ACADEMIC


RE-DESIGN

GENERATIVE AI IN ARCHITECTURE


in collaboration with Dakota Bacchus

TOOLS

Comfy UI Diffusion, Rhino 7 + Grasshopper, ChatGPT, Gemini, PromeAI, AutoTRIZ, Rodin, Photoshop, Illustrator, 3D Printing

COMPLETED

December 2024

This project is the culmination of 12 weeks of rigerous immersion into various Generative AI tools and exploring the role of AI in architecture. Through these tools, this project looks at reimagining public space, and how landscape and architecture can intersect to create intentional third-spaces in our cities. The process begins with mass image generation from a series of engineered prompts, then generating 3D forms based on those images. The forms are 3D printed, spatially composed, photographed, and then re-interpreted with AI. Each step of the process was woven with our architectural vision for the space, with AI as the vessel for rapid iteration and then visual refinement.

︎





DESIGN OBJECTIVES

INTERVENTIONS

- Interactive Pathways, Kinetic Tiles
- Playful Pavement
- Sound & Temperature Responsive Features

AGENT SIMULATION

- Movement Simulation
- Path & Engagement Analysis
- Layout & Configuration Optimization

BENEFITS/IMPACT

- Encouraging Movement & Exploration
- Foster Social Interaction
- Cultivate a Sense of Ownership


AGENT SIMULATION

Grasshopper
Identify Form
Visualize Data


FINAL VISUALS

“HERO” IMAGE, ARIAL VIEW

POV: WALKING THROUGH



POV: COMING UP THE ELEVATOR



PLAN VIEW: NIGHT-TIME



PLAN VIEW: PARTI