New to Claude Skills? Learn how to install them →

github on GitHub

Nano Banana Pro OpenRouter

OfficialFree

Generate and edit images with OpenRouter's Gemini 3 Pro.

by github37.7k stars on github/awesome-copilot
4 views
Updated Aug 10, 2026
Get this skill

Free · Opens the source repo

What Nano Banana Pro OpenRouter does

Nano Banana Pro OpenRouter is a Python-based skill designed for generating and editing images using the Gemini 3 Pro Image model from OpenRouter. This tool allows users to create images purely from text prompts, edit existing images by specifying changes, and compose multiple images into a single output. It supports high-resolution outputs of 1K, 2K, or 4K, making it suitable for various visual projects.

The skill operates through a command-line interface, utilizing a simple script to handle image generation tasks. Users can generate an image by providing a descriptive prompt, such as 'A cinematic sunset over snow-capped mountains,' and the output is saved as a specified filename. For editing, users can input an existing image and a prompt that describes the desired modification, like changing the sky in a photo. The ability to compose multiple images into one allows for creative combinations, such as merging different portraits into a single studio shot.

Customization is also a key feature, as users can adjust the system prompt via a provided template file, enabling tailored image generation behavior without needing to delve into the code. This makes the skill accessible for both developers and designers looking for flexibility in their image creation processes. The integration with OpenRouter means that users need to manage API keys, ensuring secure access to the image generation capabilities.

Overall, Nano Banana Pro OpenRouter is an effective tool for anyone in need of advanced image generation and editing capabilities, whether for personal projects, professional design work, or creative experimentation. Its straightforward command structure and high-resolution output options make it a valuable addition to any developer or designer's toolkit.

When to use it

Use this skill when you need to create or modify images quickly and efficiently, especially when working with high-resolution outputs.

When not to use it

This skill may not be suitable for users looking for a GUI-based image editing solution or those who require extensive image manipulation features beyond basic edits and compositions.

What you can build with it

Creating Custom Artwork

Generate unique artwork based on text prompts for personal or professional projects.

Editing Existing Images

Modify specific elements in existing images, such as changing backgrounds or adding effects.

Combining Multiple Images

Compose multiple images into a single cohesive piece, useful for creating collages or composite portraits.

How to install Nano Banana Pro OpenRouter

View source

1. Install with the skills CLI

npx skills add github/awesome-copilot/nano-banana-pro-openrouter --agent claude-code

2. Or install it manually

Download the skill folder and drop it into ~/.claude/skills/ for all projects, or .claude/skills/ to scope it to one repo. Restart Claude Code so it picks up the new skill.

Anthropic's agentic coding CLI, and the reference implementation of Agent Skills. Drop a skill folder into ~/.claude/skills and Claude Code loads it automatically whenever a task matches the skill's description. Claude Code docs

Inside SKILL.md

Written by github

Nano Banana Pro OpenRouter

Overview

Generate or edit images with OpenRouter using the google/gemini-3-pro-image-preview model. Support prompt-only generation, single-image edits, and multi-image composition.

Prompt-only generation

uv run {baseDir}/scripts/generate_image.py \
  --prompt "A cinematic sunset over snow-capped mountains" \
  --filename sunset.png

Edit a single image

uv run {baseDir}/scripts/generate_image.py \
  --prompt "Replace the sky with a dramatic aurora" \
  --input-image input.jpg \
  --filename aurora.png

Compose multiple images

uv run {baseDir}/scripts/generate_image.py \
  --prompt "Combine the subjects into a single studio portrait" \
  --input-image face1.jpg \
  --input-image face2.jpg \
  --filename composite.png

Resolution

  • Use --resolution with 1K, 2K, or 4K.
  • Default is 1K if not specified.

System prompt customization

The skill reads an optional system prompt from assets/SYSTEM_TEMPLATE. This allows you to customize the image generation behavior without modifying code.

Behavior and constraints

  • Accept up to 3 input images via repeated --input-image.
  • --filename accepts relative paths (saves to current directory) or absolute paths.
  • If multiple images are returned, append -1, -2, etc. to the filename.
  • Print MEDIA: <path> for each saved image. Do not read images back into the response.

Troubleshooting

If the script exits non-zero, check stderr against these common blockers:

SymptomResolution
OPENROUTER_API_KEY is not setAsk the user to set it. PowerShell: $env:OPENROUTER_API_KEY = "sk-or-..." / bash: export OPENROUTER_API_KEY="sk-or-..."
uv: command not found or not recognizedmacOS/Linux: <code>curl -LsSf https://astral.sh/uv/install.sh | sh</code>. Windows: <code>powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"</code>. Then restart the terminal.
AuthenticationError / HTTP 401Key is invalid or has no credits. Verify at https://openrouter.ai/settings/keys.

For transient errors (HTTP 429, network timeouts), retry once after 30 seconds. Do not retry the same error more than twice — surface the issue to the user instead.

Frequently asked questions about Nano Banana Pro OpenRouter

Similar skills