skills.rest
adamhjouj
adamhjoujCOMMUNITY
Explore all skills by this author →
Website𝕏@adamk_issaGitHub

nano-banana-pro

Generate or edit images via Google's Gemini 3 Pro Image API and save PNG outputs.

4|1|Updated Mar 6, 2026
Search Tags:#image#gemini#generate#prompt#pro#edits#ai-art
One-click install
npx skills add https://github.com/adamhjouj/shieldclaw --skill nano-banana-pro-adamhjouj
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro
Source: https://github.com/adamhjouj/shieldclaw/tree/main/openclaw/skills/nano-banana-pro
Command: npx skills add https://github.com/adamhjouj/shieldclaw --skill nano-banana-pro-adamhjouj

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 quickly and reliably using Google's Gemini 3 Pro Image API, cutting manual design time and iteration cycles.

Core Features & Use Cases

  • Generate new images from prompts with optional input images for editing
  • Control output with adjustable resolution and aspect ratio
  • Compose multi-image scenes and save results in PNG for design workflows
  • Use Case: Create a portrait and then refine colors by providing an input image and a second prompt

Quick Start

Provide a prompt and optional input images to generate or edit an image with Gemini 3 Pro 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 or edit images using Gemini 3 Pro?▼

Generate or edit images using Gemini 3 Pro by providing a text prompt and up to 14 input images. The skill processes your request via the Google Gemini API and saves the customized output directly as a PNG file.

How many images can I include for batch edits with Gemini?▼

You can include up to 14 input images for batch edits. The skill composes multi-image scenes and applies prompt-driven customizations to generate a single refined PNG output.

Do I need an API key to generate images with this tool?▼

Yes, you need a Gemini API key to generate or edit images. The skill requires this key to authenticate your requests with the Google Gemini 3 Pro Image API.

Can I control output resolution and aspect ratio when generating images?▼

Yes, you can control the output resolution and aspect ratio. The skill supports configurable output size and prompt-driven customization to fit your specific design workflow requirements.

What file format are the generated images saved as?▼

Generated images are saved as PNG files. This format ensures easy integration into your design pipelines and supports high-quality output for rapid prototyping.

What is the best way to refine colors on an existing portrait?▼

Refine colors on a portrait by providing the original input image alongside a second prompt. The skill uses Gemini 3 Pro to apply the requested edits and saves the adjusted image as a PNG.

Related Skills

Explore More Design & Creative Skills→
resultanyildiziresultanyildizi
4

nano-banana-pro

Generate and edit images via Google's Gemini 3 Pro Image API.

Community
Intermediate
Estrella-231Estrella-231

generate-image

Generate and edit images from text prompts via OpenRouter, saving PNG outputs.

Community
Intermediate
feed-mobfeed-mob
1

gemini-image-generator

Convert prompts and images into Gemini image generation API calls.

Official
Intermediate
yxc023yxc023

gemini-imagegen

Generate and edit images using the Gemini API from text prompts and references.

Community
Advanced