nanobanana

Generate and edit images via text prompts using the nanobanana CLI.

48|8|Updated Oct 17, 2025
One-click install
npx skills add https://github.com/maragudk/skills --skill nanobanana
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nanobanana
Source: https://github.com/maragudk/skills/tree/main/nanobanana
Command: npx skills add https://github.com/maragudk/skills --skill nanobanana

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill simplifies the process of generating and editing images using generative AI, making it accessible through a straightforward command-line interface without needing deep knowledge of AI models or complex software.

Core Features & Use Cases

  • Image Generation: Create single or multiple images from text prompts using the nanobanana generate command.
  • Image Editing: Modify existing images by providing text-based instructions, enabling precise adjustments to visual content.
  • Prompt Optimization: Provides tips for crafting effective prompts to achieve desired visual outcomes, enhancing creative control.
  • Use Case: A marketing team needs several variations of a product icon. This skill allows them to generate multiple options with a single command and then refine a chosen image by instructing the AI to "make the background blue" or "add a subtle glow," saving design iteration time.

Quick Start

Generate a single image

nanobanana generate output.png "a beautiful sunset over mountains"

Frequently Asked Questions about nanobanana

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

FAQPage Schema
How do I generate AI images from text prompts using a CLI?

Generate AI images by running `nanobanana generate output.png "your prompt"` from the command line. The CLI accesses Google's generative AI models to create images from text descriptions, supporting PNG and JPG output formats with optional quality settings via the -pro flag.

Can I edit existing images with text instructions?

Yes, image editing modifies existing PNG or JPG files by applying text-based instructions. Use the `nanobanana` CLI to provide editing prompts—such as "make the background blue"—to adjust specific visual elements without regenerating the entire image.

What setup is required to use generative AI image tools via CLI?

Configure a Google API key by setting the GOOGLE_API_KEY environment variable or adding it to a .env file. This prerequisite enables CLI access to Google's generative AI image models for both generation and editing tasks.

How do I generate multiple image variations for design iteration?

The `nanobanana generate` command creates single or multiple images from a single text prompt, allowing rapid design iteration. Combine generation with the editing capability to refine chosen variations by adjusting visual properties through text instructions.

What's the difference between standard and pro image generation?

The -pro flag enables Google's higher-quality generative AI model for improved image output. Use the pro model when standard generation doesn't meet quality requirements, balancing results against any associated API costs.

Does CLI-based image generation work for logos and concept art?

Yes, image generation via CLI supports logos, concept art, and other visual assets. The generative AI models handle diverse creative use cases through text prompts, making it suitable for marketing teams and designers needing rapid visual prototyping.