nano-banana-pro-openrouter

Generate and edit images via the OpenRouter API using Google Gemini 3 Pro.

Updated Feb 16, 2026

Search Tags:#image generation #image editing #AI art #OpenRouter #Gemini Pro #compositing

Ready to run

npx skills add https://github.com/Thedougler/agent-template --skill nano-banana-pro-openrouter-thedougler

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: nano-banana-pro-openrouter
Source: https://github.com/Thedougler/agent-template/tree/main/.github/skills/nano-banana-pro-openrouter
Command: npx skills add https://github.com/Thedougler/agent-template --skill nano-banana-pro-openrouter-thedougler

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill enables the creation and modification of images using advanced AI models through the OpenRouter API, streamlining visual content generation.

Core Features & Use Cases

Prompt-only Image Generation: Create new images from descriptive text prompts.
Image Editing: Modify existing images by recoloring, restyling, or swapping elements based on prompts.
Multi-Image Compositing: Blend subjects from multiple input images into a single cohesive output.
Resolution Control: Supports 1K, 2K, and 4K output resolutions for various use cases.

Quick Start

Use the nano-banana-pro-openrouter skill to generate an image of a futuristic cityscape at sunset with a 2K 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 and edit images with Gemini 3 Pro using OpenRouter?▼

To generate and edit images with Gemini 3 Pro, this Skill sends your text prompts and input images to the OpenRouter API, supporting prompt-only generation, single-image edits, and multi-image compositing at 1K, 2K, or 4K resolutions.

What do I need to set up before generating AI art via the OpenRouter API?▼

Before generating AI art via the OpenRouter API, you need to configure an OPENROUTER_API_KEY environment variable and install the `uv` utility for script execution, along with the openai Python dependency.

Can I combine multiple input images into a single AI art output?▼

Yes, you can combine multiple input images into a single AI art output using the multi-image compositing feature, which blends subjects from separate images into one cohesive generated result.

Does this AI image generation tool support high resolution outputs?▼

This AI image generation tool supports high resolution outputs up to 4K, offering adjustable 1K, 2K, and 4K resolution settings to match your specific visual content requirements.

What is the best way to restyle or swap elements in an existing image?▼

The best way to restyle or swap elements in an existing image is using the single-image edit function, which modifies your input image by applying descriptive text prompts to recolor, restyle, or swap specific elements.