> ## Documentation Index > Fetch the complete documentation index at: https://docs.img-processing.com/llms.txt > Use this file to discover all available pages before exploring further. # Visualize Image > Answer a prompt based on the content of an image. ### Description This endpoint returns a response based on the content of an image and a base prompt. The prompt can be a question, statement, or any text that you want to ask about the image. The API will analyze the content of the image and generate a response based on the prompt using a pre-trained model. Right now there are two models available for this endpoint: * **Uform-Gen**: [UForm-Gen is a small](https://huggingface.co/unum-cloud/uform-gen2-qwen-500m) generative vision-language model primarily designed for Image Captioning and Visual Question Answering. * **Llava**: [LLaVA](https://huggingface.co/llava-hf/llava-1.5-7b-hf) is a large multimodal model that can generate text based on images and text prompts. * **Gemini**: [Gemini](https://deepmind.google/models/gemini/) is a multimodal model with advanced capabilities for understanding and generating text based on images. Test images may return accurate results due the `test` watermarks applied to them. If you want to get better results, please use live images. If you just want to test this feature, contact support to temporarily upgrade your account. *** ## OpenAPI ````yaml openapi.json post /v1/images/{image_id}/visualize openapi: 3.1.0 info: title: IMG Processing API description: > This powerful and flexible API provides a wide range of image manipulation and analysis capabilities, allowing developers to integrate advanced image processing features into their applications with ease. version: 1.0.0 servers: - url: https://api.img-processing.com description: IMG Processing API Server security: - ApiKeyAuth: [] paths: /v1/images/{image_id}/visualize: post: tags: - Analysis Endpoints summary: Visualize Image description: >- This endpoint returns a response based on the content of an image and a base prompt. The prompt can be a question, statement, or any text that you want to ask about the image. The API will analyze the content of the image and generate a response based on the prompt using a pre-trained model. Right now there are three models available for this endpoint: - Uform-Gen: UForm-Gen is a small generative vision-language model primarily designed for Image Captioning and Visual Question Answering. - Llava: LLaVA is a large multimodal model that can generate text based on images and text prompts. - Gemini: Gemini is a multimodal model with advanced capabilities for understanding and generating text based on images. operationId: visualize parameters: - in: path name: image_id schema: type: string description: >- The unique identifier of the image. This identifier is used to reference the image in subsequent requests. required: true requestBody: content: application/json: schema: type: object properties: prompt: type: string minLength: 1 maxLength: 1000 description: >- The prompt to answer based on the content of the image. This is a natural language question or instruction that the model will respond to. model: type: string enum: - uform-gen - llava - gemini description: >- The model to use for the visualization. Supported models are uform-gen, llava, and gemini. If not provided, the default model will be used. required: - prompt examples: - prompt: What is in this image? model: uform-gen responses: '201': description: The API will return the Image object in the response body. content: application/json: schema: $ref: '#/components/schemas/VisualizeResponse' '401': description: >- Error object for unauthorized access. Probably due to missing or invalid API key. content: application/json: schema: $ref: '#/components/schemas/UnauthorizedError' '403': description: >- Error object for forbidden access. Probably due to insufficient permissions. content: application/json: schema: $ref: '#/components/schemas/ForbiddenError' '422': description: Error object for validation errors. content: application/json: schema: $ref: '#/components/schemas/ValidationError' '429': description: Error object for rate limit exceeded. content: application/json: schema: $ref: '#/components/schemas/RateLimitError' 5XX: description: Error object for internal server errors. content: application/json: schema: $ref: '#/components/schemas/ServerError' components: schemas: VisualizeResponse: type: object properties: response: type: string description: >- The response from the AI model. This is the description of the image based on the prompt provided. required: - response title: Visualize Response description: Response object for the visualize endpoint. examples: - response: >- A beautiful sunset over the mountains with a clear sky and vibrant colors. UnauthorizedError: type: object properties: type: type: string description: The type of error error: type: string description: The title of the error status: type: number const: 401 description: The status of the error message: type: string description: The error message required: - type - error - status - message title: Unauthorized Error description: >- Error object for unauthorized access. Probably due to missing or invalid API key examples: - type: https://docs.img-processing.com/errors/unauthorized error: Unauthorized status: 401 message: API key is required. ForbiddenError: type: object properties: type: type: string description: The type of error error: type: string description: The title of the error status: type: number const: 403 description: The status of the error message: type: string description: The error message required: - type - error - status - message title: Forbidden Error description: >- Error object for forbidden access. Probably due to insufficient permissions. examples: - type: https://docs.img-processing.com/errors/forbidden error: Forbidden status: 403 message: You are not allowed to access this image. ValidationError: type: object properties: type: type: string description: The type of error error: type: string description: The title of the error status: type: number const: 422 description: The status of the error errors: type: array items: type: string description: The validation errors required: - type - error - status - errors title: Validation Error description: Error object for validation errors examples: - type: https://docs.img-processing.com/errors/validation-error error: Validation Error status: 422 errors: - '{field or param} {error message}' RateLimitError: type: object properties: type: type: string description: The type of error error: type: string description: The title of the error status: type: number const: 429 description: The status of the error message: type: string description: The error message required: - type - error - status - message title: Rate Limit Error description: Error object for rate limit exceeded. examples: - type: https://docs.img-processing.com/errors/too-many-requests error: Too Many Requests status: 429 message: Rate limit exceeded. Try again later. ServerError: type: object properties: type: type: string description: The type of error error: type: string description: The title of the error status: type: number description: The status of the error message: type: string description: The error message required: - type - error - status - message title: Server Error description: Error object for internal server errors. examples: - type: https://docs.img-processing.com/errors/internal-error error: Internal Error status: 500 message: >- An unexpected error occurred. Please try again later. If the problem persists, contact support. securitySchemes: ApiKeyAuth: type: apiKey in: header name: x-api-key description: API Key for authentication ````