nano-banana-pro

Generate and edit images via the Gemini 3 Pro API.

55|6|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/NJX-njx/opensoul --skill nano-banana-pro-njx-njx
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/NJX-njx/opensoul/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/NJX-njx/opensoul --skill nano-banana-pro-njx-njx

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables users to generate and modify images quickly through API integration, bypassing complex graphic design tools and manual editing.

Core Features & Use Cases

  • Image Generation: Produce high-quality images from descriptive prompts for visual content creation.
  • Image Editing: Modify existing images based on user instructions, supporting creative workflows.
  • Use Case: Suppose you want a surreal landscape; provide a prompt, and this Skill generates the image automatically ready for use in marketing or art projects.

Quick Start

Use the nano-banana-pro Skill to generate an image of a futuristic cityscape with a detailed prompt.

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 AI images from text prompts for design projects?

To generate AI images from text prompts for design projects, this Skill processes descriptive prompts via the Gemini 3 Pro API to automatically produce high-quality visual assets.

Can I edit existing images using API commands instead of manual photo editing software?

Yes, you can edit existing images using API commands instead of manual photo editing software by sending modification instructions directly to the Gemini 3 Pro API integration.

Do I need a GEMINI_API_KEY to authenticate image generation requests?

Yes, you need a GEMINI_API_KEY to authenticate image generation requests, as this Skill requires this specific key to securely access the Gemini 3 Pro API for processing visuals.

What is the best way to create multi-image compositions for marketing campaigns?

The best way to create multi-image compositions for marketing campaigns is using this Skill, which supports multi-image compositions and prompt-based creation to generate combined visual assets.

Does this image generation Skill work with Python dependencies like Pillow?

This image generation Skill works with Python dependencies like Pillow and google-genai, utilizing these libraries to handle image processing and API interactions for creative workflows.