hey /vtai/ sorry to bug you but I need some help. I was fucking around with stable diffusion two months ago but never really got into it because my oshi didn't have a lora. she does now so i'm trying to get back into it but I keep running into problems. I did a fresh reinstall of the software based on
https://github.com/AUTOMATIC1111/stable-diffusion-webui/wiki/Install-and-Run-on-NVidia-GPUs and made sure all my drivers were up to date but every time I try to generate an image I get this 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.I tried enabling the setting it recommend but it still did not work, but as a tech illiterate man I do not know what it means by "using the --no-half commandline argument to fix this" I tried asking in my home thread to see if they could give me some answers but nobody knew how to help so they told me to come here. i'm sorry if this post is retarded, I have basically no idea what i'm doing.
