Computational Ekphrasis: Reflections on generative modes of cultural production

by Daniel Chávez Heras, King’s College London

Abstract

Contemporary generative AI systems enable a mode of visual production through verbal interaction. Multi-modal models that take text and/or images interchangeably as inputs and reproduce them as outputs are being used by millions of people around the world and are already having a significant impact on contemporary visual culture.

In philosophy, there is a term to describe this type of inter-semiotic correspondence between words and images: Ekphrasis ―from the Greek ek meaning “out” and phrásis meaning “speak.” Current generative systems allow new forms of correspondence and permutation between visual and linguistic registers through calculation, I call this: computational ekphrasis, a process by which language can frozen to be seen all at once, as if it was an image, and images can be sequentially unrolled as it they were read and written.

In this presentation I elaborate on this notion of computational ekphrasis. Through a series of examples, including from my own practice in the computational modelling of moving images, I explore ways to mobilise aesthetic frameworks to think critically about programming and about generative modes of cultural production, before and after generative AI.

Bio

Dr Daniel Chávez Heras is a lecturer in Digital Culture and Creative Computing in the Department of Digital Humanities at King’s College London.

He specialises in the computational production and analysis of visual culture. His research combines critical frameworks in the history and theories of cinema, television, and photography, with advanced technical practice in creative and scientific computing, including applied machine learning technologies.

His new book Cinema and Machine Vision is out now.