Version 1
: Received: 15 December 2023 / Approved: 18 December 2023 / Online: 19 December 2023 (09:22:12 CET)
How to cite:
Ou, Y.; Xu, J. WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design. Preprints2023, 2023121380. https://doi.org/10.20944/preprints202312.1380.v1
Ou, Y.; Xu, J. WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design. Preprints 2023, 2023121380. https://doi.org/10.20944/preprints202312.1380.v1
Ou, Y.; Xu, J. WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design. Preprints2023, 2023121380. https://doi.org/10.20944/preprints202312.1380.v1
APA Style
Ou, Y., & Xu, J. (2023). WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design. Preprints. https://doi.org/10.20944/preprints202312.1380.v1
Chicago/Turabian Style
Ou, Y. and Jingjun Xu. 2023 "WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design" Preprints. https://doi.org/10.20944/preprints202312.1380.v1
Abstract
People are drawn to woodcut-style designs due to their striking visual impact and strong contrast. However, traditional woodcut prints and previous computer-aided methods have not addressed the issues of dwindling design inspiration, lengthy production times, and complex adjustment procedures. We propose a novel network framework, the Woodcut-style Design Assistant Network (WDANet), to tackle these challenges. Notably, our research is the first to utilize diffusion models to streamline the woodcut-style design process. We've curated the Woodcut-62 dataset, featuring works from 62 renowned historical artists, to train WDANet in absorbing and learning the aesthetic nuances of woodcut prints, offering users a wealth of design references. Based on a noise reduction network, our dual cross-attention mechanism effectively integrates text and woodcut-style image features. This allows users to input or slightly modify a text description to quickly generate accurate, high-quality woodcut-style designs, saving time and offering flexibility. As confirmed by user studies, quantitative and qualitative analyses show that WDANet outperforms the current state-of-the-art in generating woodcut-style images and proves its value as a design aid.
Keywords
woodcut-style design; diffusion model; computer-aided design; text-to-image model
Subject
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.