Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process

Tommaso Turchi; Silvio Carta; Luciano Ambrosini; Alessio Malizia

doi:10.1007/978-3-031-34433-6_3

Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process

Tommaso Turchi, Silvio Carta, Luciano Ambrosini, Alessio Malizia

School of Creative Arts

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

Large-scale Text-to-image Generative Models (LTGMs) are a cutting-edge class of Artificial Intelligence (AI) algorithms specifically designed to generate images from natural language descriptions (prompts). These models have demonstrated impressive capabilities in creating high-quality images from a wide range of inputs, making them powerful tools for non-technical users to tap into their creativity. The field is advancing rapidly and we are witnessing the emergence of an increasing number of tools, such as DALL-E, MidJourney and StableDiffusion, that are leveraging LTGMs to support creative work across various domains. However, there is a lack of research on how the interaction with these tools might affect the users’ creativity and their ability to control the generated outputs. In this paper, we investigate how the interaction with LTGMs-based tools might impact creativity by analyzing the feedback provided by groups of design students developing an architectural project with the help of LTGMs tools

Original language	English
Title of host publication	End-User Development
Subtitle of host publication	9th International Symposium, IS-EUD 2023, Proceedings
Editors	Lucio Davide Spano, Albrecht Schmidt , Carmen Santoro, Simone Stumpf
Publisher	Springer Nature
Pages	35-51
Number of pages	17
ISBN (Electronic)	978-3-031-34433-6
ISBN (Print)	978-3-031-34432-9
DOIs	https://doi.org/10.1007/978-3-031-34433-6_3
Publication status	Published - 30 May 2023
Event	9th International Symposium on End User Development - Cagliari, Italy Duration: 6 Jun 2023 → 8 Jun 2023 Conference number: 9 https://cg3hci.dmi.unica.it/iseud2023/index.html

Publication series

Name	Lecture Notes in Computer Science (LNCS)
Publisher	Springer
Volume	13917
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	9th International Symposium on End User Development
Abbreviated title	IS-EUD 2023
Country/Territory	Italy
City	Cagliari
Period	6/06/23 → 8/06/23
Internet address	https://cg3hci.dmi.unica.it/iseud2023/index.html

Keywords

AI-driven design process
Creativity
Generative AI
Human-AI

Access to Document

10.1007/978-3-031-34433-6_3Licence: Unspecified

Cite this

Turchi, T., Carta, S., Ambrosini, L., & Malizia, A. (2023). Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process. In L. D. Spano, A. Schmidt , C. Santoro, & S. Stumpf (Eds.), End-User Development: 9th International Symposium, IS-EUD 2023, Proceedings (pp. 35-51). (Lecture Notes in Computer Science (LNCS); Vol. 13917). Springer Nature . https://doi.org/10.1007/978-3-031-34433-6_3

Turchi, Tommaso ; Carta, Silvio ; Ambrosini, Luciano et al. / Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process. End-User Development: 9th International Symposium, IS-EUD 2023, Proceedings. editor / Lucio Davide Spano ; Albrecht Schmidt ; Carmen Santoro ; Simone Stumpf . Springer Nature , 2023. pp. 35-51 (Lecture Notes in Computer Science (LNCS)).

@inproceedings{fc500081414e4d0484abef954720fef0,

title = "Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process",

abstract = "Large-scale Text-to-image Generative Models (LTGMs) are a cutting-edge class of Artificial Intelligence (AI) algorithms specifically designed to generate images from natural language descriptions (prompts). These models have demonstrated impressive capabilities in creating high-quality images from a wide range of inputs, making them powerful tools for non-technical users to tap into their creativity. The field is advancing rapidly and we are witnessing the emergence of an increasing number of tools, such as DALL-E, MidJourney and StableDiffusion, that are leveraging LTGMs to support creative work across various domains. However, there is a lack of research on how the interaction with these tools might affect the users{\textquoteright} creativity and their ability to control the generated outputs. In this paper, we investigate how the interaction with LTGMs-based tools might impact creativity by analyzing the feedback provided by groups of design students developing an architectural project with the help of LTGMs tools",

keywords = "AI-driven design process, Creativity, Generative AI, Human-AI",

author = "Tommaso Turchi and Silvio Carta and Luciano Ambrosini and Alessio Malizia",

note = "{\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. All rights are reserved by the Publisher.; 9th International Symposium on End User Development, IS-EUD 2023 ; Conference date: 06-06-2023 Through 08-06-2023",

year = "2023",

month = may,

day = "30",

doi = "10.1007/978-3-031-34433-6_3",

language = "English",

isbn = "978-3-031-34432-9",

series = "Lecture Notes in Computer Science (LNCS)",

publisher = "Springer Nature ",

pages = "35--51",

editor = "Spano, {Lucio Davide} and {Schmidt }, Albrecht and Carmen Santoro and {Stumpf }, Simone",

booktitle = "End-User Development",

address = "Netherlands",

url = "https://cg3hci.dmi.unica.it/iseud2023/index.html",

}

Turchi, T, Carta, S, Ambrosini, L & Malizia, A 2023, Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process. in LD Spano, A Schmidt , C Santoro & S Stumpf (eds), End-User Development: 9th International Symposium, IS-EUD 2023, Proceedings. Lecture Notes in Computer Science (LNCS), vol. 13917, Springer Nature , pp. 35-51, 9th International Symposium on End User Development, Cagliari, Italy, 6/06/23. https://doi.org/10.1007/978-3-031-34433-6_3

Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process. / Turchi, Tommaso; Carta, Silvio; Ambrosini, Luciano et al.
End-User Development: 9th International Symposium, IS-EUD 2023, Proceedings. ed. / Lucio Davide Spano; Albrecht Schmidt ; Carmen Santoro; Simone Stumpf . Springer Nature , 2023. p. 35-51 (Lecture Notes in Computer Science (LNCS); Vol. 13917).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process

AU - Turchi, Tommaso

AU - Carta, Silvio

AU - Ambrosini, Luciano

AU - Malizia, Alessio

N1 - Conference code: 9

PY - 2023/5/30

Y1 - 2023/5/30

N2 - Large-scale Text-to-image Generative Models (LTGMs) are a cutting-edge class of Artificial Intelligence (AI) algorithms specifically designed to generate images from natural language descriptions (prompts). These models have demonstrated impressive capabilities in creating high-quality images from a wide range of inputs, making them powerful tools for non-technical users to tap into their creativity. The field is advancing rapidly and we are witnessing the emergence of an increasing number of tools, such as DALL-E, MidJourney and StableDiffusion, that are leveraging LTGMs to support creative work across various domains. However, there is a lack of research on how the interaction with these tools might affect the users’ creativity and their ability to control the generated outputs. In this paper, we investigate how the interaction with LTGMs-based tools might impact creativity by analyzing the feedback provided by groups of design students developing an architectural project with the help of LTGMs tools

AB - Large-scale Text-to-image Generative Models (LTGMs) are a cutting-edge class of Artificial Intelligence (AI) algorithms specifically designed to generate images from natural language descriptions (prompts). These models have demonstrated impressive capabilities in creating high-quality images from a wide range of inputs, making them powerful tools for non-technical users to tap into their creativity. The field is advancing rapidly and we are witnessing the emergence of an increasing number of tools, such as DALL-E, MidJourney and StableDiffusion, that are leveraging LTGMs to support creative work across various domains. However, there is a lack of research on how the interaction with these tools might affect the users’ creativity and their ability to control the generated outputs. In this paper, we investigate how the interaction with LTGMs-based tools might impact creativity by analyzing the feedback provided by groups of design students developing an architectural project with the help of LTGMs tools

KW - AI-driven design process

KW - Creativity

KW - Generative AI

KW - Human-AI

UR - http://www.scopus.com/inward/record.url?scp=85173570210&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-34433-6_3

DO - 10.1007/978-3-031-34433-6_3

M3 - Conference contribution

SN - 978-3-031-34432-9

T3 - Lecture Notes in Computer Science (LNCS)

SP - 35

EP - 51

BT - End-User Development

A2 - Spano, Lucio Davide

A2 - Schmidt , Albrecht

A2 - Santoro, Carmen

A2 - Stumpf , Simone

PB - Springer Nature

T2 - 9th International Symposium on End User Development

Y2 - 6 June 2023 through 8 June 2023

ER -

Turchi T, Carta S, Ambrosini L, Malizia A. Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process. In Spano LD, Schmidt A, Santoro C, Stumpf S, editors, End-User Development: 9th International Symposium, IS-EUD 2023, Proceedings. Springer Nature . 2023. p. 35-51. (Lecture Notes in Computer Science (LNCS)). doi: 10.1007/978-3-031-34433-6_3

Human-AI Co-Creation: Evaluating the Impact of Large-scale Text-to-Image Generative Models on the Creative Process

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this