---
_id: '60847'
abstract:
- lang: eng
  text: "With the rise of multimodal AI tools, such as DALL-E, Midjourney, or Stable\r\nDiffusion,
    it has never been easier and faster to produce compelling fashion\r\nimages. While
    the proliferation of AI-generated fashion images can be\r\nseen as the ultimate
    triumph of the fashion image over both fashion text\r\nand fashionable garments,
    this paper critically examines how these images\r\nare produced, what exactly
    they show, and ultimately, how this impacts our\r\nunderstanding of fashion. Building
    on current research on multimodal AI,\r\nspecifically text-to-image models, I
    argue that AI-generated fashion images\r\nare produced through textual means,
    that is, through “operative ekphrasis”\r\n(Bajohr 2024: 83). This means that the
    generation of fashion images created\r\nvia multimodal AI is based on textual
    prompts that extract statistically\r\nprobable images from a latent space, which,
    in turn, is the result of previously\r\nindexed and labeled image-text pairs.
    Because the indexing of images\r\nrequires a reduction of complexity, images generated
    through multimodal\r\nAI are often generic. In the case of fashion images, this
    is reflected in the lack\r\nof texture and the reproduction of fashion photography’s
    conventions. As\r\nfashion photography is not necessarily a representation of
    ‘the world’ or even\r\nfashionable garments, it resembles AI-generated images
    more than other photographic\r\ngenres. AI-generated fashion images are then not
    images of fashionable\r\ngarments, but images about fashion images—a statistically
    probable permutation\r\nof fashion photographs from the past (cf. Meyer 2023:
    108). As such,\r\nAI-generated fashion images are not only the product of a mediated
    collective\r\nimaginary but also feed back into it. The view on fashion shaped
    by AI-generated\r\nfashion images is then based on reduction and stylized normativity."
article_type: original
author:
- first_name: Charlotte
  full_name: Brachtendorf, Charlotte
  id: '95414'
  last_name: Brachtendorf
  orcid: 0000-0001-5739-933X
citation:
  ama: 'Brachtendorf C. Possible Fashion Images: Operative Ekphrasis and the Reduction
    of Fashion Through Multimodal AI. <i>Image: The Interdisciplinary Journal of Image
    Sciences</i>. 2025;42(2):155-168. doi:<a href="https://doi.org/10.1453/1614-0885-2-2025-16663">10.1453/1614-0885-2-2025-16663</a>'
  apa: 'Brachtendorf, C. (2025). Possible Fashion Images: Operative Ekphrasis and
    the Reduction of Fashion Through Multimodal AI. <i>Image: The Interdisciplinary
    Journal of Image Sciences</i>, <i>42</i>(2), 155–168. <a href="https://doi.org/10.1453/1614-0885-2-2025-16663">https://doi.org/10.1453/1614-0885-2-2025-16663</a>'
  bibtex: '@article{Brachtendorf_2025, title={Possible Fashion Images: Operative Ekphrasis
    and the Reduction of Fashion Through Multimodal AI}, volume={42}, DOI={<a href="https://doi.org/10.1453/1614-0885-2-2025-16663">10.1453/1614-0885-2-2025-16663</a>},
    number={2}, journal={Image: The Interdisciplinary Journal of Image Sciences},
    author={Brachtendorf, Charlotte}, year={2025}, pages={155–168} }'
  chicago: 'Brachtendorf, Charlotte. “Possible Fashion Images: Operative Ekphrasis
    and the Reduction of Fashion Through Multimodal AI.” <i>Image: The Interdisciplinary
    Journal of Image Sciences</i> 42, no. 2 (2025): 155–68. <a href="https://doi.org/10.1453/1614-0885-2-2025-16663">https://doi.org/10.1453/1614-0885-2-2025-16663</a>.'
  ieee: 'C. Brachtendorf, “Possible Fashion Images: Operative Ekphrasis and the Reduction
    of Fashion Through Multimodal AI,” <i>Image: The Interdisciplinary Journal of
    Image Sciences</i>, vol. 42, no. 2, pp. 155–168, 2025, doi: <a href="https://doi.org/10.1453/1614-0885-2-2025-16663">10.1453/1614-0885-2-2025-16663</a>.'
  mla: 'Brachtendorf, Charlotte. “Possible Fashion Images: Operative Ekphrasis and
    the Reduction of Fashion Through Multimodal AI.” <i>Image: The Interdisciplinary
    Journal of Image Sciences</i>, vol. 42, no. 2, 2025, pp. 155–68, doi:<a href="https://doi.org/10.1453/1614-0885-2-2025-16663">10.1453/1614-0885-2-2025-16663</a>.'
  short: 'C. Brachtendorf, Image: The Interdisciplinary Journal of Image Sciences
    42 (2025) 155–168.'
date_created: 2025-07-31T12:24:29Z
date_updated: 2025-11-15T19:35:14Z
ddc:
- '770'
doi: 10.1453/1614-0885-2-2025-16663
file:
- access_level: closed
  content_type: application/pdf
  creator: chbr8
  date_created: 2025-11-15T19:31:45Z
  date_updated: 2025-11-15T19:31:45Z
  file_id: '62210'
  file_name: 10.14531614-0885-2-2025-16663.pdf
  file_size: 982100
  relation: main_file
  success: 1
file_date_updated: 2025-11-15T19:31:45Z
has_accepted_license: '1'
intvolume: '        42'
issue: '2'
language:
- iso: eng
main_file_link:
- open_access: '1'
  url: https://image-journal.de/possible-fashion-images-operative-ekphrasis-and-the-reduction-of-fashion-through-multimodal-ai/
oa: '1'
page: 155-168
publication: 'Image: The Interdisciplinary Journal of Image Sciences'
publication_identifier:
  issn:
  - 1614-0885
publication_status: published
quality_controlled: '1'
status: public
title: 'Possible Fashion Images: Operative Ekphrasis and the Reduction of Fashion
  Through Multimodal AI'
type: journal_article
user_id: '95414'
volume: 42
year: '2025'
...