出现错误ValueError: Query/Key/Value should all have the same dtype query.dtype: torch.float32 key.dtype : torch.float32 value.dtype: torch.float16
#242
by
qiuchen123
- opened
我在云端生成图像，套用一个模型进去，但出现问题： 没打勾之前是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. 打钩之后是ValueError: Query/Key/Value should all have the same dtype query.dtype: torch.float32 key.dtype : torch.float32 value.dtype: torch.float16 找不到解决办法，求指点
同问