> ## 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 Edit > Calls Ali `wan2.7-image-pro` to perform image editing. The public calling convention keeps top-level `model`, `input`, `response_format`, and exposes `size`, `n`, `watermark`, `negative_prompt`, `seed`, `bbox_list` as top-level fields. Input images are placed in `input.messages[0].content[].image`, and the editing instruction is in a `text` item within the same array. The request body does not accept a top-level `parameters` field. ## OpenAPI ````yaml api-reference/en/zmodelImage/ali/wan-edit.json POST /v1/images/edits openapi: 3.0.1 info: title: Wan image editing version: 1.0.0 description: >- Ali Wan image editing capability documentation. The unified API endpoint is `/v1/images/edits`. This document describes the public gateway contract for `wan2.7-image-pro`: `input.messages[].content[]` carries images and text instructions, while other control fields use top-level OpenAI-style fields that the gateway maps to upstream `parameters`. 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 Image description: Wan image editing capability paths: /v1/images/edits: post: tags: - Wan Image summary: Wan image editing description: >- Calls Ali `wan2.7-image-pro` to perform image editing. The public calling convention keeps top-level `model`, `input`, `response_format`, and exposes `size`, `n`, `watermark`, `negative_prompt`, `seed`, `bbox_list` as top-level fields. Input images are placed in `input.messages[0].content[].image`, and the editing instruction is in a `text` item within the same array. The request body does not accept a top-level `parameters` field. operationId: aliWanImageEdit requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/WanImageEditRequest' examples: image_edit: summary: Image editing value: model: wan2.7-image-pro response_format: url input: messages: - role: user content: - image: https://example.com/car.webp - image: https://example.com/paint.webp - text: >- Spray the graffiti from image 2 onto the car in image 1 size: 2K 'n': 1 watermark: false negative_prompt: Preserve original car body color seed: 0 interactive_edit: summary: Interactive editing value: model: wan2.7-image-pro response_format: url input: messages: - role: user content: - image: https://example.com/clock.webp - image: https://example.com/room.webp - text: >- Place the alarm clock from image 1 at the selected area in image 2 bbox_list: - [] - - - 989 - 515 - 1138 - 681 size: 2K 'n': 1 watermark: false responses: '200': description: Success. Returns the image editing result. content: application/json: schema: $ref: '#/components/schemas/ImageResponse' '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' '413': description: Request body too large. 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: Internal server error while processing the request. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '502': description: Upstream provider returned an abnormal response. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '503': description: >- Upstream provider is temporarily unavailable, or no available channel for the current model. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - BearerAuth: [] components: schemas: WanImageEditRequest: type: object required: - model - input properties: model: type: string enum: - wan2.7-image-pro description: 'Model name. Available value: `wan2.7-image-pro`.' response_format: type: string enum: - url - b64_json description: 'Unified response format. Supported values: `url` or `b64_json`.' default: url input: $ref: '#/components/schemas/WanImageInput' size: type: string description: >- Controls output image resolution. Supports two modes (do not mix): **Mode 1: Resolution preset (recommended)** Supported presets: `1K`, `2K` (default), `4K`. - Text-to-image (no input image, non-sequential): supports 1K, 2K, 4K. - Other scenarios: supports 1K, 2K. - Pixel totals: 1K = 1024×1024, 2K = 2048×2048, 4K = 4096×4096. - With input image: output aspect ratio matches the last input image, scaled to the selected resolution. - Without input image: output is square. **Mode 2: Custom width×height** Format: `{width}*{height}`, e.g. `1024*768`. - Text-to-image: total pixels [768×768, 4096×4096], aspect ratio [1:8, 8:1]. - Other scenarios: total pixels [768×768, 2048×2048], aspect ratio [1:8, 8:1]. Note: actual output dimensions may differ slightly from the specified values. x-enum: - 1K - 2K default: 1K 'n': type: integer minimum: 1 maximum: 12 description: >- Important: `n` directly affects cost. Cost = unit price × number of successfully generated images. Confirm the model pricing before calling. When group mode is disabled, this value represents the number of generated images. Range: 1-4, default: 1. When group mode is enabled, this value represents the maximum number of generated images. Range: 1-12, default: 12. The actual count is determined by the model and will not exceed `n`. 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 negative_prompt: type: string description: Negative prompt. Describes what should be avoided in the output. seed: type: integer description: >- Random seed. Range [0, 2147483647]. Using the same seed value helps keep generation results relatively stable. If not provided, the algorithm automatically uses a random seed. Note: the generation process is probabilistic; the same seed does not guarantee identical results every time. default: 0 minimum: 0 maximum: 2147483647 bbox_list: type: array description: >+ Interactive editing bounding box regions. Correspondence: The list length must match the number of input images. If an image does not need editing, pass an empty array `[]` at the corresponding position. Coordinate format: `[x1, y1, x2, y2]` (top-left x, top-left y, bottom-right x, bottom-right y), using absolute pixel coordinates of the original image, with (0,0) at the top-left corner. Constraint: Maximum 2 bounding boxes per image. Example: Input 3 images where the 2nd image has no selection, and the 1st has two selections: ``` [ [[0, 0, 12, 12], [25, 25, 100, 100]], # Image 1 (2 boxes) [], # Image 2 (no box) [[10, 10, 50, 50]] # Image 3 (1 box) ] ``` items: type: array items: type: array items: type: integer ImageResponse: type: object properties: created: type: integer format: int64 description: Response generation timestamp. data: type: array description: List of generated image results. items: $ref: '#/components/schemas/ImageData' metadata: type: object description: Pass-through raw response metadata from the upstream provider. 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 an upstream-compatible error type. code: type: string param: type: string WanImageInput: type: object required: - messages properties: messages: type: array minItems: 1 maxItems: 1 description: >- Message content array. Currently only single-turn conversation is supported, i.e. one set of `role`/`content` parameters. Multi-turn conversation is not supported. items: $ref: '#/components/schemas/WanImageMessage' ImageData: type: object properties: url: type: string description: Used when the result is returned as a URL. b64_json: type: string description: Used when the result is returned as Base64. revised_prompt: type: string description: Revised prompt returned by the upstream provider. WanImageMessage: type: object required: - role - content properties: role: type: string enum: - user description: Fixed to `user`. content: type: array description: Message content array. Contains `text` and/or `image` objects. items: $ref: '#/components/schemas/WanImageContent' WanImageContent: type: object properties: image: type: string description: >- Input image URL or Base64 encoded string. Image restrictions: Image formats: JPEG, JPG, PNG (no alpha channel), BMP, WEBP. Image resolution: width and height must both be in the range [240, 8000] pixels, aspect ratio [1:8, 8:1]. File size: up to 20MB. Image count limits: 0-9 images can be provided. When inputting multiple images, pass multiple `image` objects in the `content` array in sequential order. Supported input formats: - Publicly accessible URL Supports HTTP or HTTPS. Example: `http://wanx.alicdn.com/material/xxx.jpeg`. - Base64 encoded image string Format: `data:{MIME_type};base64,{base64_data}` Example: `data:image/jpeg;base64,GDU7MtCZzEbTbmRZ...` (illustration only, actual complete string required). text: type: string maxLength: 5000 description: >- Prompt. Supports Chinese and English, up to 5000 characters (each character, letter, digit, or symbol counts as one). Excess characters will be automatically truncated. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ````