modules.devices.NansException: A tensor with 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.　のエラーの解決方法

概要

「Generate」を実行した際、以下のエラーが表示される場合があります

modules.devices.NansException: A tensor with 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.

解決方法

Web UIの

①「Settings」をクリック

②「Stable Diffusion」をクリック

③「Upcast cross attention layer to float32」にチェックを入れる

④最後に、「Apply settings」をクリックして保存します