RuntimeError: CUDA error: invalid device ordinal CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. about difface HOT 2 OPEN

I have updated the code. Please have a try:
CUDA_VISIBLE_DEVICES=0,1,2,3 torchrun --standalone --nproc_per_node=4 --nnodes=1 main_diffusion.py --cfg_path configs/training/diffusion_ffhq512.yaml --save_dir yourfolder

I suggest you firstly train the model using one GPU, and then turn to the distributed training.

from difface.

Thank you for your timely reply. I have used single GPU for training and successfully, I will try your new code right now.

from difface.