From Continuous to Discrete to Continuous – Text-to-Image Models as Limit to Indeterminate Phantasy

Author(s)

  • Sebastian Rozenberg Linköping University

DOI:

https://doi.org/10.54195/technophany.18016

Keywords:

AI-generated images, Husserl, Imagination, Image Theory, Indeterminacy, Phenomenology, Text-to-Image models

Abstract

This essay analyses the interplay of indeterminacy and determinacy in the experience of images generated through text-to-image (T2I) models. Through an interdisciplinary approach, it uncovers three layers of indeterminacy: the computational indeterminacy inherent in text-to-image model processes, the indeterminacy of imagination in Husserl’s concept of protean phantasy, and finally the visual indeterminacy that figures in meaning making in all images. Generated images pass through these stages of indeterminacy, transforming indeterminate phantasy into determined visual objects, resulting in a conflict of consciousness between potential and actual. A distinction emerges between artificial phantasy, characterized by quasi-experience, and artificial imagination, grounded in images both as training data and perceptual image objects. As mediators between indeterminacy and determination, T2I images appear as technical media that mediate multiple forms of indeterminacy, showing the circulation between phantasy and imagination, between continuous and discrete. The generated image marks the limit of the unlimited indeterminate imagination.

Downloads

Download data is not yet available.

Downloads

Published

2024-09-23

Issue

Section

Computational Creativity Articles (Edited by Anna Longo)

How to Cite

Rozenberg, Sebastian. 2024. “From Continuous to Discrete to Continuous – Text-to-Image Models As Limit to Indeterminate Phantasy”. Technophany, A Journal for Philosophy and Technology 2 (1): 1-23. https://doi.org/10.54195/technophany.18016.