.7-r2v`: default `5`. - When reference assets include a video: range [2, 10]. - When reference assets do not include a video: range [2, 15]. default: '5' enum: - '2' - '3' - '4' - '5' - '6' - '7' - '8' - '9' - '10' - '11' - '12' - '13' - '14' - '15' ratio: type: string enum: - '16:9' - '9:16' - '1:1' - '4:3' - '3:4' description: >- Video aspect ratio. Behavior logic: - If no first frame image is provided: generates video at the specified `ratio`. - If a first frame image is provided: the `ratio` parameter is ignored and the video is generated at an approximate ratio matching the first frame image's aspect ratio. Available values and corresponding output resolutions: **720P:** - `16:9` → 1280×720 - `9:16` → 720×1280 - `1:1` → 960×960 - `4:3` → 1104×832 - `3:4` → 832×1104 **1080P:** - `16:9` → 1920×1080 - `9:16` → 1080×1920 - `1:1` → 1440×1440 - `4:3` → 1648×1248 - `3:4` → 1248×1648 default: '16:9' negative_prompt: type: string description: >- Negative prompt describing content you do not want to see in the video. Limits unwanted visual elements. Supports Chinese and English, up to 500 characters. Example: low resolution, error, worst quality, low quality, deformed, extra fingers, bad proportions, etc. prompt_extend: type: boolean description: >- Whether to enable intelligent prompt rewriting. When enabled, a large language model rewrites the input prompt for better results. Particularly effective for short prompts, but increases processing time. - `true` (default): enable intelligent rewriting. - `false`: disable intelligent rewriting. watermark: type: boolean description: >- Whether to add a watermark to the video. 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]. If not specified, the system automatically generates a random seed. To improve reproducibility of generation results, it is recommended to fix the seed value. Note: Due to the probabilistic nature of model generation, the same seed does not guarantee identical results every time. media: type: array description: >- Array of media assets, including images, videos, and audio. Supports image/video input as visual reference, and images can provide multi-view references for characters, props, scenes, etc. Each element in the array is a media object containing `type` and `url` fields. The order in the array defines the reference mapping order in the prompt. Images and videos are counted separately, so "Image 1" and "Video 1" can exist simultaneously. - The 1st `reference_video` in the array corresponds to "Video 1", the 2nd to "Video 2", etc. - The 1st `reference_image` in the array corresponds to "Image 1", the 2nd to "Image 2", etc. items: $ref: '#/components/schemas/ReferenceToVideoMediaInput' VideoTaskResponse: type: object properties: id: type: string description: Public task ID. task_id: type: string description: Public task ID alias. 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: Unix timestamp in seconds. ErrorResponse: type: object required: - code - message properties: code: type: string description: Error code. example: invalid_request message: type: string description: Error message. data: nullable: true description: Additional error data. Currently usually null. ReferenceToVideoMediaInput: type: object required: - type - url properties: type: type: string enum: - reference_image - reference_video - first_frame description: >- Media asset type. Available values: reference_image: Reference image. Provides subject (person/animal/object) and scene reference. reference_video: Reference video. Provides subject (person/animal/object) and voice reference. B-roll/empty scene videos are not recommended. first_frame: First frame image. Generates video based on the first frame, typically containing the subject (person/animal/object). Supports combined use with subject reference for consistency, or voice reference. First frame: already contains the subject to reference; you can pair it with subject reference for enhanced consistency, or use voice reference. First frame: does not yet contain the subject to reference; you can use subject reference to define the characteristics of the new subject appearing during the video. Material constraints: First frame image: max 1. At least 1 reference image or reference video must be provided. Total reference images + reference videos ≤ 5. When a reference asset contains a subject character, it should contain only a single character. url: type: string description: >- Media asset URL. Each value points to an image or video. **For reference image (`type=reference_image`):** Reference image URL or Base64 encoded data. The reference image can be a subject (person/animal/object) or a background. When it contains a subject, it should include only one character. Image constraints: - Formats: JPEG, JPG, PNG (no alpha channel), BMP, WEBP. - Resolution: width and height range [240, 8000] pixels. - Aspect ratio: 1:8 to 8:1. - File size: up to 20MB. Supported input formats: - Public URL: HTTP or HTTPS, e.g. `https://xxx/xxx.png`. - Temporary URL (OSS): `oss://dashscope-instant/xxx/xxx.png` (must be obtained by uploading the file). - Base64 encoded string: `data:{MIME_type};base64,{base64_data}`, e.g. `data:image/png;base64,...`. **For reference video (`type=reference_video`):** Reference video URL. The video should contain a subject (person/animal/object). B-roll or empty scene videos are not recommended. When it contains a subject, it should include only one character. If the video has audio, the voice can also be referenced. Video constraints: - Formats: mp4, mov. - Duration: 1 to 30 seconds. - Resolution: width and height range [240, 4096] pixels. - Aspect ratio: 1:8 to 8:1. - File size: up to 100MB. Supported input formats: - Public URL: HTTP or HTTPS, e.g. `https://xxx/xxx.mp4`. - Temporary URL (OSS): `oss://dashscope-instant/xxx/xxx.mp4` (must be obtained by uploading the file). reference_voice: type: string description: >- Audio URL for voice reference. Used to specify the voice of the subject character in the reference asset (image/video). Used together with `reference_image` or `reference_video`. The audio is only used for voice timbre reference, unrelated to the speech content. It is recommended to match the language of the reference audio with the prompt language for better results. **Voice activation logic:** - Default behavior: If the `reference_video` contains audio and no `reference_voice` is specified, the original video audio is used by default. - Priority: If both `reference_video` (with audio) and `reference_voice` are provided, `reference_voice` takes priority and overrides the video's original audio. Audio constraints: - Formats: wav, mp3. - Duration: 1 to 10 seconds. - File size: up to 15MB. Supported input formats: - Public URL: HTTP or HTTPS, e.g. `https://xxx/xxx.mp3`. - Temporary URL (OSS): `oss://dashscope-instant/xxx/xxx.mp3` (must be obtained by uploading the file). securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: API Key description: 'Pass `Authorization: Bearer ` in the request header.' ````