skills.rest
ruiming2ai
ruiming2aiCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana

Generate and edit images from text prompts using Google Gemini Nano Banana models.

Updated Mar 25, 2026
Search Tags:#image generation#image editing#AI art#text-to-image#Gemini models
One-click install
npx skills add https://github.com/ruiming2ai/GB-MEP-Drawing-Review --skill nano-banana-ruiming2ai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana
Source: https://github.com/ruiming2ai/GB-MEP-Drawing-Review/tree/main/Archive%20%28Not%20Used%29/2026-03-25%20CrossBeam/.claude/skills/nano-banana
Command: npx skills add https://github.com/ruiming2ai/GB-MEP-Drawing-Review --skill nano-banana-ruiming2ai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires python, generate_image.py, edit_image.py, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill streamlines the creation and editing of images, providing a user-friendly interface for generating images from text and modifying existing ones with powerful AI capabilities.

Core Features & Use Cases

  • Text-to-Image Generation: Transform text descriptions into high-quality images using Google Gemini's Nano Banana models.
  • Image Editing: Apply text-based edits to images for various creative and practical purposes.
  • Multi-Image Reference: Maintain consistency across images by using multiple references.
  • Use Case: Generate social media content, edit product photos, or create custom graphics.

Quick Start

Generate an image from the text "a futuristic cityscape at night" using the 'gemini-3-pro-image-preview' model.

Frequently Asked Questions about nano-banana

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

FAQPage Schema
How do I generate images from text using Gemini models?▼

Text-to-image generation with Gemini models transforms written descriptions into visual content. You provide a text prompt, such as a futuristic cityscape, and the model outputs a corresponding high-quality image.

Can I edit existing images with text prompts?▼

Yes, image editing with text prompts allows you to apply modifications to existing photos. You input an image and specify desired changes in text, and the AI applies those visual edits.

Do I need Python to run text-to-image generation tasks?▼

Yes, Python is required to execute the text-to-image generation and image editing scripts. The skill relies on specific Python files to interface with the Gemini models.

How do I maintain visual consistency across multiple generated images?▼

Maintaining visual consistency across multiple images is achieved by using multi-image reference features. Providing reference images ensures the AI generates new content matching the established style.

What is the best way to create custom graphics for social media marketing?▼

Creating custom graphics for social media marketing is best handled by AI art generation tools. Transforming text descriptions into high-quality images streamlines content creation for design projects.

Which Gemini model is used for AI art generation?▼

AI art generation utilizes the 'gemini-3-pro-image-preview' model. This specific Gemini model processes text descriptions to create diverse visual content.

Related Skills

Explore More Design & Creative Skills→
wixettewixette
10

nano-banana-pro

Generate and edit images using the Gemini 3 Pro Image model.

Community
Intermediate
adriangmrraaadriangmrraa

Business Forge Engineer

Convert AI-generated assets into exportable marketing visuals with Google Imagen 3.

Community
Intermediate
IgorVaryvodaIgorVaryvoda

sirv-ai-studio

Orchestrate Sirv AI Studio image and video tasks via MCP endpoints.

Community
Advanced
ckrono-progckrono-prog

ai-integrations-gemini

Access Gemini-compatible APIs for content and image generation via Replit AI Integrations proxy.

Community
Intermediate