nano-banana-pro

Generate and edit images with the Gemini 3 Pro Image model via Python.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/spoonbobo/trinity --skill nano-banana-pro-spoonbobo
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/spoonbobo/trinity/tree/main/app/skills/nano-banana-pro
Command: npx skills add https://github.com/spoonbobo/trinity --skill nano-banana-pro-spoonbobo

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the creation and modification of images using advanced AI, eliminating the need for complex design software or manual editing for many tasks.

Core Features & Use Cases

  • Image Generation: Create new images from detailed text prompts.
  • Image Editing: Modify existing images based on specific instructions.
  • Multi-Image Composition: Combine multiple images into a single scene.
  • Use Case: Generate a realistic image of a "cyberpunk cat wearing sunglasses" or edit a photo to "add a hat to the person in the image."

Quick Start

Use the nano-banana-pro skill to generate an image of a serene landscape with a waterfall.

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?

To generate images from text prompts using Gemini, you can use a Python script that calls the Gemini 3 Pro Image model. You provide a descriptive text prompt, and the script outputs the generated image without requiring manual design software.

How do I edit an existing image with AI instructions?

You can edit an existing image with AI instructions by passing the image and specific text guidelines to the Gemini 3 Pro model. The script processes your modifications and outputs the newly edited image file.

What environment variables do I need for Gemini image generation scripts?

For Gemini image generation scripts, you need the GEMINI_API_KEY environment variable configured. You also need the 'uv' package manager installed to execute the Python script and manage dependencies like google-genai and pillow.

Can I compose multiple images into a single scene with Gemini?

Yes, you can compose multiple images into a single scene with Gemini. The script supports multi-image composition by combining several input images into one unified output based on your instructions.

Does Gemini image editing work without complex design software?

Gemini image editing works without complex design software by automating modifications through a Python script. It leverages the Gemini 3 Pro model to process text prompts and image edits directly, bypassing traditional manual editing tools.