Taming Transformers for High-Resolution Image Synthesis驯服 Transformer 用于高分辨率图像合成Patrick Esser* Robin Rombach* Björn Ommer Heidelberg Collaboratory for Image Processing, IWR, Heidelberg University, Germany *Both authors contributed equally to this workPatrick Esser* Robin Rombach* Björn Ommer 海德堡图像处理协作实验室，IWR，德国海德堡大学*两位作者对本工作贡献相同Figure 1: Figure 1. Our approach enables transformers to synthesize high-resolution images like this one, which contains 1280x460 pixels.图1：图1。我们的方法使 Transformer 能够合成像这样包含1280x460 像素的高分辨率图像。Abstract摘要Des