EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stable Diffusion Models Reveal a Persisting Human–AI Gap in Visual Creativity

Silvia Rondini iD, Claudia Alvarez-Martin iD, Paula Angermair-Barkai, Olivier Penacchio, Marc Paz, Matthew Pelowski, Dan Dediu, Antoni Rodriguez-Fornells, Xim Cerda-Company iD

Advanced Science · 2026-05 · 13 (27)

DOI: 10.1002/advs.202524142 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 24.03.2026. Verfasst von Silvia Rondini und 8 weiteren Autor:innen. Beteiligte Einrichtung: Cognition and Brain Plasticity Unit, Bellvitge Biomedical Research Institute, L'Hospitalet De Llobregat, Spain. Hauptthemen laut MEDLINE: Creativity, Artificial Intelligence. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MICIU/AEI/10.13039/501100011033, Ministerio de Asuntos Económicos y Transformación Digital, Agència de Gestió d'Ajuts Universitaris i de Recerca.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

While recent research suggests Large Language Models match human creative performance in divergent thinking tasks, visual creativity remains underexplored. This study compared image generation in human participants (Visual Artists and Non‐Artists) and using an image‐generation AI model (two prompting conditions with varying human input: high for Human‐Inspired, low for Self‐Guided). The creativity of the resulting images was evaluated by human raters (N = 255) and GPT‐4o acting as an AI rater under two conditions: strictly mirroring the human rating task and using in‐context learning with human‐rated examples as guidance. We observed a clear creativity gradient: Visual Artists > Non‐Artists ≥ Human‐Inspired GenAI > Self‐Guided GenAI. Increased human guidance strongly improved GenAI's creative output, bringing its productions close to those of Non‐Artists. Moreover, while Guided‐GPT‐4o more closely approximated human creativity judgment patterns, baseline GPT‐4o (without guidance) exhibited markedly different creativity evaluations, showing reduced discrimination between image categories and inflated scores for GenAI outputs. These results suggest that, in contrast to language‐centered tasks, GenAI models may face unique challenges in visual domains, where creativity depends on perceptual nuance and contextual sensitivity, distinctly human capacities that may not be readily transferable from language models.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CreativityArtificial IntelligenceHumansGenerative Artificial IntelligenceFemaleLarge Language ModelsMaleAdultYoung Adult

Stichwörter der Autor:innen

creativitygenerative AIstable diffusion

Autor:innen und Institutionen

  • Cognition and Brain Plasticity Unit, Bellvitge Biomedical Research Institute, L'Hospitalet De Llobregat, Spain.
  • Bridging Research in AI and Neuroscience, Computer Vision Center, Bellaterra, Spain.
  • Department of Cognition, Development and Educational Psychology, University of Barcelona, Barcelona, Spain.
  • Vienna Cognitive Science Hub, Vienna, Austria.
  • Faculty of Psychology, University of Vienna, Vienna, Austria.
  • Computer Science Department, Universitat Autonoma de Barcelona, Bellaterra, Spain.

ORCID-Profile: Silvia Rondini, Claudia Alvarez-Martin, Xim Cerda-Company

Förderung

  • MICIU/AEI/10.13039/501100011033
  • Ministerio de Asuntos Económicos y Transformación Digital
  • Agència de Gestió d'Ajuts Universitaris i de Recerca
  • H2020 Marie Skłodowska-Curie Actions
  • HORIZON-MSCA-2023-CITIZENS-01

Zitieren

APA

Rondini, S., Alvarez-Martin, C., Angermair-Barkai, P., Penacchio, O., Paz, M., Pelowski, M., Dediu, D., Rodriguez-Fornells, A., & Cerda-Company, X. (2026). Stable Diffusion Models Reveal a Persisting Human–AI Gap in Visual Creativity. Advanced Science, 13(27). https://doi.org/10.1002/advs.202524142

Vancouver

Rondini S, Alvarez-Martin C, Angermair-Barkai P, Penacchio O, Paz M, Pelowski M, et al. Stable Diffusion Models Reveal a Persisting Human–AI Gap in Visual Creativity. Advanced Science. 2026;13(27). doi:10.1002/advs.202524142

BibTeX
@article{Rondini2026,
  author = {Rondini, Silvia and Alvarez-Martin, Claudia and Angermair-Barkai, Paula and Penacchio, Olivier and Paz, Marc and Pelowski, Matthew and Dediu, Dan and Rodriguez-Fornells, Antoni and Cerda-Company, Xim},
  title = {Stable Diffusion Models Reveal a Persisting Human–AI Gap in Visual Creativity},
  journal = {Advanced Science},
  year = {2026},
  volume = {13},
  number = {27},
  doi = {10.1002/advs.202524142}
}
Kostenlos starten →