# Generate Image **Introduction** The "Generate Image" step allows for the creation of images based on textual prompts. This functionality is ideal for generating visual content dynamically within automations, leveraging advanced AI models to interpret and visualize prompts into images. **Configuration** * **API Token**: The required API token for accessing the image generation service. * **Prompt**: The textual description of the image to be generated. This prompt should be as descriptive as possible to guide the AI in creating an image that closely matches the desired outcome. * **Count**: Specify the number of images to generate from the prompt. You can generate between 1 and 10 images per request. Default is 1. * **Size**: Choose the resolution of the generated images. Options include 256x256, 512x512, or 1024x1024 pixels. Selecting a higher resolution will result in more detailed images. **Outputs** * **Images**: A list of objects representing the generated images. Each object contains: * **URL**: The URL where the generated image can be accessed. This allows for easy retrieval and use of the image within your automation or application. **Usage** This step can be utilized in various scenarios, such as creating visual content for social media posts, generating images for digital marketing campaigns, or simply enriching your applications with dynamic and customized visual elements based on user input or predefined prompts. By configuring the "Generate Image" step with a detailed prompt and appropriate settings, you can unlock creative possibilities and enhance your digital content with unique, AI-generated images tailored to your needs. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.flexy.bot/modules/openai/steps/generate-image.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.