잘되다가 갑자기 안되길래 에러 로그 이렇게뜸.

modules.devices.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. 

시키는대로 설정이랑 --no-half 도 추가해줌.

그런데 안됨.

아 좆됐나 싶다가 누가 모델 관련 댓글이라고 쓴거 봤음.

모델 다른거 로딩했다가 다시 원래꺼 로딩하니까 잘됨

???