nano-banana-pro

Generate and edit images via Gemini 3 Pro Image with a Python script.

636|136|Updated Feb 18, 2026

Search Tags:#image #composition #gemini #generate #image-editing #multi-image #api-key

Ready to run

npx skills add https://github.com/swarmclawai/swarmclaw --skill nano-banana-pro-swarmclawai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/swarmclawai/swarmclaw/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/swarmclawai/swarmclaw --skill nano-banana-pro-swarmclawai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai>=1.0.0, pillow>=10.0.0, and includes scripts (resource) components.

What problem does it solve?

Automates the creation and editing of images by interfacing with Gemini 3 Pro Image, reducing manual design time and enabling rapid visual content generation.

Core Features & Use Cases

Generate new images from natural language prompts with adjustable resolution (1K, 2K, or 4K) and optional aspect ratios.
Edit existing images by supplying input images and a prompt to modify content, style, or composition.
Compose multiple images into a single scene (up to 14 inputs) for complex visuals or marketing assets.
Use API key management to securely authenticate with Gemini and keep credentials separate from code.

Quick Start

Use the bundled script to generate or edit images by providing a prompt and optional input images.

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 with Gemini using a Python script?▼

You generate images with Gemini by running the bundled Python script, providing a natural language prompt and selecting a resolution of 1K, 2K, or 4K with an optional aspect ratio.

Can I combine multiple images into one composition with Gemini Pro?▼

You can compose multiple images into a single scene with Gemini Pro by supplying up to 14 input images and a prompt to modify content, style, or composition for complex visuals.

Do I need an API key to edit existing images with Gemini?▼

You need a Gemini API key to edit existing images, and the script enforces API key handling to securely authenticate and keep your credentials separate from the codebase.

What is the maximum number of input images supported for multi-image composition?▼

The maximum number of input images supported for multi-image composition is 14, allowing you to merge multiple inputs into a single generated scene or marketing asset.

Does the image generation script require specific Python packages?▼

The image generation script requires the google-genai package version 1.0.0 or higher and the pillow package version 10.0.0 or higher to handle API interfacing and image processing.