我下了有那么些chat point，再有那么几个ckpt跑320×320、一个girl的图，一跑就给我报错半精度32的错，其他的ckpt都没问题。
按照他提示的设置了下，还把我系统给整几回蓝屏
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.
Time taken: 2.59sTorch active/reserved: 1688/1762 MiB, Sys VRAM: 3240/6144 MiB (52.73%)
就是这图片的几个ckpt
这是怎么回事儿呢？
按照他提示的设置了下，还把我系统给整几回蓝屏
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.
Time taken: 2.59sTorch active/reserved: 1688/1762 MiB, Sys VRAM: 3240/6144 MiB (52.73%)
就是这图片的几个ckpt
这是怎么回事儿呢？
