skills.rest
me2Doc
me2DocCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate and manipulate images via the Gemini 3 Pro Image API.

6|Updated Mar 13, 2026
Search Tags:#editing#image#ai#visuals#generation#gemini
One-click install
npx skills add https://github.com/me2Doc/friendlyclaw --skill nano-banana-pro-me2doc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/me2Doc/friendlyclaw/tree/main/body/skills/nano-banana-pro
Command: npx skills add https://github.com/me2Doc/friendlyclaw --skill nano-banana-pro-me2doc

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill removes the friction of manual image creation and editing by providing a direct interface to Google's advanced image generation models, allowing for rapid visual asset production.

Core Features & Use Cases

  • Text-to-Image Generation: Create high-quality visuals from natural language prompts with selectable resolutions.
  • Image Editing & Composition: Modify existing images or combine up to 14 separate images into a single scene.
  • Use Case: Quickly generate custom UI mockups or combine multiple reference sketches into a single cohesive concept art piece for project documentation.

Quick Start

Use the nano-banana-pro skill to generate a high-resolution image of a futuristic workspace with the filename workspace-concept.png.

Frequently Asked Questions about nano-banana-pro

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

FAQPage Schema
How do I generate images from text prompts using Gemini 3 Pro?▼

To generate images from text prompts using Gemini 3 Pro, you provide a natural language description and specify a desired resolution. The skill uses the google-genai API to create high-quality visuals and saves the output as an image file like png.

Can I combine multiple reference images into a single composition?▼

Yes, you can combine multiple reference images into a single composition. The skill supports multi-image composition, allowing you to merge up to 14 separate images into one cohesive scene using the Gemini 3 Pro Image API.

Do I need to install specific libraries to use the Gemini image generation API?▼

Yes, you need to install specific libraries to use the Gemini image generation API. The skill requires the google-genai and pillow dependencies to handle API communication and image processing tasks for your creative workflows.

What is the best way to edit existing images with AI for UI mockups?▼

The best way to edit existing images with AI for UI mockups is using the Gemini 3 Pro Image API. This skill provides a direct interface to modify existing visuals or generate custom mockups rapidly from natural language prompts.

Are there limitations on resolution scaling when generating AI visuals?▼

The skill supports selectable resolutions for generating AI visuals, allowing you to scale outputs for your specific needs. It removes manual friction by providing direct API access for high-resolution image generation.

Related Skills

Explore More Design & Creative Skills→
8b-is8b-is

gemini-imagegen

Generate and edit images via the Gemini API in Python.

Official
Advanced
neo4j-labsneo4j-labs
406

excalidraw

Generate Excalidraw JSON diagrams from textual descriptions.

Official
Basic
Umbral-BotUmbral-Bot

pillow-imaging

Automate image processing tasks with Pillow for batch resizing and watermarking.

Official
Intermediate
sixtycat2000-ctrlsixtycat2000-ctrl
3

seedream

Generate AI images via Volcengine Seedream with text-to-image and editing.

Community
Intermediate