nano-banana-pro

Generate or edit images with Gemini 3 Pro Image using prompts and input images.

Updated Mar 19, 2026
One-click install
npx skills add https://github.com/jason9693/Open-Jordy --skill nano-banana-pro-jason9693
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/jason9693/Open-Jordy/tree/main/openjordy/skills/nano-banana-pro
Command: npx skills add https://github.com/jason9693/Open-Jordy --skill nano-banana-pro-jason9693

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?

Generate or edit images using Gemini 3 Pro Image to streamline visual creation.

Core Features & Use Cases

  • Generate images from prompts using Gemini 3 Pro Image.
  • Edit existing images with prompts and optional input images (up to 14).
  • Create multi-image compositions for marketing, design, or social media.

Quick Start

Generate an image by providing a descriptive prompt to the Nano Banana Pro script.

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 3 Pro from a text prompt?

To generate images with Gemini 3 Pro, you provide a descriptive text prompt to the script, which then processes your input to create a visual output. You can control the output resolution by selecting 1K, 2K, or 4K settings.

Can I edit existing images and combine multiple inputs using Gemini 3 Pro?

Yes, you can edit existing images by providing prompts alongside optional input images. The tool supports up to 14 input images, allowing you to perform multi-image editing and simple compositions for marketing or social media tasks.

Do I need an API key to use Gemini 3 Pro for image generation?

Yes, you need to configure the GEMINI_API_KEY environment variable to authenticate your requests. This API key management step is required before the script can successfully generate or edit images using the Gemini 3 Pro Image model.

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

The maximum number of input images supported for multi-image composition tasks is 14. You can upload these existing images alongside a text prompt to generate edited visuals suitable for design and marketing workflows.

What resolution options are available when generating images with Gemini 3 Pro?

When generating images with Gemini 3 Pro, you can select resolution settings of 1K, 2K, or 4K. This allows you to control the output quality of your generated or edited images based on your specific design requirements.