Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding

We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and ev...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2024-05
Hauptverfasser:	Li, Zhimin, Zhang, Jianwei, Lin, Qin, Xiong, Jiangfeng, Long, Yanxin, Deng, Xinchi, Zhang, Yingfang, Liu, Xingchao, Huang, Minbin, Xiao, Zedong, Chen, Dayou, He, Jiajun, Li, Jiahao, Li, Wenyue, Zhang, Chen, Quan, Rongwei, Lu, Jianxiang, Huang, Jiabin, Yuan, Xiaoyan, Zheng, Xiaoxiao, Li, Yixuan, Zhang, Jihong, Zhang, Chao, Chen, Meng, Liu, Jie, Zheng, Fang, Wang, Weiyan, Xue, Jinbao, Yangyu Tao, Zhu, Jianchen, Liu, Kai, Lin, Sihuan, Sun, Yifu, Li, Yun, Wang, Dongdong, Chen, Mingtao, Hu, Zhichao, Xiao, Xiao, Chen, Yan, Liu, Yuhong, Liu, Wei, Wang, Di, Yang, Yong, Jiang, Jie, Lu, Qinglin
Format:	Artikel
Sprache:	eng
Schlagworte:	Image processing Large language models Source code Transformers
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!