nano-banana-pro-openrouter
github/awesome-copilot
Generate and edit images via OpenRouter using Gemini 3 Pro Image model with 1K/2K/4K output.
What is nano-banana-pro-openrouter?
This skill generates images from text prompts, edits existing images, and composites multiple images together using OpenRouter's Gemini 3 Pro Image model. Use it when you need AI-powered image creation or manipulation with flexible resolution options.
- Generate images from text prompts only
- Edit single images with descriptive instructions
- Compose multiple images (up to 3) into a single output
- Support 1K, 2K, and 4K resolution outputs
- Customize behavior via optional system prompt template
- Save outputs with automatic multi-image naming
How to install nano-banana-pro-openrouter
npx skills add https://github.com/github/awesome-copilot --skill nano-banana-pro-openrouter- OPENROUTER_API_KEY environment variable set with valid OpenRouter credentials
- uv package manager installed (curl/PowerShell install scripts provided)
- Input images in common formats (JPG, PNG) if doing edits or compositing
How to use nano-banana-pro-openrouter
- 1.Set your OPENROUTER_API_KEY environment variable with a valid OpenRouter API key
- 2.Install uv if not already present using the provided install scripts
- 3.For text-only generation: run `uv run {baseDir}/scripts/generate_image.py --prompt "your description" --filename output.png`
- 4.For image edits: add `--input-image input.jpg` and describe the edit in the prompt
- 5.For compositing: add multiple `--input-image` flags (up to 3) and describe the composition in the prompt
- 6.Optionally specify `--resolution 2K` or `--resolution 4K` (default is 1K)
- 7.Check the output path printed as `MEDIA: <path>` to locate saved images
Use cases
- Create concept art or visual mockups from descriptions
- Modify existing images (e.g., change sky, adjust composition)
- Combine multiple reference images into a composite portrait or scene
- Generate marketing or presentation graphics at specific resolutions
- Iterate on image edits with custom system prompts
- Designers and visual creators
- Product managers prototyping UI/UX concepts
- Content creators needing quick image generation
- Developers building image-heavy applications
- Teams collaborating on visual assets
nano-banana-pro-openrouter FAQ
Up to 3 input images via repeated `--input-image` flags for compositing or multi-image edits.
1K (default), 2K, and 4K. Specify with `--resolution` flag.
Create an optional system prompt file at `assets/SYSTEM_TEMPLATE` to customize the model's behavior without changing code.
Verify your OPENROUTER_API_KEY is valid and has credits at https://openrouter.ai/settings/keys.
If the model returns multiple images, they are appended with `-1`, `-2`, etc. to the base filename.
Full instructions (SKILL.md)
Source of truth, from github/awesome-copilot.
name: nano-banana-pro-openrouter description: '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.' metadata: emoji: 🍌 requires: bins: - uv env: - OPENROUTER_API_KEY primaryEnv: OPENROUTER_API_KEY
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
--resolutionwith1K,2K, or4K. - Default is
1Kif 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. --filenameaccepts 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.
Related skills
More from github/awesome-copilot and the wider catalog.
git-commit
Execute semantic git commits with conventional message analysis and intelligent staging.
excalidraw-diagram-generator
Generate Excalidraw diagrams from natural language descriptions.
documentation-writer
Create structured technical documentation using the Diátaxis framework for tutorials, how-to guides, references, and explanations.
gh-cli
GitHub CLI comprehensive reference for repositories, issues, PRs, Actions, projects, releases, and all GitHub operations from the command line.
prd
Generate comprehensive Product Requirements Documents with executive summaries, user stories, technical specs, and risk analysis.
refactor
Surgical code refactoring to improve maintainability without changing behavior.