Generate images using Nano Banana Pro (Gemini 3 Pro Preview). Use when creating app icons, logos, UI graphics, marketing banners, social media images, illustrations, diagrams, or any visual assets...
Generate images using Nano Banana Pro (Gemini 3 Pro Preview) for any visual asset needs. Supports reference images for style transfer and character consistency.
# Basic generation
python scripts/generate_image.py "A friendly robot mascot waving" --output ./mascot.png
# With style reference (keep same visual style)
python scripts/generate_image.py "Same style, new content" --ref ./reference.jpg --output ./new.png
python scripts/generate_image.py <prompt> --output <path> [options]
Required:
prompt - Image description--output, -o - Output file pathOptions:
--aspect, -a - Aspect ratio (default: 1:1)1:12:3, 3:4, 4:5, 9:163:2, 4:3, 5:4, 16:9, 21:9--size, -s - Resolution: 1K, 2K (default), 4K--ref, -r - Reference image (can use multiple times, max 14)Gemini supports up to 14 reference images for:
Keep the visual style (colors, textures, mood) from a reference:
python scripts/generate_image.py "New scene with mountains, same visual style as reference" \
--ref ./style-reference.jpg --output ./styled-mountains.png
Maintain character appearance across multiple images:
python scripts/generate_image.py "Same character now in a forest setting" \
--ref ./character.png --output ./character-forest.png
Combine elements from multiple references:
python scripts/generate_image.py "Combine the style of first image with subject of second" \
--ref ./style.png --ref ./subject.png --output ./combined.png
For generating a series with consistent style:
--ref for subsequent images# Generate cover
python scripts/generate_image.py "Tech knowledge card cover" -o ./01-cover.png
# Generate subsequent cards with style reference
python scripts/generate_image.py "Card 2 content, same style" --ref ./01-cover.png -o ./02-card.png
python scripts/generate_image.py "Card 3 content, same style" --ref ./01-cover.png -o ./03-card.png
Determine output location - Place images where contextually appropriate:
./assets/icons/./marketing/./src/assets/./generated/Craft effective prompts - Be specific and descriptive:
Choose appropriate settings:
--aspect 1:1--aspect 16:9 or 21:9--aspect 9:16--aspect 3:4--aspect 3:2 or 4:3App icon:
python scripts/generate_image.py "Minimalist flat design app icon of a lightning bolt, purple gradient background, modern iOS style" \
--output ./assets/app-icon.png --aspect 1:1
Marketing banner:
python scripts/generate_image.py "Professional website hero banner for a productivity app, abstract geometric shapes, blue and white color scheme" \
--output ./public/images/hero-banner.png --aspect 16:9
Xiaohongshu knowledge card:
python scripts/generate_image.py "Tech knowledge card, dark blue purple gradient, neon cyan accents, code block style, Chinese text 'æ ‡é¢˜'" \
--output ./xiaohongshu/card.png --aspect 3:4
Style transfer:
python scripts/generate_image.py "Transform this photo into watercolor painting style" \
--ref ./photo.jpg --output ./watercolor.png
Character in new scene:
python scripts/generate_image.py "Same character from reference, now sitting in a cafe, warm lighting" \
--ref ./character.png --output ./character-cafe.png --aspect 3:2