nanobanana

Text-to-image and image editing powered by Google's Gemini 3 Pro Image model. Generate and edit images using Google's Gemini 3 Pro Image model ( gemini-3-pro-image-preview , nicknamed "Nano Banana Pro" 🍌). Required: Install dependencies: Main image generation script. Supported aspect ratios: Generate multiple images with sequential naming. Example: You can also use the module directly: Create images from text descriptions. The model excels at: Transform existing images with natural language: Enable --search for factually accurate images involving: Good prompts include: Example: "API key not found" "No image in response" "Rate limit exceeded" - Supports text-to-image generation, image editing with natural language prompts, and batch generation of multiple variations - Offers flexible aspect ratios (1:1, 16:9, 21:9, etc.) and high-resolution output up to 4K for enhanced detail - Includes optional Google Search grounding for factually accurate images of real people, places, and landmarks - Provides both command-line scripts and Python API for direct integration into agent workflows - GEMINI_API_KEY - Get from Google AI Studio - Python 3.10+ with google-genai package - 1:1 - Square (default) - 2:3 , 3:2 - Portrait/Landscape - 3:4 , 4:3 - Standard - 4:5 , 5:4 - Photo - 9:16 , 16:9 - Widescreen - 21:9 - Ultra-wide/Cinematic - Photorealistic images - Artistic styles (pixel art,...