Hi, Shawn. When I processed to 3:01, I got an error "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."
Then I enter a command "./webui.sh --no-half --disable-nan-check" in the terminal. Clicked "Generate" btn and got another error"RuntimeError: MPS backend out of memory (MPS allocated: 15.42 GB, other allocations: 2.48 GB, max allowed: 18.13 GB). Tried to allocate 512.00 MB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure)." My mac is mini M1, 16G Memory, MacOSsonoma 14.1.1. Did I miss anything?
Hi, Shawn. When I processed to 3:01, I got an error "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."
Then I enter a command "./webui.sh --no-half --disable-nan-check" in the terminal. Clicked "Generate" btn and got another error"RuntimeError: MPS backend out of memory (MPS allocated: 15.42 GB, other allocations: 2.48 GB, max allowed: 18.13 GB). Tried to allocate 512.00 MB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure)."
My mac is mini M1, 16G Memory, MacOSsonoma 14.1.1. Did I miss anything?