nano-banana-pro-openrouter

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

Updated Feb 1, 2026
One-click install
npx skills add https://github.com/alexandereiseghohi/comicr --skill nano-banana-pro-openrouter-alexandereiseghohi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: nano-banana-pro-openrouter
Source: https://github.com/alexandereiseghohi/comicr/tree/main/skills/nano-banana-pro-openrouter
Command: npx skills add https://github.com/alexandereiseghohi/comicr --skill nano-banana-pro-openrouter-alexandereiseghohi

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill empowers users to generate and edit images using advanced AI models, transforming text prompts into visual art or modifying existing images with creative descriptions.

Core Features & Use Cases

  • Prompt-only Image Generation: Create entirely new images from detailed text descriptions.
  • Image Editing: Modify existing images by replacing elements or altering the scene based on prompts.
  • Multi-Image Composition: Combine subjects from multiple input images into a single, cohesive output.
  • Resolution Control: Generate images in 1K, 2K, or 4K resolutions.
  • Use Case: Generate a "cyberpunk cityscape at night with neon lights" or edit a photo of a dog to "wear a tiny crown and a monocle."

Quick Start

Use the nano-banana-pro-openrouter skill to generate an image of a futuristic city skyline at sunset.

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 AI images from text prompts using Gemini 3 Pro?

To generate images from text prompts using the Gemini 3 Pro Image model, you need an OpenRouter API key and the 'uv' binary installed. The skill processes your text descriptions to create new visual art in 1K, 2K, or 4K resolutions.

Can I combine multiple images into a single composition with AI image editing?

Yes, multi-image composition allows you to combine subjects from multiple input images into a single cohesive output. You can merge elements from different pictures by providing them alongside your editing instructions to the model.

What do I need to set up before editing images via OpenRouter?

Before editing images via OpenRouter, you must configure your OPENROUTER_API_KEY and ensure the 'uv' binary is available for script execution. You can also customize the model's behavior by modifying the provided system prompt asset file.

Does multi-image composition support 4K resolution outputs?

Multi-image composition supports resolution control up to 4K. You can generate and edit your combined images in 1K, 2K, or 4K resolutions depending on your specific visual requirements.

Why does AI image generation require the uv binary to run?

AI image generation requires the uv binary because the skill executes internal scripts to process prompts and communicate with the OpenRouter API. This dependency ensures the Python environment runs correctly to handle the image generation workflow.

Are there limitations when replacing elements in a photo with AI art?

When replacing elements in a photo with AI art, limitations depend on the Gemini 3 Pro Image model's interpretation of your prompt. Complex edits are handled via single-image editing commands, but results vary based on prompt clarity and original image complexity.