banana-maker

Generate images via the Gemini API with Nano Banana Pro prompting.

4|1|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/m2ai-portfolio/m2ai-skills-pack --skill banana-maker
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: banana-maker
Source: https://github.com/m2ai-portfolio/m2ai-skills-pack/tree/main/skills/banana-maker
Command: npx skills add https://github.com/m2ai-portfolio/m2ai-skills-pack --skill banana-maker

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, python-dotenv.

What problem does it solve?

Generate images using the Gemini image generation API with the Nano Banana Pro prompting methodology. Use when the user asks to generate, create, or make an image, picture, photo, illustration, or visual.

Core Features & Use Cases

  • Automates high-quality image generation by offering model choices (flash, pro, grounded) and prompting flow.
  • Applies prompting best practices from the Nano Banana Pro guide to craft detailed, production-ready prompts.
  • Use cases include thumbnails, posters, concept visuals, product visuals, or any visual content creation.

Quick Start

Provide a descriptive prompt and select a model (flash, pro, or grounded) to generate an image immediately.

Frequently Asked Questions about banana-maker

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

FAQPage Schema
How do I generate high-quality images using the Gemini API?

To generate high-quality images using the Gemini API, you provide a descriptive prompt and select a model like flash, pro, or grounded to produce production-ready visual content. The system applies Nano Banana Pro prompting methodology to craft detailed prompts for illustrations and thumbnails.

What is Nano Banana Pro prompting for AI image generation?

Nano Banana Pro prompting is a methodology for crafting detailed, production-ready prompts for AI image generation. It automates high-quality visual content creation by applying prompting best practices within the Gemini image generation API workflow.

Do I need a Google GenAI API key to generate visual content?

Yes, you need a Gemini or Google GenAI API key to generate visual content. The image generation process requires this key to authenticate requests and return the generated image file along with optional notes.

Can I use reference images when generating illustrations with Gemini?

Yes, you can use reference images when generating illustrations with Gemini. The image generation process supports reference images and model options to help guide the visual content creation workflow for posters and concept visuals.

What are the limitations of using the Gemini API for visual design workflows?

Limitations of using the Gemini API for visual design workflows include dependency on external API keys and model availability. Users must choose between flash, pro, or grounded models to balance generation speed and output quality for their specific design needs.