How to run it on non-default GPU or multiple GPUs?

[coolbunnyx]

The code can only run on the default GPU:0. Exceptions occur when device is switched to the non-default one.

os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID" os.environ["CUDA_VISIBLE_DEVICES"] = "2"

Exception has occurred: AttributeError 'str' object has no attribute 'traceback'

The above exception was the direct cause of the following exception:

File "RPG-DiffusionMaster-main/modules/errors.py", line 98, in run code() File "RPG-DiffusionMaster-main/modules/devices.py", line 76, in enable_tf32 device_id = (int(shared.cmd_opts.device_id) if shared.cmd_opts.device_id is not None and shared.cmd_opts.device_id.isdigit() else 0) or torch.cuda.current_device()

During handling of the above exception, another exception occurred:

File "RPG-DiffusionMaster-main/modules/errors.py", line 68, in display te = traceback.TracebackException.from_exception(e) File "RPG-DiffusionMaster-main/modules/errors.py", line 100, in run display(task, e) File "RPG-DiffusionMaster-main/modules/devices.py", line 84, in errors.run(enable_tf32, "Enabling TF32") File "RPG-DiffusionMaster-main/modules/interrogate.py", line 13, in from modules import devices, paths, shared, lowvram, modelloader, errors File "RPG-DiffusionMaster-main/modules/shared_options.py", line 7, in from modules import interrogate File "RPG-DiffusionMaster-main/RPG.py", line 22, in initialize from modules import options, shared_options File "RPG-DiffusionMaster-main/RPG.py", line 256, in initialize(model_name='albedobaseXL_v20.safetensors')