Nanobanana Image Generation Skill
Generate or edit images using Google Gemini API through the nanobanana tool.
Requirements
- GEMINI_API_KEY: Must be configured in
~/.nanobanana.env or export GEMINI_API_KEY=<your-api-key>
- Python3 with dependent packages installed: google-genai, Pillow, python-dotenv. They could be installed via
python3 -m pip install -r ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/requirements.txt if not installed yet.
- Executable:
${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py
Instructions
For image generation
Ask the user for:
- What they want to create (the prompt)
- Desired aspect ratio/size (optional, defaults to 9:16 portrait)
- Output filename (optional, auto-generates UUID if not specified)
- Model preference (optional, defaults to gemini-3.1-flash-image-preview)
- Resolution (optional, defaults to 1K)
Run the nanobanana script with appropriate parameters:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt "description of image" --output "filename.png"
Show the user the saved image path when complete
For image editing
Ask the user for:
- Input image file(s) to edit
- What changes they want (the prompt)
- Output filename (optional)
Run with input images:
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt "editing instructions" --input image1.png image2.png --output "edited.png"
Available Options
Aspect Ratios (--size)
1024x1024 (1:1) - Square
832x1248 (2:3) - Portrait
1248x832 (3:2) - Landscape
864x1184 (3:4) - Portrait
1184x864 (4:3) - Landscape
896x1152 (4:5) - Portrait
1152x896 (5:4) - Landscape
768x1344 (9:16) - Portrait (default)
1344x768 (16:9) - Landscape
1536x672 (21:9) - Ultra-wide
Models (--model)
gemini-3.1-flash-image-preview (default) - Latest, fast generation
gemini-3-pro-image-preview - Higher quality, supports thinking/reasoning
Resolution (--resolution)
Other Options
--no-search - Disable Google Search grounding (enabled by default)
--no-think - Disable thinking/reasoning mode
Examples
Generate a simple image
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt "A serene mountain landscape at sunset with a lake"
Generate with specific size and output
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \
--prompt "Modern minimalist logo for a tech startup" \
--size 1024x1024 \
--output "logo.png"
Generate landscape image with high resolution
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \
--prompt "Futuristic cityscape with flying cars" \
--size 1344x768 \
--resolution 2K \
--output "cityscape.png"
Edit existing images
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \
--prompt "Add a rainbow in the sky" \
--input photo.png \
--output "photo-with-rainbow.png"
Use pro model for higher quality
python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \
--prompt "Detailed portrait of a cat in watercolor style" \
--model gemini-3-pro-image-preview \
--output "cat-portrait.png"
Error Handling
If the script fails:
- Check that
GEMINI_API_KEY is exported or set in ~/.nanobanana.env
- Verify input image files exist and are readable
- Ensure the output directory is writable
- If no image is generated, try making the prompt more specific about wanting an image
Best Practices
- Be descriptive in prompts - include style, mood, colors, composition
- For logos/graphics, use square aspect ratio (1024x1024)
- For social media posts, use 9:16 for stories or 1:1 for posts
- For wallpapers, use 16:9 or 21:9
- Start with 1K resolution for testing, upgrade to 2K/4K for final output
- Use gemini-3-pro-image-preview for best quality, gemini-3.1-flash-image-preview (default) for speed
1---2name: nanobanana-skill-43description: 'Generate or edit images using Google Gemini API via nanobanana. Triggers: "nanobanana", "generate image", "create image", "edit image", "AI drawing", "图片生成", "AI绘图", "图片编辑", "生成图片".'4allowed-tools: Read, Write, Glob, Grep, Task, Bash(cat:*), Bash(ls:*), Bash(tree:*), Bash(python3:*)5metadata:6 source: https://skillmd.com/skills/majiayu000/nanobanana-skill-47---89# Nanobanana Image Generation Skill1011Generate or edit images using Google Gemini API through the nanobanana tool.1213## Requirements14151. **GEMINI_API_KEY**: Must be configured in `~/.nanobanana.env` or `export GEMINI_API_KEY=<your-api-key>`162. **Python3 with dependent packages installed**: google-genai, Pillow, python-dotenv. They could be installed via `python3 -m pip install -r ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/requirements.txt` if not installed yet.173. **Executable**: `${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py`1819## Instructions2021### For image generation22231. Ask the user for:24 - What they want to create (the prompt)25 - Desired aspect ratio/size (optional, defaults to 9:16 portrait)26 - Output filename (optional, auto-generates UUID if not specified)27 - Model preference (optional, defaults to gemini-3.1-flash-image-preview)28 - Resolution (optional, defaults to 1K)29302. Run the nanobanana script with appropriate parameters:3132 ```bash33 python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt "description of image" --output "filename.png"34 ```35363. Show the user the saved image path when complete3738### For image editing39401. Ask the user for:41 - Input image file(s) to edit42 - What changes they want (the prompt)43 - Output filename (optional)44452. Run with input images:4647 ```bash48 python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt "editing instructions" --input image1.png image2.png --output "edited.png"49 ```5051## Available Options5253### Aspect Ratios (--size)5455- `1024x1024` (1:1) - Square56- `832x1248` (2:3) - Portrait57- `1248x832` (3:2) - Landscape58- `864x1184` (3:4) - Portrait59- `1184x864` (4:3) - Landscape60- `896x1152` (4:5) - Portrait61- `1152x896` (5:4) - Landscape62- `768x1344` (9:16) - Portrait (default)63- `1344x768` (16:9) - Landscape64- `1536x672` (21:9) - Ultra-wide6566### Models (--model)6768- `gemini-3.1-flash-image-preview` (default) - Latest, fast generation69- `gemini-3-pro-image-preview` - Higher quality, supports thinking/reasoning7071### Resolution (--resolution)7273- `1K` (default)74- `2K`75- `4K`7677### Other Options7879- `--no-search` - Disable Google Search grounding (enabled by default)80- `--no-think` - Disable thinking/reasoning mode8182## Examples8384### Generate a simple image8586```bash87python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py --prompt "A serene mountain landscape at sunset with a lake"88```8990### Generate with specific size and output9192```bash93python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \94 --prompt "Modern minimalist logo for a tech startup" \95 --size 1024x1024 \96 --output "logo.png"97```9899### Generate landscape image with high resolution100101```bash102python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \103 --prompt "Futuristic cityscape with flying cars" \104 --size 1344x768 \105 --resolution 2K \106 --output "cityscape.png"107```108109### Edit existing images110111```bash112python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \113 --prompt "Add a rainbow in the sky" \114 --input photo.png \115 --output "photo-with-rainbow.png"116```117118### Use pro model for higher quality119120```bash121python3 ${CLAUDE_PLUGIN_ROOT}/skills/nanobanana-skill/nanobanana.py \122 --prompt "Detailed portrait of a cat in watercolor style" \123 --model gemini-3-pro-image-preview \124 --output "cat-portrait.png"125```126127## Error Handling128129If the script fails:130131- Check that `GEMINI_API_KEY` is exported or set in ~/.nanobanana.env132- Verify input image files exist and are readable133- Ensure the output directory is writable134- If no image is generated, try making the prompt more specific about wanting an image135136## Best Practices1371381. Be descriptive in prompts - include style, mood, colors, composition1392. For logos/graphics, use square aspect ratio (1024x1024)1403. For social media posts, use 9:16 for stories or 1:1 for posts1414. For wallpapers, use 16:9 or 21:91425. Start with 1K resolution for testing, upgrade to 2K/4K for final output1436. Use gemini-3-pro-image-preview for best quality, gemini-3.1-flash-image-preview (default) for speed