Chris Ward

Confirmed fixed using `:nvidia-full` instead of `:cuda` ???

+1

https://github.com/pawelmalak/snippet-box/issues/34 Spotted this issue - could be because I'm using named volumes

@emileswain dude! long time!!! I'm giving this a go today - a lot to be desired from docs of this repo... fun fun

Fighting CSP has been the bane of my career and this issue has defeated me. Seppuku time lol

How did it go in the end?

any joy?

Downgraded venv to 3.8, upgraded pip - same error Found this - https://discuss.pytorch.org/t/pytorch-pip-installation-not-working/134884/3

okay, figured it out and started training.... https://github.com/JoePenna/Dreambooth-Stable-Diffusion/issues/96#issuecomment-1296292055 ``` pip install torch==1.12.1+cu116 -f https://download.pytorch.org/whl/torch_stable.html ```

You need to set up the regularization images also; ``` git clone https://github.com/djbielejeski/Stable-Diffusion-Regularization-Images-person_ddim mkdir -p regularization_images/person_ddim mv -v Stable-Diffusion-Regularization-Images-person_ddim/person_ddim/*.* regularization_images/person_ddim ```