Nano Banana — Image Generation

Generate and edit images via the Gemini API. If the API key is missing, run /nano-banana:setup.

Workflow

1. Determine the mode from the user's request:

   • Creating a new image from text? → Text-to-image (no --images)
   • Editing/retouching an existing image? → Image editing (--images source.png)
   • Applying one image's style to another? → Style transfer (--images style.png target.png)
   • Combining or referencing multiple images? → Multi-image (--images a.png b.png ..., up to 14)
   • Need 2K or 4K output? → Add --resolution 2K|4K to any mode above

2. Craft the prompt — describe the desired result narratively. See references/prompting-guide.md for domain-specific patterns (website visuals, placeholders, product shots, etc.).

3. Run the script:

python "$CLAUDE_PLUGIN_ROOT/scripts/genimage.py" --prompt "..." [options]