Our review
Generates and edits images using Google's Gemini Image API (Nano Banana) from the command line.
Strengths
- Fast generation with standard Nano Banana model
- Edit existing images (background replacement, content modification)
- Pro model support for professional-quality visuals
- Simple usage via uv with no manual installation
Limitations
- Requires a Gemini API key and internet connection
- Cost per image (approx $0.039 for Nano Banana)
- Quality depends on model choice and prompt
Best for quickly creating visuals, infographics, or editing images without complex graphic tools.
Avoid for precise photo compositing or professional retouching that requires desktop software.
Security analysis
SafeThe skill instructs running a Python script that uses a local API key to call Google's Gemini API for image generation. No destructive commands, exfiltration, or obfuscation present. The script is not provided, but assuming it follows the instructions, it is safe.
No concerns found
Examples
Generate an image of a futuristic city at sunset with flying cars and neon lights.Edit this image: change the background to a beach sunset. The image is at /path/to/photo.jpg.Create an infographic about renewable energy sources using the Pro model.name: nano-banana-imagegen description: Generate and edit images using Google's Nano Banana (Gemini Image API). Use when the user wants to create AI-generated images, edit existing images, create infographics, generate product mockups, design social media graphics, or perform any image generation/manipulation task. Requires GEMINI_API_KEY environment variable.
Nano Banana Image Generation
Generate and edit images using Google's Gemini Image models (Nano Banana and Nano Banana Pro).
Prerequisites
-
API Key: Set the
GEMINI_API_KEYenvironment variable- Get key from: https://aistudio.google.com/apikey
-
uv: The script uses inline dependencies with uv (no manual install needed)
Quick Start
Using the Script
# Generate an image
uv run scripts/generate_image.py "A futuristic city at sunset" -o city.png
# Edit an existing image
uv run scripts/generate_image.py "Remove the background" -i photo.jpg -o edited.png
# Use Nano Banana Pro for higher quality
uv run scripts/generate_image.py "Create a detailed infographic" -m pro -o infographic.png
Direct Python Usage (with uv)
uv run --with google-genai python -c '
from google import genai
import os
client = genai.Client(api_key=os.environ["GEMINI_API_KEY"])
response = client.models.generate_content(
model="gemini-2.5-flash-image",
contents=["Create an image of a cat wearing a space helmet"]
)
for part in response.candidates[0].content.parts:
if part.inline_data:
with open("output.png", "wb") as f:
f.write(part.inline_data.data)
print("Saved to output.png")
'
Model Selection
| Model | Use Case |
|-------|----------|
| gemini-2.5-flash-image (Nano Banana) | Fast generation, iterations, high volume |
| gemini-3-pro-image-preview (Nano Banana Pro) | Professional quality, text rendering, complex prompts |
Common Tasks
Image Generation
uv run scripts/generate_image.py "A serene Japanese garden with cherry blossoms" -o garden.png
Image Editing
uv run scripts/generate_image.py "Change the background to a beach sunset" -i input.jpg -o edited.png
Infographics (use Pro model)
uv run scripts/generate_image.py "Create an infographic about renewable energy" -m pro -o infographic.png
Resources
- Script:
scripts/generate_image.py- CLI tool with inline uv dependencies - API Reference: See
references/api_reference.mdfor detailed SDK usage - Prompting Guide: See
references/prompting_guide.mdfor effective prompts
Pricing
~$0.039 per image for Nano Banana (1290 tokens per image at $30/1M tokens)
Content Repurposer
Content
Transforms a single piece of content into platform-adapted publications.
SEO Blog Post Writer
Content
Writes SEO-optimized blog posts with proper structure and keywords.
YouTube Script Writer
Content
Writes engaging YouTube scripts with hooks, structure, and retention.