Home/AI Agent External Interaction/nano-banana-pro-openrouter
N

nano-banana-pro-openrouter

by @githubv
4.5(309)

Generates or edits images using the Gemini 3 Pro image model via OpenRouter, supporting pure prompt generation, image editing, and multi-image composition.

nano-banana-proopenrouterai-model-apigenerative-aillm-integrationGitHub
Installation
npx skills add github/awesome-copilot --skill nano-banana-pro-openrouter
compare_arrows

Before / After Comparison

1
Before

Traditional image processing tools are complex to operate, making image generation or editing time-consuming and laborious, and hindering the realization of creative ideas. Multi-image synthesis is difficult, limiting visual content creation.

After

With the OpenRouter image model, images can be quickly generated, edited, or synthesized through prompts. This significantly enhances image creation efficiency and the ability to realize creative ideas.

SKILL.md

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: curl -LsSf https://astral.sh/uv/install.sh | sh. Windows: powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex". 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.

User Reviews (0)

Write a Review

Effect
Usability
Docs
Compatibility

No reviews yet

Statistics

Installs9.5K
Rating4.5 / 5.0
Version
Updated2026年5月19日
Comparisons1

User Rating

4.5(309)
5
23%
4
51%
3
23%
2
2%
1
0%

Rate this Skill

0.0

Compatible Platforms

🔧Claude Code
🔧OpenClaw
🔧OpenCode
🔧Codex
🔧Gemini CLI
🔧GitHub Copilot
🔧Amp
🔧Kimi CLI

Timeline

Created2026年3月16日
Last Updated2026年5月19日