Article:
Fuzzy Ingenuity: Creative Potentials and Mechanics of Fuzziness in Processes of Image Creation with AI-Based Text-to-Image Generators

Simple item page
dc.creatorFeyersinger, Erwin
dc.creatorKohmann, Lukas
dc.creatorPelzer, Michael
dc.date.accessioned2024-06-14T11:09:36Z
dc.date.available2024-06-14T11:09:36Z
dc.date.issued2023
dc.description.abstractThis explorative paper focuses on fuzziness of meaning and visual rep- resentation in connection with text prompts, image results, and the mapping between them by discussing the question: How does the fuzziness inherent in artificial intelligence-based text-to-image generators such as DALL·E 2, Midjour- ney, or Stable Diffusion influence creative processes of image production – and how can we grasp its mechanics from a theoretical perspective? In addressing these questions, we explore three connected interdisciplinary approaches: (1) Text-to-image generators give new relevance to Hegel’s notion of language as ‘the imagination which creates signs’. They reinforce how language itself inevitably acts as a meaning-transforming system and extend the formative dimension of language with a technology-driven facet. (2) From the perspective of speech act theory, we discuss this explorative interaction with an algorithm as performative utterances. (3) In further examining the pragmatic dimension of this interac- tion, we discuss the creative potential arising from the visual feedback loops it includes. Following this thought, we show that the fuzzy variety of images which DALL·E 2 presents in response to one and the same text prompt contributes to a highly accelerated form of externalized visual thinking.en
dc.identifier.doihttp://dx.doi.org/10.25969/mediarep/22317
dc.identifier.urihttps://mediarep.org/handle/doc/23749
dc.languageeng
dc.publisherHerbert von Halem
dc.publisher.placeKöln
dc.relation.isPartOfissn:1614-0885
dc.relation.ispartofseriesIMAGE. Zeitschrift für interdisziplinäre Bildwissenschaft
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/
dc.subjectvisual representationen
dc.subjecttext promptsen
dc.subjectartificial intelligenceen
dc.subjecttext-to-image generatorsen
dc.subject.ddcddc:700
dc.titleFuzzy Ingenuity: Creative Potentials and Mechanics of Fuzziness in Processes of Image Creation with AI-Based Text-to-Image Generatorsen
dc.typearticle
dc.type.statuspublishedVersion
dspace.entity.typeArticle
local.coverpage2024-06-16T02:32:03
local.source.epage149
local.source.issue1
local.source.issueTitleGenerative Imagery: Towards a ‘New Paradigm’ of Machine Learning-Based Image Production
local.source.spage135
local.source.volume19

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
IMAGE_37_2023_135-149_Feyersinger_ea_Fizzy_.pdf
Size:
500.33 KB
Format:
Adobe Portable Document Format
Description:
Original PDF with additional cover page.
Download

Collections

2023 | 37