Ok, i've activated venv in auto1111 folder, then installed latest pytorch with cuda and it worked. It was telling me I don't have torchvision before this.

[barleyj21]

I've installed fresh automatic1111 first, then followed TingTingin instructions from another issue here:

"go to the folder you have automatic1111 install (the stable diffusion folder) type cmd in the address bar (where the file path is) then enter this will open cmd in the current folder then type venv\scripts\activate (this will activate the virtual environment where SD is Installed)"

Then installed latest pytorch from with this line:

pip3 install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/cu118

And then started TikTokDiffusion.bat

Now it's working