From nano-banana
Generate, edit, or create any image — photos, illustrations, icons, thumbnails, hero images, banners, placeholder visuals, website graphics, social media assets, product shots, logos, diagrams, or any visual content. Use this skill whenever the task involves creating an image, populating a UI with visuals, generating placeholder or mockup images, editing or retouching a photo, applying style transfer, composing multiple images, or producing any graphic asset. Triggers on requests like "generate an image", "create a visual", "make a placeholder", "add a hero image", "design a thumbnail", "edit this photo", "create website graphics", "populate with images", or any task requiring image creation or manipulation.
npx claudepluginhub ibrahim-3d/nano-banana-claude-plugin --plugin nano-bananaThis skill uses the workspace's default tool permissions.
Generate and edit images via the Gemini API. If the API key is missing, run `/nano-banana:setup`.
Generates AI images from text prompts, edits images, and composes from multiple references using Gemini models. Supports t2i, i2i, product mockups, and stickers.
Generates images from text, edits images with references, performs product placement, style transfer, and multi-image composition using OpenAI DALL-E or Google Gemini.
Generates or edits images via Google Gemini from text prompts or up to 14 reference images for text-to-image and multi-image editing.
Share bugs, ideas, or general feedback.
Generate and edit images via the Gemini API. If the API key is missing, run /nano-banana:setup.
Determine the mode from the user's request:
--images)--images source.png)--images style.png target.png)--images a.png b.png ..., up to 14)--resolution 2K|4K to any mode aboveCraft the prompt — describe the desired result narratively. See references/prompting-guide.md for domain-specific patterns (website visuals, placeholders, product shots, etc.).
Run the script:
python "$CLAUDE_PLUGIN_ROOT/scripts/genimage.py" --prompt "..." [options]
| Flag | Required | Purpose |
|---|---|---|
--prompt "text" | Yes | Describe the desired image |
--output file.png | No | Output path (default: generated_image.png) |
--images path [...] | No | Input image(s) — omit for text-to-image |
--aspect-ratio RATIO | No | 1:1 2:3 3:2 3:4 4:3 4:5 5:4 9:16 16:9 21:9 |
--resolution RES | No | 1K 2K 4K (uppercase K required, triggers Pro model) |
gemini-3.1-flash-image-preview): Default. Fast, high-quality.gemini-3-pro-image-preview): Auto-selected when --resolution is set. 4K output, advanced reasoning, high-fidelity text rendering.| Use case | Example command |
|---|---|
| Website hero image | --prompt "..." --aspect-ratio 16:9 |
| Social media post | --prompt "..." --aspect-ratio 1:1 |
| Mobile banner | --prompt "..." --aspect-ratio 9:16 |
| Placeholder / mockup | --prompt "..." --output placeholder.png |
| Edit existing photo | --prompt "remove the background" --images photo.png |
| Style transfer | --prompt "Apply watercolor style" --images style.png photo.png |
| High-res asset | --prompt "..." --resolution 4K |
All editing is text-guided — describe what to change ("replace the sky", "remove the person", "add a sunset") and Gemini identifies and modifies regions automatically. No masks needed.