Kaggle Train with 2 GPUs

So because I'm broke, I use Kaggle with anything to do with AIs. When I heard of Stable Diffusion, I used this Repo for training. Recently I got the text to image working, and then the image to image working. But I'm trying to get their T4 GPUs to Train, which combined, has a total of 30 GB of memory. The current problem is that mpiexec is not recognizing there is 2 GPUs and also what is the bare minimum requirements for training?