Generative Metaverse: Machine Learning Applications in Architecture

-artificial intelligence,-computational design | - online workshop | -English


Required Skills: Basic Rhino, Grasshopper, and Python are suggested

Required Software: Rhino, Grasshopper, Google Colab

Required Hardware: PC or laptop
Maximum number of participating students: 100

YouTube Stream Link:

Generative Metaverse is a workshop that revisits the relationship between spoken and written language and architecture as well as current notions of the metaverse. Generated through a combination of the latest machine learning models, images can be generated from text inputs. The parameters behind each model and semantics of these inputs establish new forms of architectural and cultural production where human agency remains critical in this creative process. In this workshop, we will question whether this novel design process would pass the architectural Turing Test, a question posed in last year’s Machine Intelligence Workshop. To do this, students will learn about text-to-image machine learning models, including CLIP, Dalle, and Imagen, and image to 3D processes in Grasshopper, and apply these to architectural design outputs. We will collectively create a Latent City of the Captive Globe – a series of latent urban morphologies and students will learn an overview of how 3D NFTs can be minted, as a digital and personalized metaverse. Harvard GSD Workshop Instructors: George Guida, Dongyun Kim, GeneratiVerse.eth

1 / 2
2 / 2


timezone: (GMT -5:00) Eastern Time (US & Canada), Bogota, Lima
Start timeEnd timeDescription
2022-06-29 - 09:002022-06-29 - 12:00Lecture 01 - Machine Learning and applications in architecture and design; Hands on workshop on text - image models.
2022-06-30 - 09:002022-06-30 - 12:00Lecture 02; 2.5D process workflows in grasshopper; Additional Office hours provided.
2022-07-01 - 09:002022-07-01 - 12:00Lecture 03; 3d ML workflows and Unity introduction; Additional Office hours provided.
2022-07-02 - 09:002022-07-02 - 23:00Final student project presentations with Harvard GSD guests.


George Guida George Guida is a researcher at Harvard Laboratory for Design Technologies, co-founder of ArchiTAG LLP, and a RIBA ARB architect working to synthesize design and technology. His main research lies in understanding the architecture of complex contemporary challenges and developing prototypes for a more participatory, responsive, and innovative future. This spans creative applications of 2D & 3D machine learning, web3, mixed reality, and current notions of the metaverse. He has published extensively in these fields, has worked several years with Foster + Partners, and conducted computational research at Harvard and at the MIT Media Lab.
Dongyun Kim Dongyun Kim is an architectural and computational designer based in the United States. He completed his Master in Design Studies with a concentration in Technology at Harvard University Graduate School of Design, Master of Science in Design at the University of Pennsylvania, and Bachelor of Architecture at Hongik University in Seoul, Korea.
generativerse .eth GeneratiVerse is an collective effort to build a crowd-sourcing generative metaverse!

All workshops will accept 100 applications MAX.