> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # Wan2.7 Image / Pro > Generate, edit, and create image sequences with wan2.7-image and wan2.7-image-pro. ## OpenAPI ````yaml api-reference/model-api/alibaba/openapi/wan2.7-image/openapi.yaml POST /v1/images/generations openapi: 3.1.0 info: title: Wan2.7 Image / Pro description: >- Generate, edit, and create image sequences with wan2.7-image and wan2.7-image-pro through AnyFast. version: 2.0.0 servers: - url: https://www.anyfast.ai security: - bearerAuth: [] paths: /v1/images/generations: post: summary: Generate or edit images description: > Calls `wan2.7-image` or `wan2.7-image-pro` synchronously. The endpoint accepts the existing flat OpenAI-compatible format and the newly adapted nested DashScope-compatible format used by AnyFast. Supported modes: - Text-to-image - Multi-image editing and reference generation - Interactive region editing with `bbox_list` - Text-to-sequence or image-to-sequence generation with `enable_sequential` `parameters.prompt_extend` defaults to `true`. For special-content requests, select the **Special-Ns** resource group and set this parameter to `false`. operationId: createWan27Image parameters: - name: X-DashScope-DataInspection in: header required: false description: Optional DashScope data inspection control forwarded by AnyFast. schema: type: string example: '{"input":"disable","output":"disable"}' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/Wan27Request' examples: textToImage: summary: Text-to-image (flat OpenAI-compatible format) value: model: wan2.7-image prompt: >- A cinematic flower shop with detailed windows and a wooden door size: 2K 'n': 1 watermark: false thinking_mode: true singleImageEditing: summary: Single-image editing (flat OpenAI-compatible format) value: model: wan2.7-image-pro prompt: Replace the vase with a bouquet of red roses image: https://example.com/room.png size: 2K 'n': 1 multiImageEditing: summary: Multi-image editing value: model: wan2.7-image-pro input: messages: - role: user content: - image: https://example.com/person.png - image: https://example.com/background.png - text: >- Place the person from image 1 into the setting from image 2 parameters: size: 2K 'n': 1 watermark: false prompt_extend: true interactiveEditing: summary: Interactive region editing value: model: wan2.7-image-pro input: messages: - role: user content: - image: https://example.com/room.png - text: Replace the selected vase with red roses parameters: size: 2K 'n': 1 bbox_list: - - - 420 - 280 - 760 - 720 prompt_extend: true sequentialGeneration: summary: Sequential image generation value: model: wan2.7-image-pro input: messages: - role: user content: - text: >- Create four images of the same orange cat across the four seasons parameters: size: 2K enable_sequential: true 'n': 4 watermark: false prompt_extend: true responses: '200': description: Images generated successfully content: application/json: schema: $ref: '#/components/schemas/Wan27Response' example: data: - url: https://dashscope-result.example.com/generated.png b64_json: '' revised_prompt: '' created: 1784274013 metadata: output: choices: - finish_reason: stop message: content: - image: >- https://dashscope-result.example.com/generated.png type: image role: assistant finished: true usage: image_count: 1 input_tokens: 25 output_tokens: 2 size: 2048*2048 total_tokens: 27 request_id: f30f2d2b-e0ee-9a47-ba5e-68b66360fe47 '400': description: Invalid request parameters '401': description: Unauthorized '429': description: Rate limit exceeded components: schemas: Wan27Request: oneOf: - $ref: '#/components/schemas/FlatWan27Request' - $ref: '#/components/schemas/NestedWan27Request' description: Flat OpenAI-compatible request or nested DashScope-compatible request. Wan27Response: type: object required: - data - created - metadata properties: data: type: array description: AnyFast-compatible generated image results. items: type: object properties: url: type: string format: uri description: >- Temporary generated image URL. Upstream results are retained for 24 hours. b64_json: type: string description: Base64 result field. Empty for URL responses. revised_prompt: type: string description: Revised prompt field. It can be empty. created: type: integer description: Unix creation timestamp. metadata: type: object description: Upstream Wan response and usage details. properties: output: type: object properties: choices: type: array items: type: object properties: finish_reason: type: string example: stop message: type: object properties: role: type: string example: assistant content: type: array items: type: object properties: image: type: string format: uri type: type: string example: image finished: type: boolean usage: type: object properties: image_count: type: integer input_tokens: type: integer output_tokens: type: integer size: type: string example: 2048*2048 total_tokens: type: integer request_id: type: string description: Upstream request ID. FlatWan27Request: type: object required: - model - prompt properties: model: type: string enum: - wan2.7-image-pro - wan2.7-image prompt: type: string maxLength: 5000 description: Text prompt. image: type: string description: >- Optional public image URL or Base64 data URI for single-image editing. size: type: string default: 2K example: 2K 'n': type: integer minimum: 1 maximum: 12 default: 1 enable_sequential: type: boolean default: false thinking_mode: type: boolean default: true watermark: type: boolean default: false seed: type: integer minimum: 0 maximum: 2147483647 response_format: type: string enum: - url - b64_json default: url NestedWan27Request: type: object required: - model - input properties: model: type: string enum: - wan2.7-image-pro - wan2.7-image description: >- Model ID. `wan2.7-image-pro` supports 4K for non-sequential text-to-image; `wan2.7-image` supports up to 2K and is faster. example: wan2.7-image-pro input: type: object required: - messages properties: messages: type: array minItems: 1 maxItems: 1 description: >- A single user message. Multi-turn conversations are not supported. items: type: object required: - role - content properties: role: type: string enum: - user description: Message role. Must be `user`. content: type: array minItems: 1 description: >- Prompt and zero to nine input images. Item order defines image order. items: oneOf: - $ref: '#/components/schemas/TextContent' - $ref: '#/components/schemas/ImageContent' parameters: $ref: '#/components/schemas/Wan27Parameters' TextContent: type: object required: - text properties: text: type: string maxLength: 5000 description: >- Chinese or English prompt. Content after 5,000 characters is truncated upstream. example: A cinematic flower shop with detailed windows and a wooden door ImageContent: type: object required: - image properties: image: type: string description: > Public HTTP/HTTPS URL or Base64 data URI (`data:{MIME};base64,{data}`). Supported formats: JPEG, JPG, PNG without transparency, BMP, WEBP. Maximum 20 MB per image; width and height 240–8,000 px; aspect ratio 1:8–8:1. A request can contain up to 9 images. example: https://example.com/input.png Wan27Parameters: type: object properties: size: type: string default: 2K description: > Output resolution. - `wan2.7-image-pro`: 1K, 2K, or 4K for non-sequential text-to-image; other modes support 1K or 2K. - `wan2.7-image`: 1K or 2K for all modes. Custom dimensions are also accepted within the upstream pixel and aspect-ratio limits. example: 2K 'n': type: integer minimum: 1 maximum: 12 description: >- Number of images. Non-sequential mode: 1–4, default 1. Sequential mode: maximum output count 1–12, default 12. example: 1 enable_sequential: type: boolean default: false description: >- Enables text-to-sequence or image-to-sequence generation. Actual output count does not exceed `n`. thinking_mode: type: boolean default: true description: >- Improves text-to-image quality. Only applies when no image is supplied and sequential mode is disabled. prompt_extend: type: boolean default: true description: >- Controls AnyFast prompt extension. For special-content requests, select the Special-Ns resource group and set this parameter to `false`. bbox_list: type: array description: >- Interactive editing boxes. Provide one box list per input image; use an empty list when an image has no box. Each image supports up to two boxes. items: type: array maxItems: 2 items: type: array minItems: 4 maxItems: 4 items: type: integer minimum: 0 description: Absolute source-image coordinates `[x1, y1, x2, y2]`. color_palette: type: array minItems: 3 maxItems: 10 description: >- Color theme available when sequential mode is disabled. Ratios must total 100.00%. items: type: object required: - hex - ratio properties: hex: type: string pattern: ^#[0-9A-Fa-f]{6}$ example: '#E63946' ratio: type: string pattern: ^[0-9]+\.[0-9]{2}%$ example: 25.00% watermark: type: boolean default: false description: Adds the fixed AI-generated watermark in the lower-right corner. seed: type: integer minimum: 0 maximum: 2147483647 description: >- Random seed. Equal values can produce similar outputs, but exact reproduction is not guaranteed. securitySchemes: bearerAuth: type: http scheme: bearer ````