Nanobanana Image Generation

关于

Integrates Google Gemini's powerful generative AI capabilities into your environment to create or modify visual assets via simple text instructions. Whether you are generating minimalist logos, cinematic landscapes, or editing existing photos to add new elements, this skill provides granular control over the output including support for resolutions up to 4K and specialized models for both speed and quality. It streamlines the creative workflow by handling the technical requirements of the Gemini API through a localized Python interface, making it ideal for developers and designers who need rapid visual prototyping.

主要功能

• Comprehensive aspect ratio support from square to ultra-wide
• 69 GitHub stars
• Image editing and modification using existing files as input
• Dual-model support for high-quality previews or fast generation
• Text-to-image generation with descriptive prompting
• High-resolution output options including 1K, 2K, and 4K

使用场景

• Generating custom logos, icons, and UI graphics for development projects
• Creating high-resolution concept art or wallpapers using text descriptions
• Modifying existing images to add specific objects or change stylistic elements