nano-banana-pro

Generate and edit images with Google Gemini models via a command-line interface.

8|Updated Jul 26, 2026

Search Tags:#automation #image generation #visual content #image editing #gemini #ai art

Ready to run

npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill nano-banana-pro-joonlab

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/joonlab/joonlab-claudecode-setting-for-share/tree/main/claude/skills/nano-banana-pro
Command: npx skills add https://github.com/joonlab/joonlab-claudecode-setting-for-share --skill nano-banana-pro-joonlab

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, pillow, and includes scripts (resource) components.

What problem does it solve?

This skill removes the friction of switching between chat interfaces and image generation tools by providing a direct, command-line-driven interface to Gemini image models for instant visual content creation and modification.

Core Features & Use Cases

Text-to-Image Generation: Create high-resolution visuals from detailed text prompts with support for multiple aspect ratios.
Image Editing: Modify existing images by providing an input file and specific editing instructions, perfect for refining infographics or adjusting visual elements.
Robust Execution: Includes automatic retry logic for 503 errors and support for both fast (flash) and high-quality (pro) model variants.

Quick Start

Use the nano-banana-pro skill to generate a 4K landscape image of a futuristic city skyline.

Frequently Asked Questions about nano-banana-pro

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate images using Google Gemini models from the command line?▼

To generate images using Google Gemini models, you provide text prompts to the command-line interface, which then synthesizes high-resolution visuals. You can specify aspect ratios and choose between fast flash or high-quality pro variants.

Can I edit existing images with Gemini without switching to a separate interface?▼

Yes, you can edit existing images with Gemini by providing an input file and specific editing instructions directly in the command-line interface. This allows you to refine infographics or adjust visual elements seamlessly.

Do I need a paid API key to use Gemini for text-to-image synthesis?▼

Yes, you need a paid API key to use Gemini for text-to-image synthesis. The environment requires the GEMINI_PAID_API_KEY environment variable to be set, along with the google-genai and pillow Python libraries.

What's the best way to handle 503 errors during AI image generation?▼

The best way to handle 503 errors during AI image generation is to rely on the built-in automatic retry logic. This robust execution feature manages temporary service unavailability automatically without interrupting your workflow.

Does this command-line image generation tool support multiple aspect ratios?▼

Yes, this command-line image generation tool supports multiple aspect ratios. You can create high-resolution visuals from detailed text prompts and specify the exact aspect ratio needed for your visual content requirements.

Why use a command-line interface for AI art instead of a chat interface?▼

Using a command-line interface for AI art removes the friction of switching between chat interfaces and image generation tools. It provides a direct, automated interface to Gemini image models for instant visual content creation.