Skip to search boxSkip to navigationSkip to main content

CanFuUI: a Canvas-centric web user interface for iterative image generation with diffusion models and ControlNet

  • Qihan Hu
    ,
  • Zhenghui Xu
    ,
  • Peng Du
    ,
  • Hao Zeng
    ,
  • Tongqing Ma
    ,
  • Youbing Zhao
  • Communication University of Zhejiang
    ,
  • Uber Technologies, Inc.
    ,
  • Jiangsu Dongyin Intelligent Engineering Technology Research Institute
    ,
  • Jiangsu CRRC Digital Technology Co. Ltd.
Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Abstract

Today, various AI generation tools are emerging in succession. And the majority of existing tools are predominantly model-centric in design, resulting in steep learning curves and high usability thresholds for users. Moreover, current user interfaces lack built-in image editing capabilities, forcing users to rely on external software even for basic image editing tasks. Considering that most image generation is an iterative process, this limitation significantly hampers user experience and creative potential. Instead, this paper proposes a novel canvas-centric design that seamlessly integrates editing functionalities into the UI called CanFuUI, streamlining secondary image processing. Users can crop, modify, and annotation of specific regions of generated images within the same canvas in CanFuUI. Furthermore, canvas content is utilized as preprocessed images, directly integrated into the ControlNet preprocessing procedure, reinforcing the customization capabilities of AI-generated outputs.

Publication Information

Output type

Research Output: Chapter in Book/Report/Conference proceeding Conference contribution Peer-review

Original language

English

Pages from-to (Number of pages)

Pages 128-138 (11 pages)

Publication milestones

  • Published - 02/11/2023

Publication status

Published - 02/11/2023

Publisher

Springer, Japan, India, Australia, Germany, United States, United Arab Emirates, Austria, Switzerland, Italy, China, United Kingdom, Netherlands, Brazil, France, Singapore

Publication series

  • Publication series name: Communications in Computer and Information Science
    ISSN (Print): 1865-0929
    ISSN (Electronic): 1865-0937
    Volume: 1946 CCIS

ISBN (Print)

9789819975860

ISBN (Electronic)

9789819975877

External Publication IDs

  • handle.net: 10547/626111
  • Scopus: 85177199228

Host publication title

AI-generated Content - 1st International Conference, AIGC 2023, Revised Selected Papers

Host publication editors

  • Feng Zhao
  • Duoqian Miao

Access to documents

Publication metrics

Metrics

PlumX, opens in new tab

Captures
4
3
Mentions
3