food-diorama-skill
Generate artistic 3D city-themed food diorama images using Google Gemini API. Creates Pop Mart style four-quadrant layouts featuring iconic dishes, cultural symbols, and city-specific heritage elements.
Introduction
The food-diorama-skill is a specialized generative AI tool designed to create high-quality, isometric 3D dioramas that visualize the culinary heritage of various Chinese cities. It serves as an imaginative bridge between local gastronomy and artistic display, transforming traditional food culture into miniature, Pop Mart-inspired blind box scenes. This skill is ideal for content creators, travel bloggers, and culture enthusiasts who need unique, visually striking artwork for social media, presentations, or digital wallpapers. It operates by coordinating with the nanobanana skill to leverage advanced image generation models for consistent stylistic output.
-
Generates four-quadrant circular layouts representing diverse culinary themes such as morning tastes, historical feasts, street food, and sweet cultures.
-
Features chibi-style characters interacting with oversized food items, adding a playful and engaging aesthetic to the 3D diorama.
-
Includes an integrated database for major cities like Xi'an, Chongqing, Chengdu, Beijing, and Guangzhou, with customizable data fields for cultural symbols and historical inscriptions.
-
Offers flexible image parameters including resolution (1K to 4K), aspect ratios for various platforms (square for social media, landscape for wallpapers), and model selection (e.g., gemini-3-pro-image-preview).
-
Provides a command-line interface for rapid prototyping, featuring prompt previews via --show-prompt and an extensible CITY_DATABASE structure for adding new cities.
-
Requires prior configuration of the nanobanana skill and a valid GEMINI_API_KEY.
-
Operates using Python 3, making it highly portable for integration into automated content workflows.
-
Best results are achieved by balancing resolution settings against generation time; 2K is recommended for standard quality, while 4K is reserved for print or high-end display needs.
-
Supports extensive customization through the modification of city metadata, allowing users to add specific textural details and cultural action scenes for new locations.
-
Always verify city availability using the --list-cities command before running generation scripts to ensure the input name matches the internal registry.
Repository Stats
- Stars
- 18
- Forks
- 1
- Open Issues
- 0
- Language
- Python
- Default Branch
- main
- Sync Status
- Idle
- Last Synced
- May 3, 2026, 09:14 AM