playbooks

home / skills / eyadsibai / ltk / nanobanana

nanobanana skill

/plugins/ltk-core/skills/nanobanana

This skill helps you generate and edit images using Google Gemini API, with prompts, sizes, and models for quick visual results.

npx playbooks add skill eyadsibai/ltk --skill nanobanana

Review the files below or copy the command above to add this skill to your agents.

Files (2)
SKILL.md
2.7 KB
---
name: nanobanana
description: Use when "nanobanana", "generate image", "create image", "edit image", "AI drawing", "Gemini image", "image generation"
version: 1.0.0
---

# Nanobanana Image Generation

Generate and edit images using Google Gemini API.

---

## Prerequisites

| Requirement | Setup |
|-------------|-------|
| **API Key** | Export `GEMINI_API_KEY` or add to `~/.nanobanana.env` |
| **Dependencies** | `pip install google-genai Pillow python-dotenv` |
| **Script** | `${CLAUDE_PLUGIN_ROOT}/skills/core/nanobanana/nanobanana.py` |

---

## Basic Usage

| Task | Command |
|------|---------|
| **Generate image** | `python3 nanobanana.py --prompt "description" --output "file.png"` |
| **Edit image** | `python3 nanobanana.py --prompt "changes" --input source.png --output "edited.png"` |

---

## Aspect Ratios

| Size | Ratio | Use Case |
|------|-------|----------|
| `1024x1024` | 1:1 | Square, logos |
| `768x1344` | 9:16 | Portrait, stories (default) |
| `1344x768` | 16:9 | Landscape, wallpapers |
| `832x1248` | 2:3 | Portrait photos |
| `1248x832` | 3:2 | Landscape photos |
| `1536x672` | 21:9 | Ultra-wide |

Use `--size WIDTHxHEIGHT` to specify.

---

## Models

| Model | Trade-off |
|-------|-----------|
| `gemini-3-pro-image-preview` | Higher quality (default) |
| `gemini-2.5-flash-image` | Faster generation |

Use `--model MODEL` to specify.

---

## Resolution

| Resolution | Use Case |
|------------|----------|
| `1K` | Testing, drafts (default) |
| `2K` | Good quality |
| `4K` | Final output, print |

Use `--resolution RES` to specify.

---

## Best Practices

| Practice | Why |
|----------|-----|
| Be descriptive | Include style, mood, colors, composition |
| Use 1:1 for logos | Clean square format |
| Use 9:16 for stories | Standard mobile format |
| Use 16:9 for wallpapers | Standard widescreen |
| Start with 1K | Test before using higher resolution |
| Use flash model for iteration | Save time during drafting |

---

## Examples

**Generate landscape:**

```bash
python3 nanobanana.py --prompt "Mountain sunset with lake" --size 1344x768 --output "landscape.png"
```

**Generate logo:**

```bash
python3 nanobanana.py --prompt "Minimalist tech logo" --size 1024x1024 --output "logo.png"
```

**Edit existing image:**

```bash
python3 nanobanana.py --prompt "Add rainbow to sky" --input photo.png --output "edited.png"
```

**High quality output:**

```bash
python3 nanobanana.py --prompt "Professional portrait" --resolution 2K --output "portrait.png"
```

---

## Troubleshooting

| Issue | Solution |
|-------|----------|
| Script fails | Check `GEMINI_API_KEY` is set |
| No image generated | Make prompt more specific |
| Can't read input | Verify file exists and is readable |
| Can't write output | Check directory is writable |

Overview

This skill provides a simple CLI for generating and editing images with the Google Gemini image API. It wraps model selection, aspect ratio, and resolution options into an easy script so you can produce logos, portraits, landscapes, or edits from prompts. Configure your GEMINI_API_KEY and run commands to create or modify images locally.

How this skill works

The script sends text prompts (and optional input images for edits) to a chosen Gemini image model and saves the returned image file. You can control size, resolution, and model to balance quality and speed. It supports image editing by supplying an input file plus a prompt describing the changes.

When to use it

  • Generate new images from text prompts (art, logos, wallpapers).
  • Edit or augment existing photos by providing an input image and a change prompt.
  • Iterate quickly during concepting using faster models or lower resolution.
  • Produce final high-quality outputs by increasing resolution and using the pro model.
  • Specify aspect ratios for platform-specific formats (stories, wallpapers, logos).

Best practices

  • Be descriptive in prompts: include style, mood, color, and composition details.
  • Start with 1K resolution to test prompts, then step up to 2K/4K for final exports.
  • Choose aspect ratio to match the intended use (1:1 for logos, 9:16 for mobile stories, 16:9 for wallpapers).
  • Use faster model for drafts and the higher-quality model for final renders.
  • Verify GEMINI_API_KEY and file permissions before running tasks.

Example use cases

  • Create a minimalist company logo: prompt + --size 1024x1024 -> logo.png.
  • Generate a portrait for a portfolio: prompt + --resolution 2K -> portrait.png.
  • Produce a landscape wallpaper: prompt + --size 1344x768 -> landscape.png.
  • Edit a photo to add elements: --input photo.png --prompt "Add rainbow to sky" --output edited.png.
  • Iterate concepts quickly by using gemini-2.5-flash-image at 1K for drafts.

FAQ

How do I set the API key?

Export GEMINI_API_KEY in your shell or place it in ~/.nanobanana.env so the script can read it.

Which model should I pick?

Use the pro preview model for best quality; choose the flash model for faster, lower-cost drafts.

What size should I use for logos?

Use 1024x1024 (1:1) for logos to get a clean square composition suitable for branding.