nanobanana  by gemini-cli-extensions

AI image generation and manipulation CLI extension

Created 3 months ago
674 stars

Top 50.3% on SourcePulse

GitHubView on GitHub
Project Summary

A Gemini CLI extension, Nano Banana provides a powerful command-line interface for generating and manipulating images using the Gemini 2.5 Flash Image model. It targets Gemini CLI users seeking efficient, AI-driven image creation and editing capabilities directly from their terminal, offering a versatile toolset for various visual tasks.

How It Works

Nano Banana leverages the Gemini 2.5 Flash Image model through the Gemini CLI's extension framework, utilizing the Model Context Protocol (MCP) SDK for robust client-server communication. Its architecture is modular, with dedicated components for image generation, editing, restoration, file management, and protocol handling. This design allows for specialized command execution and flexible integration with the Gemini CLI ecosystem.

Quick Start & Requirements

  • Primary install: gemini extensions install https://github.com/gemini-cli-extensions/nanobanana
  • Prerequisites: Gemini CLI installed and configured; Node.js 20+ and npm; API Key set via environment variables (NANOBANANA_GEMINI_API_KEY, NANOBANANA_GOOGLE_API_KEY, GEMINI_API_KEY, or GOOGLE_API_KEY). Refer to the official Gemini CLI documentation for authentication setup.
  • Links: Official Gemini CLI documentation for authentication.

Highlighted Details

  • Versatile Image Tasks: Supports text-to-image generation, image editing, restoration, app icon/favicon generation, seamless pattern creation, visual storytelling sequences, and technical diagram generation (flowcharts, architecture, etc.).
  • Command Interface: Offers specific commands like /generate, /edit, /restore, /icon, /pattern, /story, /diagram, alongside a flexible natural language /nanobanana interface.
  • Advanced Options: Features include style variations, image count control, preview generation, seeding for reproducibility, and various output formats and styles.
  • Smart File Management: Implements user-friendly, prompt-based filenames with automatic duplicate prevention and configurable search paths for input files, saving outputs to ./nanobanana-output/.

Maintenance & Community

The project follows a standard open-source contribution model via pull requests on GitHub. Development commands include npm run build, npm run install-deps, and npm run dev. The MCP server has its own build and run commands. No specific community channels (e.g., Discord, Slack) or roadmap links are detailed in the provided README.

Licensing & Compatibility

  • License: Apache License 2.0.
  • Compatibility: The Apache 2.0 license is permissive, generally allowing for commercial use and integration within closed-source projects.

Limitations & Caveats

As an extension, Nano Banana's functionality is dependent on a correctly installed and configured Gemini CLI environment. The README indicates comprehensive error handling and debugging features, suggesting potential complexities in setup or API key configuration. The project relies on the Gemini 2.5 Flash Image model, and its performance is tied to the underlying model's capabilities and limitations.

Health Check
Last Commit

4 days ago

Responsiveness

Inactive

Pull Requests (30d)
3
Issues (30d)
3
Star History
118 stars in the last 30 days

Explore Similar Projects

Starred by Peter Norvig Peter Norvig(Author of "Artificial Intelligence: A Modern Approach"; Research Director at Google).

NanoBananaEditor by markfulton

1.8%
570
Advanced AI image generation and editing platform
Created 4 months ago
Updated 3 months ago
Feedback? Help us improve.