> ## 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. # Qwen image edit > Calls the Ali `qwen-image-2.0-pro` model to perform image editing. The `input.messages[0].content[]` array must contain 1-3 `image` objects (input image URL or Base64 data) and 1 `text` object (edit instruction). The `parameters` field controls output count `n`, negative prompt `negative_prompt`, resolution `size`, smart prompt rewriting `prompt_extend`, watermark `watermark`, and random seed `seed`. ## OpenAPI ````yaml api-reference/en/zmodelImage/ali/api/qwen-image-edit.json POST /ali/api/v1/services/aigc/multimodal-generation/generation openapi: 3.0.1 info: title: Qwen image edit version: 1.0.0 description: >- Ali Qwen image edit capability documentation. The unified API endpoint is `/ali/api/v1/services/aigc/multimodal-generation/generation`. This document describes the public gateway contract for `qwen-image-2.0-pro`: `input.messages[].content[]` carries 1-3 input images and 1 edit instruction, and `parameters` controls negative prompt, count, watermark, and random 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: Qwen Image description: Qwen image edit capability paths: /ali/api/v1/services/aigc/multimodal-generation/generation: post: tags: - Qwen Image summary: Qwen image edit description: >- Calls the Ali `qwen-image-2.0-pro` model to perform image editing. The `input.messages[0].content[]` array must contain 1-3 `image` objects (input image URL or Base64 data) and 1 `text` object (edit instruction). The `parameters` field controls output count `n`, negative prompt `negative_prompt`, resolution `size`, smart prompt rewriting `prompt_extend`, watermark `watermark`, and random seed `seed`. operationId: aliQwenImageEdit requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageEditRequest' examples: qwen_image_2_pro_edit: summary: Qwen-Image-2.0 Pro image edit value: model: qwen-image-2.0-pro input: messages: - role: user content: - image: >- https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20260310/jiydyi/image+%2818%29-2026-03-10-16-39-59.webp - text: >- 在画面右下角石板路旁、靠近树干根部的位置，以浅灰墨色手写体题写一首七言绝句，字体为行楷风格，笔触自然流畅、略带飞白，大小适中（约占画面高度1/10），与整体水墨淡雅氛围协调。诗文内容为：“青石桥畔柳风轻， 素手拈花闭目听。 一水碧痕浮旧梦， 半篙烟雨入空舲。”诗句横向排列，四句分两行书写（前两句一行，后两句一行），末句“舲”字右下角钤一枚朱红小印，印文为“江南”二字篆书，尺寸约等于单字高度的1/3。 parameters: 'n': 1 negative_prompt: ' ' prompt_extend: true watermark: false size: 2048*2048 responses: '200': description: Success. Returns the image edit result. content: application/json: schema: $ref: '#/components/schemas/ImageResponse' examples: success: summary: Success response value: output: choices: - finish_reason: stop message: content: - image: >- https://dashscope-result-sz.oss-cn-shenzhen.aliyuncs.com/xxx.png?Expires=xxx role: assistant usage: height: 2048 image_count: 1 width: 2048 request_id: 571ae02f-5c9d-436c-83c2-f221e6df0xxx '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: ImageEditRequest: type: object required: - model - input properties: model: type: string enum: - qwen-image-2.0-pro description: 'Model name. Example: `qwen-image-2.0-pro`.' input: $ref: '#/components/schemas/QwenImageEditInput' parameters: $ref: '#/components/schemas/QwenImageEditParameters' ImageResponse: type: object properties: output: $ref: '#/components/schemas/ImageOutput' description: Contains model generation results. usage: $ref: '#/components/schemas/ImageUsage' request_id: type: string description: >- Unique request identifier. It can be used for request traceability and troubleshooting. code: type: string description: >- Error code returned when the request fails. This parameter is not returned on success. message: type: string description: >- Detailed error message returned when the request fails. This parameter is not returned on success. ErrorResponse: type: object properties: code: type: string description: >- Error code returned when the request fails. This parameter is not returned on success. message: type: string description: >- Detailed error message returned when the request fails. This parameter is not returned on success. request_id: type: string description: >- Unique request identifier. It can be used for request traceability and troubleshooting. QwenImageEditInput: type: object required: - messages properties: messages: type: array minItems: 1 maxItems: 1 description: >- Request content array. Currently only single-turn conversations are supported, so the array must contain exactly one object with `role` and `content` properties. items: $ref: '#/components/schemas/QwenImageEditMessage' description: Input parameter object. QwenImageEditParameters: type: object properties: negative_prompt: type: string maxLength: 500 description: >- Negative prompt used to describe content you do not want to see in the image and to constrain the image. Chinese and English are supported. Maximum length is 500 characters; each Chinese character, letter, number, or symbol counts as one character, and extra content is automatically truncated. Example: low resolution, errors, worst quality, low quality, incomplete content, extra fingers, poor proportions, etc. 'n': type: integer minimum: 1 maximum: 6 default: 1 description: >- Number of output images. Default is 1. For the `qwen-image-2.0` series, you can generate 1-6 images. watermark: type: boolean default: false description: >- Whether to add a "Qwen-Image" watermark in the lower-right corner of the image. Default is `false`. seed: type: integer format: int64 minimum: 0 maximum: 2147483647 description: >- Random seed. Range [0, 2147483647]. Using the same `seed` value can make generated content relatively stable. If omitted, the algorithm automatically uses a random seed. Note: generation is probabilistic, so the same `seed` cannot guarantee identical results every time. size: type: string description: >- Output image resolution in `width*height` format, for example `1024*1536`. For the `qwen-image-2.0` series, total pixels must be between `512*512` and `2048*2048`. By default, total pixels are close to `1024*1024`, and the aspect ratio is close to the input image (for multi-image input, the last image). Recommended common resolutions: 1:1 `1024*1024`, `1536*1536`; 2:3 `768*1152`, `1024*1536`; 3:2 `1152*768`, `1536*1024`; 3:4 `960*1280`, `1080*1440`; 4:3 `1280*960`, `1440*1080`; 9:16 `720*1280`, `1080*1920`; 16:9 `1280*720`, `1920*1080`; 21:9 `1344*576`, `2048*872`. prompt_extend: type: boolean default: true description: >- Whether to enable smart prompt rewriting. Default is `true`. When enabled, the model optimizes the positive prompt (`text`), which is especially helpful for simple prompts. description: Additional parameters controlling image generation. ImageOutput: type: object properties: choices: type: array description: Result choices list. items: $ref: '#/components/schemas/ImageChoice' ImageUsage: type: object properties: image_count: type: integer description: Number of generated images. width: type: integer description: Generated image width in pixels. height: type: integer description: Generated image height in pixels. description: Resource usage for this call. Returned only when the call succeeds. QwenImageEditMessage: type: object required: - role - content properties: role: type: string enum: - user description: Message sender role. Must be set to `user`. content: type: array minItems: 1 maxItems: 3 description: >- Message content. Includes 1-3 images in `{"image":"..."}` format and a single edit instruction in `{"text":"..."}` format. items: $ref: '#/components/schemas/QwenImageEditContentItem' ImageChoice: type: object properties: finish_reason: type: string description: Reason the task stopped. `stop` indicates a natural stop. message: $ref: '#/components/schemas/ImageChoiceMessage' QwenImageEditContentItem: type: object required: - image - text properties: image: type: string description: >- URL or Base64-encoded data of the input image. Supports 1-3 images. For multi-image input, the image order is defined by the array order, and the output image aspect ratio follows the last image. Image requirements: Image formats: JPG, JPEG, PNG, BMP, TIFF, WEBP, and GIF. The output image is in PNG format; for GIF animations, only the first frame is processed. Image resolution: For best results, it is recommended that both width and height be between 384 and 3072 pixels. Low resolution may cause blurry results, while excessively high resolution increases processing time. Image size: No more than 10MB. Supported input formats Public URL: Supports HTTP and HTTPS protocols. Example: `https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250925/fpakfo/image36.webp`. Temporary URL: Supports the OSS protocol; you must upload a file to obtain a temporary URL. Example: oss://dashscope-instant/xxx/2024-07-18/xxx/cat.png. Base64-encoded image string Example: data:image/jpeg;base64,GDU7MtCZz... (truncated for demonstration only) text: type: string description: >- Positive prompt used to describe the image content, style, and composition you want to generate. Chinese and English are supported. The `qwen-image-2.0` series supports up to 1300 tokens; extra content is automatically truncated. Note: only one `text` item is supported; omitting it or passing multiple text items causes an error. ImageChoiceMessage: type: object properties: role: type: string description: Message role. Fixed to `assistant`. content: type: array description: Message content containing generated image information. items: $ref: '#/components/schemas/ImageChoiceContentItem' description: Message returned by the model. ImageChoiceContentItem: type: object properties: image: type: string description: >- Generated image URL in PNG format. The link is valid for 24 hours; download and save the image promptly. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ````