skills.rest
ReScienceLab
ReScienceLabOFFICIAL
Explore all skills by this author →
WebsiteGitHub

nanobanana

Generate and edit images with Google Gemini 3 Pro Image via prompts.

1.3k|126|Updated Jan 17, 2026
Search Tags:#editing#image#gemini#generate#nanobanana#prompt
One-click install
npx skills add https://github.com/ReScienceLab/opc-skills --skill nanobanana-resciencelab
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nanobanana
Source: https://github.com/ReScienceLab/opc-skills/tree/main/skills/nanobanana
Command: npx skills add https://github.com/ReScienceLab/opc-skills --skill nanobanana-resciencelab

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Generate and edit AI-generated visuals using Google Gemini 3 Pro Image, enabling quick creation of professional images from natural language prompts and simple edits without manual design work.

Core Features & Use Cases

  • Text-to-image generation with Gemini 3 Pro Image model
  • Image editing through natural language prompts
  • Control over aspect ratios (1:1, 16:9, 21:9) and resolutions (2K, 4K)
  • Use cases include marketing visuals, product mockups, social media assets, and iterative concept exploration.

Quick Start

Run the Nano Banana script with a text prompt to generate an image, for example 'a futuristic city at night'.

Frequently Asked Questions about nanobanana

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

FAQPage Schema
How do I generate images with Gemini using a text prompt?▼

You can generate images with Gemini by providing a natural language text prompt to the script, which uses the Gemini 3 Pro Image model to create the requested visual content.

Can I edit an existing image using a text prompt?▼

Yes, image editing is supported by providing an optional input image alongside a natural language prompt, allowing the Gemini model to modify the existing visual based on your instructions.

What resolutions and aspect ratios can I control when generating images?▼

Image generation supports adjustable aspect ratios including 1:1, 16:9, and 21:9, alongside high-resolution output options up to 2K and 4K for professional marketing assets and mockups.

Do I need an API key to use the Gemini image generation script?▼

Yes, you must configure a GEMINI_API_KEY and install the google-genai package within your environment to authenticate and execute the image generation and editing scripts.

What is the best way to create high-resolution marketing visuals without manual design work?▼

Using Gemini 3 Pro Image for text-to-image generation enables rapid creation of professional marketing visuals and product mockups from natural language prompts without requiring manual graphic design.

Are there limitations when using Gemini 3 Pro Image for iterative concept exploration?▼

Iterative concept exploration is limited by the Gemini API's processing capabilities and your GEMINI_API_KEY access, requiring the google-genai package for each adjustment to aspect ratios or image edits.

Related Skills

Explore More Design & Creative Skills→
aryaxtaryaxt

generate-image

Generate single or batch images using Google Gemini's image generation API.

Community
Intermediate
jason9693jason9693

nano-banana-pro

Generate or edit images with Gemini 3 Pro Image using prompts and input images.

Community
Intermediate
SkobynSkobyn

nano-banana-prompting

Transform natural language image requests into structured JSON prompts for Gemini 3 Pro Image.

Community
Intermediate
ag47-ptag47-pt
1

google-labs-product-photoshoot

Generate product photography assets from text prompts using AI image generation models.

Community
Intermediate