Fluidic Abstractions

Type - Computation (Machine Learning)
Year - 2020


Fluidic abstractions explores the possibilities of generating visuals based on conceptual works and ideas of selected designers (Zaha Hadid, Peter Cook, MAD, Archigram, Superstudio...etc.) from different eras/fields but with “similar” or sometimes “radical” beliefs.
The project is an experiment, depending on Machine Learning (StyleGAN) to understand, learn - styles, ideas and nuances of a few selected designers and eventually generate visuals based on those learnings.

Software - RunwayML + Python