在试着用一些模型跑图时，比如用dreamshaper 或者 deliberate 这样的模型跑图时，就会出现：
NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
用时:1.4 sec.
A: 2.69 GB, R: 2.81 GB, Sys: 3.8/8 GB (48.1%)
提示这种错误，但是切换到其他的模型，这种错误又没有了。
显卡是RTX3060
NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
用时:1.4 sec.
A: 2.69 GB, R: 2.81 GB, Sys: 3.8/8 GB (48.1%)
提示这种错误，但是切换到其他的模型，这种错误又没有了。
显卡是RTX3060
