Repository logo

Infoscience

  • English
  • French
Log In
Logo EPFL, École polytechnique fédérale de Lausanne

Infoscience

  • English
  • French
Log In
  1. Home
  2. Academic and Research Output
  3. Conferences, Workshops, Symposiums, and Seminars
  4. Diffusion in Style
 
conference paper

Diffusion in Style

Everaert, Martin Nicolas  
•
Bocchio, Marco
•
Arpa, Sami  
Show more
October 2023
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV23)
IEEE/CVF International Conference on Computer Vision (ICCV23)

We present Diffusion in Style, a simple method to adapt Stable Diffusion to any desired style, using only a small set of target images. It is based on the key observation that the style of the images generated by Stable Diffusion is tied to the initial latent tensor. Not adapting this initial latent tensor to the style makes fine-tuning slow, expensive, and impractical, especially when only a few target style images are available. In contrast, fine-tuning is much easier if this initial latent tensor is also adapted. Our Diffusion in Style is orders of magnitude more sample-efficient and faster. It also generates more pleasing images than existing approaches, as shown qualitatively and with quantitative comparisons.

  • Files
  • Details
  • Metrics
Type
conference paper
DOI
10.1109/ICCV51070.2023.00214
Web of Science ID

WOS:001159644302048

Author(s)
Everaert, Martin Nicolas  
Bocchio, Marco
Arpa, Sami  
Süsstrunk, Sabine  
Achanta, Radhakrishna  
Date Issued

2023-10

Published in
Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV23)
ISBN of the book

979-8-3503-0718-4

Total of pages

11

Start page

2251

End page

2261

URL
https://openaccess.thecvf.com/content/ICCV2023/html/Everaert_Diffusion_in_Style_ICCV_2023_paper.html
https://ivrl.github.io/diffusion-in-style/
Editorial or Peer reviewed

REVIEWED

Written at

EPFL

EPFL units
IVRL  
Event nameEvent placeEvent date
IEEE/CVF International Conference on Computer Vision (ICCV23)

Paris, France

October 2-6, 2023

Available on Infoscience
December 13, 2023
Use this identifier to reference this record
https://infoscience.epfl.ch/handle/20.500.14299/202605
Logo EPFL, École polytechnique fédérale de Lausanne
  • Contact
  • infoscience@epfl.ch

  • Follow us on Facebook
  • Follow us on Instagram
  • Follow us on LinkedIn
  • Follow us on X
  • Follow us on Youtube
AccessibilityLegal noticePrivacy policyCookie settingsEnd User AgreementGet helpFeedback

Infoscience is a service managed and provided by the Library and IT Services of EPFL. © EPFL, tous droits réservés