nanobanana
resciencelab/opc-skills
Generate and edit images using Google Gemini 3 Pro Image with text-to-image, editing, and 4K output.
What is nanobanana?
Nano Banana uses Google's Gemini 3 Pro Image model to generate images from text prompts and edit existing images. Use it when you need AI image generation, style transfer, or high-resolution output up to 4K.
- Generate images from text prompts with customizable aspect ratios (1:1, 16:9, 21:9, etc.)
- Edit existing images with natural language instructions (style transfer, object addition, background changes)
- Output high-resolution images in standard, 2K, or 4K sizes
- Batch generate multiple image variations with sequential naming
- Enable Google Search grounding for factually accurate images of real people, places, and landmarks
How to install nanobanana
npx skills add https://github.com/resciencelab/opc-skills --skill nanobanana- GEMINI_API_KEY from Google AI Studio (https://aistudio.google.com/apikey)
- Python 3.10 or higher
- google-genai and pillow packages (install via: pip install google-genai pillow)
How to use nanobanana
- 1.Set your GEMINI_API_KEY environment variable with your Google API key
- 2.Run generate.py with a text prompt to create an image: python3 scripts/generate.py "your prompt" -o output.png
- 3.For image editing, provide an input image: python3 scripts/generate.py "edit description" -i input.jpg -o output.png
- 4.Specify aspect ratio with --ratio (e.g., 16:9 for widescreen) and size with --size (2K or 4K for higher quality)
- 5.For batch generation, use batch_generate.py with -n flag to create multiple variations: python3 scripts/batch_generate.py "prompt" -n 20 -d ./output_dir
Use cases
- Create product photography or marketing visuals from descriptions
- Generate pixel art logos or icons in bulk with batch processing
- Edit photos by changing backgrounds, adding objects, or adjusting colors
- Produce cinematic landscapes or concept art with specific aspect ratios
- Generate variations of a design to explore different styles and compositions
- Designers and creative professionals needing quick image generation
- Content creators producing marketing or social media assets
- Product teams prototyping visual concepts
- Developers building image generation into applications
nanobanana FAQ
Supported ratios include 1:1 (square), 2:3, 3:2, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, and 21:9 (ultra-wide/cinematic).
Use the --size flag with 2K or 4K: python3 scripts/generate.py "prompt" --size 4K -o output.png. 4K provides maximum quality and best text rendering.
Yes, use the -i flag to provide an input image: python3 scripts/generate.py "edit description" -i input.jpg -o output.png. The model supports style transfer, object addition/removal, and color adjustments.
The prompt may have triggered safety filters. Try rephrasing to avoid sensitive content. You can also enable Google Search grounding with --search for factually accurate images.
Use batch_generate.py with the --delay flag to add pauses between requests (default 3 seconds). Check your quota at Google AI Studio and reduce batch size if needed.
Full instructions (SKILL.md)
Source of truth, from resciencelab/opc-skills.
name: nanobanana description: Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro). Supports text-to-image, image editing, various aspect ratios, and high-resolution output (2K/4K). Use when user wants to generate images, create images, use Gemini image generation, or do AI image generation.
Nano Banana - AI Image Generation
Generate and edit images using Google's Gemini 3 Pro Image model (gemini-3-pro-image-preview, nicknamed "Nano Banana Pro" 🍌).
Prerequisites
Required:
GEMINI_API_KEY- Get from Google AI Studio- Python 3.10+ with
google-genaipackage
Install dependencies:
pip install google-genai pillow
Quick Start
Generate an image:
python3 <skill_dir>/scripts/generate.py "a cute robot mascot, pixel art style" -o robot.png
Edit an existing image:
python3 <skill_dir>/scripts/generate.py "make the background blue" -i input.jpg -o output.png
Generate with specific aspect ratio:
python3 <skill_dir>/scripts/generate.py "cinematic landscape" --ratio 21:9 -o landscape.png
Generate high-resolution 4K image:
python3 <skill_dir>/scripts/generate.py "professional product photo" --size 4K -o product.png
Script Reference
scripts/generate.py
Main image generation script.
Usage: generate.py [OPTIONS] PROMPT
Arguments:
PROMPT Text prompt for image generation
Options:
-o, --output PATH Output file path (default: auto-generated)
-i, --input PATH Input image for editing (optional)
-r, --ratio RATIO Aspect ratio (1:1, 16:9, 9:16, 21:9, etc.)
-s, --size SIZE Image size: 2K or 4K (default: standard)
--search Enable Google Search grounding for accuracy
-v, --verbose Show detailed output
Supported aspect ratios:
1:1- Square (default)2:3,3:2- Portrait/Landscape3:4,4:3- Standard4:5,5:4- Photo9:16,16:9- Widescreen21:9- Ultra-wide/Cinematic
scripts/batch_generate.py
Generate multiple images with sequential naming.
Usage: batch_generate.py [OPTIONS] PROMPT
Arguments:
PROMPT Text prompt for image generation
Options:
-n, --count N Number of images to generate (default: 10)
-d, --dir PATH Output directory
-p, --prefix STR Filename prefix (default: "image")
-r, --ratio RATIO Aspect ratio
-s, --size SIZE Image size (2K/4K)
--delay SECONDS Delay between generations (default: 3)
Example:
python3 <skill_dir>/scripts/batch_generate.py "pixel art logo" -n 20 -d ./logos -p logo
Python API
You can also use the module directly:
from generate import generate_image, edit_image
# Generate image
result = generate_image(
prompt="a futuristic city at night",
output_path="city.png",
aspect_ratio="16:9",
image_size="4K"
)
# Edit existing image
result = edit_image(
prompt="add flying cars to the sky",
input_path="city.png",
output_path="city_edited.png"
)
Environment Variables
| Variable | Description | Default |
|---|---|---|
GEMINI_API_KEY | Google Gemini API key | Required |
IMAGE_OUTPUT_DIR | Default output directory | ./nanobanana-images |
Features
Text-to-Image Generation
Create images from text descriptions. The model excels at:
- Photorealistic images
- Artistic styles (pixel art, illustration, etc.)
- Product photography
- Landscapes and scenes
Image Editing
Transform existing images with natural language:
- Style transfer
- Object addition/removal
- Background changes
- Color adjustments
High-Resolution Output
- Standard: Fast generation, good quality
- 2K: Enhanced detail (2048px)
- 4K: Maximum quality (3840px), best for text rendering
Google Search Grounding
Enable --search for factually accurate images involving:
- Real people, places, landmarks
- Current events
- Specific products or brands
Best Practices
Prompt Writing
Good prompts include:
- Subject description
- Style/aesthetic
- Lighting and mood
- Composition details
- Color palette
Example:
"A cozy coffee shop interior, warm lighting, vintage aesthetic,
wooden furniture, plants on shelves, morning sunlight through windows,
soft focus background, 35mm film photography style"
Batch Generation Tips
- Generate 10-20 variations to explore options
- Use consistent prompts for style coherence
- Add 3-5 second delays to avoid rate limits
- Review results and iterate on best candidates
Rate Limits
- Gemini API has usage quotas
- Add delays between batch generations
- Check your quota at Google AI Studio
Troubleshooting
"API key not found"
- Set
GEMINI_API_KEYenvironment variable - Or pass via
--api-keyoption
"No image in response"
- Prompt may have triggered safety filters
- Try rephrasing to avoid sensitive content
"Rate limit exceeded"
- Wait a few seconds and retry
- Reduce batch size or add longer delays
References
- references/prompts.md - Prompt examples by category
- examples/ - Example usage scripts
Related skills
More from resciencelab/opc-skills and the wider catalog.
