TY - GEN
T1 - CanFuUI
T2 - International Conference on AI-generated Content, AIGC 2023
AU - Hu, Qihan
AU - Xu, Zhenghui
AU - Du, Peng
AU - Zeng, Hao
AU - Ma, Tongqing
AU - Zhao, Youbing
AU - Xie, Hao
AU - Zhang, Peng
AU - Liu, Shuting
AU - Zang, Tongnian
AU - Wang, Xuemei
N1 - Publisher Copyright:
© 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
PY - 2023/11/2
Y1 - 2023/11/2
N2 - 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.
AB - 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.
KW - Canvas-Centric UI
KW - ComfyUI
KW - Diffusion Models
KW - WebUI
UR - https://www.scopus.com/pages/publications/85177199228
U2 - 10.1007/978-981-99-7587-7_11
DO - 10.1007/978-981-99-7587-7_11
M3 - Conference contribution
SN - 9789819975860
T3 - Communications in Computer and Information Science
SP - 128
EP - 138
BT - AI-generated Content - 1st International Conference, AIGC 2023, Revised Selected Papers
A2 - Zhao, Feng
A2 - Miao, Duoqian
PB - Springer
Y2 - 25 August 2023 through 26 August 2023
ER -