PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation.

Junsong Chen Chongjian Ge Enze Xie Yue Wu 0002 Lewei Yao Xiaozhe Ren Zhongdao Wang Ping Luo 0002 Huchuan Lu Zhenguo Li PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation. 2024 abs/2403.04692 CoRR https://doi.org/10.48550/arXiv.2403.04692 db/journals/corr/corr2403.html#abs-2403-04692