Nanobanana Image Generation

概要

Integrate advanced AI image creation and manipulation directly into your workflow using the Google Gemini API. This skill enables the generation of visual assets from text prompts or the modification of existing images through natural language instructions. With built-in support for a wide array of aspect ratios—ranging from 1:1 squares to 21:9 ultra-wide—and resolutions up to 4K, it provides a versatile toolkit for creating logos, UI components, and social media graphics without leaving your development environment.

主な機能

• Image-to-image editing for modifying existing visual files
• Text-to-image generation using Gemini 3 Pro and 2.5 Flash models
• Support for 10+ aspect ratios including portrait, landscape, and ultra-wide
• 925 GitHub stars
• High-resolution output options ranging from 1K to 4K
• Automated file management with custom naming and UUID generation

ユースケース

• Creating custom UI assets, logos, and icons for software projects
• Rapidly prototyping visual content for social media and marketing
• Modifying existing photographs to add elements or change artistic styles