nano-banana

Generate images from natural language prompts via the Gemini API.

8|3|Updated Jan 17, 2026
One-click install
npx skills add https://github.com/dennisonbertram/claude-media-skills --skill nano-banana-dennisonbertram
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/dennisonbertram/claude-media-skills/tree/main/nano-banana
Command: npx skills add https://github.com/dennisonbertram/claude-media-skills --skill nano-banana-dennisonbertram

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires curl, jq, base64, osascript, security, open, and includes scripts (resource) components.

What problem does it solve?

This Skill enables rapid visual content creation by converting natural language prompts into Gemini-based images, accelerating ideation and output for creatives.

Core Features & Use Cases

  • Prompt enhancement: Always enhance user prompts using the techniques in PROMPTING.md.
  • Flexible rendering: Supports size, aspect ratio, and model variant (--pro or --flash) for quality and speed.
  • Image-to-image capability: Optional reference image for character consistency.
  • Easy integration: Quick Start script at ~/.claude/skills/nano-banana/scripts/generate.sh.

Quick Start

Use the nano-banana skill to generate an image from a prompt: ~/.claude/skills/nano-banana/scripts/generate.sh "a futuristic cityscape" --size 2K --aspect 16:9

Frequently Asked Questions about nano-banana

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

FAQPage Schema
How do I generate images from natural language prompts using Gemini?

To generate images from natural language prompts using Gemini, you can use a shell script to automate the process. It converts your text prompts into Gemini-based images, enabling fast iteration for creative visuals, marketing assets, and concept art.

Can I use a reference image for character consistency when generating Gemini images?

Yes, you can use an optional reference image for character consistency during image generation. This image-to-image capability allows you to maintain visual consistency across generated assets while applying prompt enhancements.

Do I need a Gemini API key to generate images from the command line?

Yes, you need Gemini API access to generate images from the command line. The script automates rendering through the API, allowing you to adjust size, aspect ratio, and model variants like pro or flash for quality and speed.

What is the best way to adjust aspect ratio and image size for Gemini image generation?

The best way to adjust aspect ratio and image size is by passing specific parameters to the generation script. You can specify dimensions like 2K and aspect ratios like 16:9 to control the output format for your creative visuals.

How does prompt enhancement work for AI image generation?

Prompt enhancement for AI image generation automatically refines your natural language input using specific techniques. This ensures consistent output quality and faster ideation when converting text prompts into creative visuals or concept art.

What is the difference between the pro and flash models for generating images?

The difference between pro and flash models lies in rendering quality versus speed. You can select the pro variant for higher quality output or the flash variant for faster image generation depending on your creative asset needs.