no code implementations • 15 Apr 2024 • Mude Hui, Siwei Yang, Bingchen Zhao, Yichun Shi, Heng Wang, Peng Wang, Yuyin Zhou, Cihang Xie
This study introduces HQ-Edit, a high-quality instruction-based image editing dataset with around 200, 000 edits.
1 code implementation • 16 Mar 2024 • Mude Hui, Zihao Wei, Hongru Zhu, Fei Xia, Yuyin Zhou
This strategy enriches the diffusion process with structured 3D information, enhancing detail and reducing noise in localized 2D images.
no code implementations • CVPR 2023 • Mude Hui, Zhizheng Zhang, Xiaoyi Zhang, Wenxuan Xie, Yuwang Wang, Yan Lu
Since different attributes have their individual semantics and characteristics, we propose to decouple the diffusion processes for them to improve the diversity of training samples and learn the reverse process jointly to exploit global-scope contexts for facilitating generation.