skills.rest
MudassarAbrar
MudassarAbrarCOMMUNITY
Explore all skills by this author →
GitHub

nano-banana-pro-openrouter

Generate or edit images with OpenRouter Gemini 3 Pro at 1K/2K/4K resolutions.

Updated Feb 13, 2026
Search Tags:#openrouter#image-generation#gemini-3-pro#prompt-engineering#image-editing#multi-image#ai-art
One-click install
npx skills add https://github.com/MudassarAbrar/HACKATHON-1.0 --skill nano-banana-pro-openrouter
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: nano-banana-pro-openrouter
Source: https://github.com/MudassarAbrar/HACKATHON-1.0/tree/main/.agent/workflows/nano-banana-pro-openrouter
Command: npx skills add https://github.com/MudassarAbrar/HACKATHON-1.0 --skill nano-banana-pro-openrouter

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires openai, and includes scripts (resource) and assets (resource) components.

What problem does it solve?

Generate or edit images efficiently using the OpenRouter Gemini 3 Pro model, enabling prompt-driven creation, precise edits, and multi-image compositions without manual drawing or manipulation.

Core Features & Use Cases

  • Prompt-only image generation, single-image edits, and multi-image composition with 1K/2K/4K outputs
  • System prompt customization via assets/SYSTEM_TEMPLATE for consistent artistic direction
  • Flexible input handling: up to three input images and deterministic output naming

Quick Start

Run the generate_image.py script with a prompt and up to three input images to produce one or more output images at a selected resolution.

Frequently Asked Questions about nano-banana-pro-openrouter

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images with Gemini 3 Pro using a text prompt?▼

To generate images with Gemini 3 Pro, you run the provided script with a text prompt to create 1K, 2K, or 4K outputs. It uses the OpenRouter API to support prompt-driven creation without manual drawing.

Can I combine multiple images for AI composition using OpenRouter?▼

Yes, you can perform multi-image composition by supplying up to three input images to the script. This allows you to merge and edit multiple visuals into a single composite image output.

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

Yes, you need an OPENROUTER_API_KEY to access the Gemini 3 Pro model for image editing. This key authenticates your requests through the OpenRouter platform to generate or refine images.

How do I apply consistent artistic direction to AI-generated images?▼

You apply consistent artistic direction by loading a system template from the assets folder. This system prompt steers the Gemini 3 Pro model to maintain a specific style across multiple image generations.

What are the limitations of multi-image composition with Gemini 3 Pro?▼

The main limitation for multi-image composition is that it supports a maximum of three input images. You also must configure your OpenRouter API key correctly to process edits and generate outputs successfully.

Related Skills

Explore More Design & Creative Skills→
ajilantonyajilantony

nano-banana-pro-openrouter

Generate and edit images via OpenRouter with Gemini 3 Pro Image.

Community
Intermediate
tiancaiamaotiancaiamao
5

nano-banana-pro

Generate and edit images with Gemini 3 Pro Image, exporting PNGs.

Community
Intermediate
peteanderson80peteanderson80

imagegen

Generate and edit images via the OpenAI Image API CLI.

Community
Advanced
flight505flight505
3

image

Generate and edit images via OpenRouter AI models from Python.

Community
Basic