Which image resolutions are supported?

The skill supports 1K, 2K, and 4K resolution outputs, allowing for both quick previews and production-ready assets.

What API key is required to use the Nanobanana skill?

You need a Google Gemini API key, which must be configured in your environment variables or in the ~/.nanobanana.env file.

Can I edit existing images with this skill?

Yes, you can provide input image files along with a text prompt to perform AI-powered edits, such as adding elements or changing the style.

What models can I choose from?

You can use gemini-3-pro-image-preview for the highest quality results or gemini-2.5-flash-image for faster generation speeds.

What aspect ratios are available?

It supports a wide variety of ratios including 1:1 (Square), 16:9 (Landscape), 9:16 (Portrait), and 21:9 (Ultra-wide).

Nanobanana Gemini Image Generator

Name: Nanobanana Gemini Image Generator
Author: feiskyer

byfeiskyer

•

1,158

Design Tools

Generates and edits high-quality images directly within Claude Code using the Google Gemini API.

About

The Nanobanana Image Generation Skill integrates Google's powerful Gemini vision models into the Claude Code environment, allowing developers to create and manipulate visual assets without leaving the terminal. It supports a wide range of functionality from text-to-image generation to complex image editing, offering granular control over aspect ratios, resolutions up to 4K, and model selection. Whether you need a quick placeholder, a high-fidelity logo, or an edited UI screenshot, this skill provides a streamlined workflow for AI-driven visual creation during the development process.

Key Features

High-resolution output options from 1K to 4K
1,158 GitHub stars
Support for 10+ aspect ratios including 16:9 and 21:9
Text-to-image generation using Google Gemini API
Flexible model switching between high-quality and fast-generation modes
Advanced image-to-image editing and modification

Use Cases

Creating custom UI assets and logos for web and mobile projects
Editing existing screenshots or images using natural language prompts
Generating high-resolution marketing visuals and social media content from the CLI

About

Key Features

High-resolution output options from 1K to 4K
1,158 GitHub stars
Support for 10+ aspect ratios including 16:9 and 21:9
Text-to-image generation using Google Gemini API
Flexible model switching between high-quality and fast-generation modes
Advanced image-to-image editing and modification

Use Cases

Creating custom UI assets and logos for web and mobile projects
Editing existing screenshots or images using natural language prompts
Generating high-resolution marketing visuals and social media content from the CLI