这种报错是现存不足吗？

sanli

NansException: A tensor with all NaNs was produced in VAE. This could be because there's not enough precision to represent the picture. Try adding --no-half-vae commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.
Time taken: 28.22sTorch active/reserved: 3559/4724 MiB, Sys VRAM: 8188/8188 MiB (100.0%)
游戏本4060，不同的模型最多画到800*800f分辨率，高清修复也这样报错，这ai绘图这么迟吃现存吗？