Nano Banana Pro Openrouter

From the author

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.

— the description by nblog

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

Nano Banana Pro OpenRouter provides an interface to generate, edit, and composite images using the google/gemini-3-pro-image-preview model through OpenRouter. It supports various resolutions and allows for system prompt customization via external templates.

What it does

Generates new images from text prompts.
Performs edits on single input images.
Composites multiple input images into a single output.
Supports 1K, 2K, and 4K resolution outputs.
Allows system prompt customization via a template file.
Handles multiple image outputs by appending indices to filenames.

When to use it

When you need to create new visual assets from text descriptions.
When you need to modify existing images using AI-driven edits.
When you need to combine multiple source images into a single composition.
When you require specific resolution outputs for your generated media.

Advantages

Flexible input handling for single or multiple source images.
Configurable resolution settings for output control.
Decoupled system prompt management via template files.
Standardized output reporting for integration with other tools.

Usage examples

“Generate an image of a futuristic city skyline at night.”: The agent executes the generation script and saves the resulting image file to the specified path.
“Edit this image to change the background to a forest.”: The agent processes the input image with the provided prompt and saves the modified version.
“Create a composite image using these two portraits.”: The agent merges the two provided source images into a single output file.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/github/nano-banana-pro-openrouter/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip nano-banana-pro-openrouter.zip -d .agents/skills

Documentation by nblog

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:

Symptom	Resolution
`OPENROUTER_API_KEY is not set`	Ask 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 recognized	macOS/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 401	Key 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.

Files

ATTRIBUTION.mdAdded by AutoGineer879 B
LICENSELicence file added by AutoGineer1.0 KiB
SKILL.md2.6 KiB
assets/SYSTEM_TEMPLATE1.2 KiB
scripts/generate_image.pyScript5.8 KiB

assets/SYSTEM_TEMPLATE

You are a visionary image‑creation artist with a poetic, dreamlike imagination.
Your role is to transform any user request—whether highly detailed or very minimal—into a vivid, concrete, and model‑ready image description.
When information is missing, infer the user's intent in a gentle and intuitive way (such as creating a character portrait, sticker design, sci‑fi avatar, creature concept, etc.).
If the user does not specify an art style, you may offer subtle optional suggestions (for example, "soft illustration," "minimal line style," or "playful entertainment‑meme style") without imposing them.

Your responsibilities:
- Ensure any text appearing in the image matches the user's language (unless explicitly specified otherwise)
- Create visually compelling and technically excellent images
- Pay attention to composition, lighting, color, and visual balance
- Follow the user's specific style preferences and requirements
- For image edits, preserve the original context while making requested modifications
- For multi-image composition, seamlessly blend subjects into cohesive results

Remember: Output only the generated image without additional commentary.

Requirements and compatibility

Written for: GitHub Copilot

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs network access, Needs an API key, Needs Python

Security

What our scanner noticed· Low risk

Instructions that use the network
Scripts that your agent may run

This skill includes scripts that your agent may run. Read them before you use it.

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Canvas Design
AnthropicOfficial
A design-focused tool for generating original visual art and aesthetic philosophies.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0GitHub stars of the source repository188.6k
Algorithmic Art
AnthropicOfficial
Generate interactive, seeded algorithmic art using p5.js within a standardized, branded interface.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Low riskHas scriptsGitHub stars of the source repository188.6k
Slack Gif Creator
AnthropicOfficial
A toolkit for programmatically creating and optimizing animated GIFs specifically for Slack.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Low riskHas scriptsGitHub stars of the source repository188.6k
Image
Corey Haines· Community
A guide for generating, editing, and optimizing marketing images using AI models and design tools.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskGitHub stars of the source repository59k
Infographics
K-Dense· Community
Generate professional, data-driven infographics using AI-powered creation, quality review, and optional automated research.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k
Generate Image
K-Dense· Community
Generate and edit images using various AI models via the OpenRouter API.
Design and creativeClaude CodeClaude appsOpenAI Codex+14 more
MITLow riskHas scriptsGitHub stars of the source repository56.4k

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download nano-banana-pro-openrouter.zip