nano-banana-pro

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

Updated Feb 18, 2026

Search Tags:#image generation #image editing #image composition #artistic expression #Gemini 3 Pro Image

Ready to run

npx skills add https://github.com/ClaudioCeppi83/kora-os-kernel --skill nano-banana-pro-claudioceppi83

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/ClaudioCeppi83/kora-os-kernel/tree/main/engines/openclaw/skills/nano-banana-pro
Command: npx skills add https://github.com/ClaudioCeppi83/kora-os-kernel --skill nano-banana-pro-claudioceppi83

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill solves the problem of generating or editing images through the Gemini 3 Pro Image (Nano Banana Pro) API, allowing users to create visually compelling content quickly.

Core Features & Use Cases

Image Generation: Generate new images based on descriptive prompts.
Image Editing: Edit existing images with additional prompts.
Multi-image Composition: Combine up to 14 images into a single scene.
API Integration: Uses the Gemini 3 Pro Image API for image processing.

Quick Start

Generate an image with the prompt 'a futuristic cityscape' and save it as 'futuristic_city.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 using the Gemini 3 Pro Image API?▼

To generate images using the Gemini 3 Pro Image API, you provide descriptive text prompts to create visually compelling content. The Skill processes these prompts to output new image files without requiring manual design work.

Can I combine multiple images into a single scene with Gemini 3 Pro?▼

Yes, you can combine multiple images into a single scene with Gemini 3 Pro. The Skill supports multi-image composition, allowing you to merge up to 14 distinct images into one cohesive visual output.

How do I edit existing images with a text prompt using Python?▼

You edit existing images with a text prompt using Python by passing the image and additional instructions to the API. The Skill uses Pillow and Google GenAI libraries to handle image processing and apply edits.

Do I need Python and Pillow to use the Gemini 3 Pro Image API?▼

Yes, you need Python and Pillow to use the Gemini 3 Pro Image API. The Skill requires these dependencies, along with the Google GenAI library, to interface with the API and manage image processing tasks.

What are the limitations of multi-image composition with the Gemini API?▼

The primary limitation of multi-image composition with the Gemini API is a maximum capacity of 14 images per scene. Users needing to merge larger batches of source images will need to break their projects into multiple separate processing jobs.

What is the best way to automate artistic expression and image editing in Python?▼

The best way to automate artistic expression and image editing in Python is by using API integration for creative content generation. This Skill interfaces with Gemini 3 Pro Image to apply descriptive prompts for automated, visually compelling results.