Set up your Gemini API key to enable image generation through the Nano-Banana-MCP server. This tool configures authentication for accessing Google AI Studio's image generation capabilities.
Create images from text descriptions using Google's Nano Banana models. Specify details like style, lighting, composition, and aspect ratio for customized visual outputs.
Generate images from text descriptions using Gemini's Nano Banana models. Create visuals for various use cases with adjustable parameters like aspect ratio and quantity, automatically selecting Pro model for text-heavy prompts.
Create images from text descriptions using Google's Gemini AI model. Save generated images to a specified directory for use in projects or visual content creation.
Enables AI image generation, editing, and composition using Google's Gemini image models (Nano Banana Pro and Nano Banana). Supports text-to-image generation, multi-image composition, flexible aspect ratios, high-resolution output up to 4K, and real-time information grounding.
Enables AI agents to generate, edit, and analyze images using Google's Gemini image generation models including Nano Banana Pro (gemini-3-pro-image-preview).