skills.rest
RobbyMo81
RobbyMo81COMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro

Generate or edit images with Gemini 3 Pro Image via a uv-based script.

Updated Feb 16, 2026
Search Tags:#images#edit#generate#gemini-3-pro#ai-art#image-composition#png-output
One-click install
npx skills add https://github.com/RobbyMo81/assistantrobby --skill nano-banana-pro-robbymo81
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/RobbyMo81/assistantrobby/tree/main/skills/nano-banana-pro
Command: npx skills add https://github.com/RobbyMo81/assistantrobby --skill nano-banana-pro-robbymo81

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 through the Nano Banana Pro script.

Core Features & Use Cases

  • Generate images from prompts using the bundled uv-based workflow.
  • Edit existing images by providing input images (up to 14) for refinement.
  • Create multi-image compositions (up to 14 inputs) and export PNG outputs.
  • Auto-resolve output resolution from image dimensions or explicit --resolution.

Quick Start

Run the bundled script with a prompt and output filename to generate or edit an image.

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 Gemini 3 Pro?▼

You can generate images by running the bundled generate_image.py script with a text prompt and an output filename. The workflow produces a new PNG file at your chosen 1K, 2K, or 4K resolution.

Can I edit multiple existing images together for a composition?▼

Yes, you can edit and compose up to 14 input images together using this workflow. By providing multiple input files, you can refine existing pictures or create multi-image compositions exported as a single PNG output.

Do I need an API key to use the Gemini 3 Pro image generation script?▼

Yes, you need a GEMINI_API_KEY configured in your environment to use the Gemini 3 Pro image generation script. Alternatively, you can pass your key directly during execution using the --api-key override flag.

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

The maximum number of input images supported for multi-image editing and composition is 14. You can supply these inputs to refine existing images or combine them into a single creative PNG output.

How do I control the output resolution of the generated PNG files?▼

You can control the output resolution of generated PNG files by explicitly passing the --resolution flag. If left unspecified, the workflow auto-resolves the resolution from the input image dimensions.

What Python dependencies are required to run the image generation workflow?▼

The image generation workflow requires the google-genai library (version 1.0.0 or higher) and Pillow (version 10.0.0 or higher). These dependencies power the Gemini 3 Pro API calls and PNG image processing.

Related Skills

Explore More Design & Creative Skills→
abhiunixabhiunix
1

nano-banana-pro

Generate or edit images with Gemini 3 Pro Image via a local script.

Community
Intermediate
ItsJupiter000ItsJupiter000

photo-editor

Process and enhance images with Python libraries like Pillow and OpenCV.

Community
Intermediate
qsimeonqsimeon
1

nano-banana-pro

Generates and edits images using the Gemini 3 Pro Image API.

Community
Intermediate
SeanHoggSeanHogg
3

nano-banana-pro

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

Community
Intermediate