generate_image
Generate images using Google Gemini AI models. Choose between fast generation with Gemini 2.0 Flash or high-quality results with Imagen 3.0. Control aspect ratios, exclude unwanted elements, and save images locally.
Instructions
Generate images using Google Gemini models. Supports 'flash' (fast, gemini-2.0-flash-exp) and 'pro' (high quality, imagen-3.0) models.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Image description prompt (1-8192 characters) | |
| model | No | Model to use: 'flash' (fast, gemini-2.0-flash-exp) or 'pro' (high quality, imagen-3.0) | flash |
| aspect_ratio | No | Image aspect ratio | 1:1 |
| negative_prompt | No | Elements to exclude from the image | |
| output_dir | No | Output directory path (default: ./nanobanana-images) | |
| count | No | Number of images to generate (1-4) |