nanobanana

Name: nanobanana
Availability: InStock
Author: danishi

Generate and edit images with Google Gemini models via Python scripts.

Updated Feb 23, 2026

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

Ready to run

npx skills add https://github.com/danishi/arcadia --skill nanobanana-danishi

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nanobanana
Source: https://github.com/danishi/arcadia/tree/main/.claude/skills/nanobanana
Command: npx skills add https://github.com/danishi/arcadia --skill nanobanana-danishi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the creation and modification of images using advanced AI models, making visual content generation accessible and efficient.

Core Features & Use Cases

Text-to-Image Generation: Create unique images from detailed text descriptions.
Image Editing: Modify existing images based on new prompts, with support for multiple input images.
Configurable Output: Control aspect ratio, resolution (1K, 2K, 4K), and enable Google Search grounding for accuracy.
Use Case: Generate a series of social media graphics for a new product launch, ensuring consistent branding by specifying aspect ratios and styles, or edit a photo to change the background to a beach scene.

Quick Start

Use the nanobanana skill to generate an image of a futuristic city skyline at sunset.

Frequently Asked Questions about nanobanana

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

FAQPage Schema

How do I generate images from text descriptions using Gemini models?▼

You can generate images from text by providing detailed descriptions to the skill, which automatically selects between Gemini Pro and Flash models based on prompt complexity to create the visual content.

Can I edit multiple existing images with a new text prompt?▼

Yes, you can edit multiple input images simultaneously by providing new text prompts, allowing you to modify existing visual content based on your updated requirements.

What resolutions and aspect ratios can I configure for AI image generation?▼

You can configure aspect ratios and select from multiple resolution options, including 1K, 2K, and 4K, to control the dimensions and quality of the generated output images.

Does this image generation skill support Google Search grounding for accuracy?▼

Yes, Google Search grounding can be enabled to enhance the accuracy of the generated images, ensuring the visual content aligns with factual information retrieved from the web.

Do I need to install specific Python libraries to run the text-to-image scripts?▼

Yes, you must install the google-genai and Pillow Python libraries in your environment to execute the scripts that handle the image generation and editing operations.