nanobanana

Generates and edits images via the Google Gemini API.

7|1|Updated Jan 14, 2026

Search Tags:#image generation #visual design #image editing #gemini #creative tools #ai art

Ready to run

npx skills add https://github.com/eyadsibai/ltk --skill nanobanana-eyadsibai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nanobanana
Source: https://github.com/eyadsibai/ltk/tree/main/plugins/ltk-core/skills/nanobanana
Command: npx skills add https://github.com/eyadsibai/ltk --skill nanobanana-eyadsibai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies the process of creating and modifying images using AI, allowing users to generate visuals from text prompts or edit existing images with specific instructions.

Core Features & Use Cases

Image Generation: Create new images based on detailed text descriptions.
Image Editing: Modify existing images by applying changes described in a prompt.
Customization: Control aspect ratio, model, and resolution for tailored outputs.
Use Case: Generate a unique logo for a new tech startup or edit a photograph to add a specific element like a sunset.

Quick Start

Generate a square logo with the text "Minimalist tech logo" and save it as logo.png.

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 prompts using the Google Gemini API?▼

To generate images from text prompts using the Google Gemini API, you provide a detailed text description to the Skill. It processes your request and creates new visuals based on your specified aspect ratio, model, and resolution.

Can I edit existing images with AI using Python and Pillow?▼

Yes, you can edit existing images with AI by providing an input file and specific modification instructions. The Skill leverages the Google Gemini API alongside Python libraries like Pillow to apply the described changes to your photograph or visual.

Do I need a GEMINI_API_KEY to create AI art locally?▼

Yes, you must configure a valid GEMINI_API_KEY in your environment using python-dotenv to create AI art. This key is strictly required to authenticate your requests to the Google Gemini API for both image generation and editing tasks.

What is the best way to control aspect ratio and resolution for AI image generation?▼

The best way to control aspect ratio and resolution for AI image generation is by specifying these parameters within your prompt instructions. The Skill supports various configurations, allowing you to tailor outputs for specific formats like square logos.

Does this AI image generation tool support batch processing for multiple assets?▼

The AI image generation tool processes input files individually based on specified prompts. The metadata indicates it handles new image creation and modifications via specified input files, without mentioning batch processing capabilities for multiple assets.