> ## 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 generation and editing 3.0 > Call Alibaba Cloud Qwen `qwen-image-3.0-pro` model to perform image generation and editing tasks, supporting both Text-to-Image (T2I) and Image-to-Image/Editing (I2I). **Text-to-Image (T2I)**: `input.messages[0].content[]` only contains a `text` object (prompt). **Image-to-Image/Editing (I2I)**: `input.messages[0].content[]` contains 1-3 `image` objects (input image URLs or Base64) and 1 `text` object (editing instruction). The `parameters` field controls resolution `size`, count `n`, intelligent prompt rewriting `prompt_extend` and `prompt_extend_mode`, negative prompt `negative_prompt`, watermark `watermark`, random seed `seed`, etc. ## OpenAPI ````yaml api-reference/en/zmodelImage/ali/api/qwen-image-3.0.json POST /ali/api/v1/services/aigc/multimodal-generation/generation openapi: 3.0.1 info: title: Qwen - Image generation and editing 3.0 version: 1.0.0 description: >- Alibaba Cloud Qwen Image 3.0 capability documentation. The platform unified API endpoint is `/ali/api/v1/services/aigc/multimodal-generation/generation`. This document describes the image generation and editing contract for the `qwen-image-3.0-pro` model: supports both Text-to-Image (T2I) and Image-to-Image/Editing (I2I). For T2I, `input.messages[].content[]` only contains a `text` prompt; for I2I, `content[]` carries 1-3 input images and 1 editing instruction. The `parameters` field controls resolution, count, prompt rewriting mode, negative prompt, watermark, seed, etc. license: name: Project License url: https://github.com/QuantumNous/new-api/blob/main/LICENSE servers: - url: https://api.powertokens.ai description: baze platform API server endpoint security: [] tags: - name: Qwen Image description: Qwen image generation and editing capability paths: /ali/api/v1/services/aigc/multimodal-generation/generation: post: tags: - Qwen Image summary: Qwen - Image generation and editing 3.0 description: >- Call Alibaba Cloud Qwen `qwen-image-3.0-pro` model to perform image generation and editing tasks, supporting both Text-to-Image (T2I) and Image-to-Image/Editing (I2I). **Text-to-Image (T2I)**: `input.messages[0].content[]` only contains a `text` object (prompt). **Image-to-Image/Editing (I2I)**: `input.messages[0].content[]` contains 1-3 `image` objects (input image URLs or Base64) and 1 `text` object (editing instruction). The `parameters` field controls resolution `size`, count `n`, intelligent prompt rewriting `prompt_extend` and `prompt_extend_mode`, negative prompt `negative_prompt`, watermark `watermark`, random seed `seed`, etc. operationId: aliQwenImage30Generation requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ImageGenerationRequest' examples: text_to_image: summary: Text-to-Image (T2I) value: model: qwen-image-3.0-pro input: messages: - role: user content: - text: >- A flower shop with exquisite windows and a beautiful wooden door, various fresh flowers displayed at the entrance, sunlight streaming through the windows onto the flowers, ancient European buildings on both sides of the street, warm and romantic atmosphere. parameters: prompt_extend: true prompt_extend_mode: direct 'n': 1 watermark: false image_to_image: summary: Image-to-Image / Editing (I2I) value: model: qwen-image-3.0-pro input: messages: - role: user content: - image: >- https://alidocs.oss-cn-zhangjiakou.aliyuncs.com/res/yBRq1ZPYEaXdyOdv/img/33a80a19-7ac7-4c64-b0fa-7d685b7046a0.png - text: >- Generate a high-end urban style portrait photo, perfectly preserving the facial features and long black hair of this young woman from the input image. Change her outfit to an elegant urban professional look, set the scene in a modern minimalist high-end coffee shop. parameters: prompt_extend: true prompt_extend_mode: direct 'n': 1 watermark: false multi_image_edit: summary: Multi-image editing value: model: qwen-image-3.0-pro input: messages: - role: user content: - image: https://example.com/input1.png - image: https://example.com/input2.png - text: >- Blend the styles of both images to generate a new artwork parameters: prompt_extend: true 'n': 1 size: 1024*1024 watermark: false responses: '200': description: Successfully returns image generation results. 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: output_height: 1024 output_width: 1024 input_image_count: 1 input_image_type: qima_input_1k output_image_count: 1 output_image_type: qima_output_1k 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 account quota exceeded. 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 temporarily unavailable, or no available channel for the current model. content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - BearerAuth: [] components: schemas: ImageGenerationRequest: type: object required: - model - input properties: model: type: string enum: - qwen-image-3.0-pro description: 'Model name. Example value: `qwen-image-3.0-pro`.' input: $ref: '#/components/schemas/QwenImage30Input' parameters: $ref: '#/components/schemas/QwenImage30Parameters' 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. Can be used for request tracing and troubleshooting. code: type: string description: Error code for failed requests. Not returned on success. message: type: string description: Detailed error message for failed requests. Not returned on success. ErrorResponse: type: object properties: code: type: string description: Error code for failed requests. Not returned on success. message: type: string description: Detailed error message for failed requests. Not returned on success. request_id: type: string description: >- Unique request identifier. Can be used for request tracing and troubleshooting. QwenImage30Input: type: object required: - messages properties: messages: type: array minItems: 1 maxItems: 1 description: >- Request content array. Currently only single-turn conversation is supported, so the array contains exactly one object. items: $ref: '#/components/schemas/QwenImage30Message' description: Input parameter object. QwenImage30Parameters: type: object properties: prompt_extend: type: boolean default: true description: >- Whether to enable intelligent prompt rewriting, default is `true` (recommended). When enabled, the model optimizes the positive prompt according to the `prompt_extend_mode` setting, significantly improving results for simpler prompts. prompt_extend_mode: type: string default: direct enum: - direct - agent description: >- Prompt rewriting method, default is `direct`. Options: - `direct`: Direct Prompt Enhancement (DPE), suitable for most scenarios. Supported for both T2I and I2I. - `agent`: Agent Prompt Enhancement (APE), provides more refined rewriting. **Only supports Text-to-Image (T2I)**. Passing `agent` for I2I will return a 400 error. 'n': type: integer minimum: 1 maximum: 6 default: 1 description: Number of output images, supports 1-6 images, default is 1. size: type: string description: >- Set output image resolution, format `width*height`, e.g., `1024*1024`. When not specified, the model automatically recommends a resolution based on the prompt. - **Text-to-Image (T2I)**: Pixel area range `512*512` to `2048*2048`, aspect ratio limit 1:8 to 8:1. - **Image-to-Image (I2I)**: Pixel area range `512*512` to `2048*2048`, aspect ratio limit 1:8 to 8:1. negative_prompt: type: string description: >- Negative prompt, used to describe content you don't want to see in the image, constraining the output. Supports Chinese and English. seed: type: integer format: int64 minimum: 0 maximum: 2147483647 description: >- Random seed, range [0, 2147483647]. Using the same `seed` value keeps generation results relatively stable. If not provided, the algorithm uses a random seed. Note: The model generation process is probabilistic; even with the same `seed`, identical results are not guaranteed. watermark: type: boolean default: false description: >- Whether to add a "AI生成" watermark in the bottom-right corner of the image. Default is `false`. description: Additional parameters controlling image generation. ImageOutput: type: object properties: choices: type: array description: Result option list. items: $ref: '#/components/schemas/ImageChoice' ImageUsage: type: object properties: output_width: type: integer description: Final output image width in pixels. output_height: type: integer description: Final output image height in pixels. input_image_count: type: integer description: >- Number of input images in the request. For T2I it is 0, for I2I it returns the actual count. input_image_type: type: string description: >- Input image metering tier. Determined by output resolution pixel area: area≤2,250,000 is `qima_input_1k`, area>2,250,000 is `qima_input_2k`. output_image_count: type: integer description: Actual number of output images returned. output_image_type: type: string description: >- Output image metering tier. Determined by output resolution pixel area: area≤2,250,000 is `qima_output_1k`, area>2,250,000 is `qima_output_2k`. description: Resource usage for this call, only returned on successful calls. QwenImage30Message: 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 description: >- Message content array. Different combinations based on usage scenario: **Text-to-Image (T2I)**: Only contains one `{"text": "..."}` object. **Image-to-Image (I2I)**: Contains 1-3 `{"image": "..."}` objects and 1 `{"text": "..."}` object. items: $ref: '#/components/schemas/QwenImage30ContentItem' ImageChoice: type: object properties: finish_reason: type: string description: Task stop reason, `stop` when naturally completed. message: $ref: '#/components/schemas/ImageChoiceMessage' QwenImage30ContentItem: type: object properties: image: type: string description: >- Input image URL or Base64 encoded data. For I2I, supports 1-3 images. When multiple images are provided, the order is defined by the array sequence. **Image requirements:** - Formats: JPG, JPEG, PNG, BMP, TIFF, WEBP, and GIF. - Resolution: Recommended width and height between 384 and 2048 pixels. - Size: No larger than 10MB. **Supported input formats:** - Public URL: Supports HTTP and HTTPS protocols. - Base64 encoding: Format `data:{MIME_type};base64,{base64_data}`. text: type: string description: >- Positive prompt, used to describe the image content, style, and composition you expect to generate or edit. Supports Chinese and English. **Note**: Only one `text` is supported. Not providing one or providing multiple will result in an error. ImageChoiceMessage: type: object properties: role: type: string description: Message role, always `assistant`. content: type: array description: Message content, contains generated image information. items: $ref: '#/components/schemas/ImageChoiceContentItem' description: Message returned by the model. ImageChoiceContentItem: type: object properties: image: type: string description: >- URL of the generated image in PNG format. The link is valid for 24 hours, please download and save the image promptly. securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Pass `Authorization: Bearer ` in the request header.' ````