nano-banana

Generate and edit images from text prompts using the Gemini API.

Updated Feb 28, 2026

Search Tags:#image generation #visual content #image editing #gemini api #text-to-image #ai art

Ready to run

npx skills add https://github.com/allixsenos/claude-stuff --skill nano-banana-allixsenos

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/allixsenos/claude-stuff/tree/main/skills/nano-banana
Command: npx skills add https://github.com/allixsenos/claude-stuff --skill nano-banana-allixsenos

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows you to create and modify images directly from Claude Code, eliminating the need for external tools or complex setups.

Core Features & Use Cases

Image Generation: Create images from text prompts using various Gemini models.
Image Editing: Modify existing images (e.g., background removal, color changes).
Multiple Variations: Generate several image options in parallel.
Use Case: Generate a hero image for a blog post about Kubernetes, or create a 1:1 icon of a lightning bolt in a flat illustration style.

Quick Start

Ask Claude Code to generate an image of a futuristic cityscape at sunset.

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 text prompts using the Gemini API?▼

You can generate images from text prompts using the Gemini API by providing a descriptive text query. The tool creates the visual content directly, supporting various aspect ratios and resolutions for your generated images.

Can I edit existing images like removing backgrounds with Gemini?▼

Yes, you can edit existing images by modifying them with the Gemini API. This includes performing tasks like background removal or changing colors directly from text prompts without needing external image editing software.

Do I need an API key to generate AI art with text-to-image models?▼

Yes, an API key is required to generate AI art with text-to-image models using this tool. You also need basic command-line tools like curl and python3 installed to execute the image generation requests.

What is the best way to create multiple image variations in parallel?▼

The best way to create multiple image variations in parallel is to use the tool's built-in parallel generation options. This feature generates several image options simultaneously from your text prompts for quick comparison.

Does Claude Code support text-to-image generation without external tools?▼

Yes, Claude Code supports text-to-image generation without external tools by leveraging the Gemini API. You can create and modify visual content directly within your development environment using simple command-line instructions.