nano-banana-image

Name: nano-banana-image
Availability: InStock
Author: byren

Generate and edit images via Google Gemini models with a CLI workflow.

Updated Jan 24, 2026

Search Tags:#editing #api #image #cli #gemini #generate #prompt

Ready to run

npx skills add https://github.com/byrencheema/nano-banana-image --skill nano-banana-image

💬 Prompt for ChatGPT / Claude Chat▼

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

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @google/genai, and includes scripts (resource) components.

What problem does it solve?

Generate and edit visuals rapidly by interfacing with Google's Gemini image generation models, removing much of the manual design workload and enabling on-demand creative iterations.

Core Features & Use Cases

Text-to-image generation: create logos, backgrounds, and product visuals from natural language prompts.
Image editing from prompts: modify color, style, or composition of existing images based on descriptive instructions.
Model selection and output control: choose between flash (fast) and pro (high quality), specify aspect ratios, and save outputs to a defined path suitable for production workflows.

Quick Start

Run node scripts/nano_banana.js with a prompt to generate an image and save the result to outputs/output.png.

Frequently Asked Questions about nano-banana-image

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?▼

To generate images from text prompts using the Gemini API, run the provided CLI script with your natural language prompt. The script interfaces with Google's Gemini image generation models and saves the output to a designated folder.

Can I edit existing images with Gemini AI using a command line interface?▼

Yes, you can edit existing images with Gemini AI by providing descriptive instructions to the CLI script. It modifies the color, style, or composition of your input image based on your prompt and saves the result.

Do I need a GEMINI_API_KEY to run the nano-banana-image script?▼

Yes, you need a GEMINI_API_KEY to run the script. The Skill requires this environment variable to authenticate requests with Google's Gemini image generation models and produce your requested visual outputs.

What is the difference between the flash and pro models for image generation?▼

The flash model offers fast image generation, while the pro model provides higher quality outputs. You can select between these two models in the script to balance speed and visual fidelity based on your workflow needs.

How do I control the aspect ratio of generated images with the Gemini CLI?▼

You can control the aspect ratio of generated images by specifying your desired dimensions when running the CLI script. This output customization ensures the final image fits your specific production requirements.

What are the limitations of using Gemini models for text-to-image generation via CLI?▼

The Skill limits you to Gemini's supported aspect ratios and model capabilities for text-to-image generation. Outputs are saved as PNG files, meaning the CLI workflow is tailored for static visual content creation rather than animated formats.