Nano Banana Pro - AI Image Generation

Generate images using Google's Gemini 3 Pro Image model.

Usage

Run the generation script:

python ~/.claude/skills/nano-banana-pro/generate_image.py "your prompt here" [options]

Option	Description	Default
`--resolution`	Output size: 1K, 2K, or 4K	2K
`--aspect`	Aspect ratio: 16:9, 1:1, 4:3, 9:16, 3:4	16:9
`--output`	Output directory path	./generated_images
`--reference`	Reference image(s) for style/editing (up to 14)	None
`--format`	Output format: png, jpeg, webp	png
`--no-text`	Add instruction to exclude text/typography	off
`--cinematic`	Add cinematic film style (ARRI, shallow DoF, grain)	off
`--photorealistic`	Add photorealistic style hints	off

python ~/.claude/skills/nano-banana-pro/generate_image.py "a serene mountain landscape at sunset, photorealistic"

python ~/.claude/skills/nano-banana-pro/generate_image.py "abstract geometric pattern in blue and gold" --aspect 1:1 --resolution 2K

python ~/.claude/skills/nano-banana-pro/generate_image.py "futuristic city skyline" --resolution 4K --output ~/Pictures/ai-generated

python ~/.claude/skills/nano-banana-pro/generate_image.py "transform this into a watercolor painting" --reference input.jpg

python ~/.claude/skills/nano-banana-pro/generate_image.py "add a rainbow in the sky" --reference landscape.png

Images are saved with timestamp filenames:

The script outputs the full path to the generated image.

Gemini 3 Pro Image requires paid billing (no free tier)
Generated images include SynthID watermarking
Reference images enable style transfer and editing capabilities
Raw prompts by default: Prompts are sent unadulterated. Use --no-text, --cinematic, or --photorealistic flags to add style hints.