A Claude Code skill for generating images using Gemini 3 Pro Preview (Nano Banana Pro).
- Text-to-image generation - Describe what you want, get an image
- Reference image support - Style transfer, character consistency (up to 14 images)
- Multiple aspect ratios - Square, portrait, landscape, cinematic
- Resolution options - 1K, 2K, 4K output
Differences from livelabs-ventures/nano-skills
| Feature | Original | This Version |
|---|---|---|
| Reference images | ❌ Not supported | ✅ Up to 14 images |
| API key config | Environment variable | Direct code edit |
Visit: https://aistudio.google.com/apikey
Edit scripts/generate_image.py, find the get_api_key() function (around line 37):
def get_api_key():
"""
Get API key.
⚠️ SETUP REQUIRED: Replace the placeholder below with your Gemini API key.
Get your API key from: https://aistudio.google.com/apikey
"""
return "YOUR_GEMINI_API_KEY_HERE" # <-- Replace this with your API keyReplace YOUR_GEMINI_API_KEY_HERE with your actual API key:
return "AIzaSy..." # Your actual keygit clone https://github.com/YOUR_USERNAME/nano-image-generator-skill.gitAdd to your ~/.claude/settings.json:
{
"skills": [
"/path/to/nano-image-generator-skill"
]
}claude skill add github:YOUR_USERNAME/nano-image-generator-skillnano-image-generator-skill/
├── SKILL.md # Skill definition for Claude Code
├── README.md # This file
├── README_CN.md # Chinese documentation
└── scripts/
└── generate_image.py # Image generation script (edit API key here)
Once installed, Claude Code will automatically use this skill when you ask to:
- "Generate an image of..."
- "Create an icon for..."
- "Design a logo..."
- "Make a banner..."
- "Same style as this image..."
python scripts/generate_image.py "A cute robot mascot" --output ./robot.pngpython scripts/generate_image.py "Website banner" --aspect 16:9 --output ./banner.pngpython scripts/generate_image.py "Same character in a forest" --ref ./character.png --output ./forest.pngpython scripts/generate_image.py "Combine styles" --ref ./img1.png --ref ./img2.png --output ./combined.png| Option | Values | Default | Description |
|---|---|---|---|
--aspect, -a |
1:1, 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9 |
1:1 |
Aspect ratio |
--size, -s |
1K, 2K, 4K |
2K |
Resolution |
--ref, -r |
Image path | - | Reference image (repeatable, max 14) |
MIT