Open opy188 opened 1 year ago
I was getting this issue too after using --medvram-sdxl
. Was able to fix by running once with --reinstall-torch
(in addition to all my other arguments). Then closed, removed --reinstall-torch
, and could rerun without getting the error.
I was getting this issue too after using
--medvram-sdxl
. Was able to fix by running once with--reinstall-torch
(in addition to all my other arguments). Then closed, removed--reinstall-torch
, and could rerun without getting the error.
In what directory/folder you must run the command? /venv?
In what directory/folder you must run the command? /venv?
I just added the argument inside of the webui-user.bat
file (which is where I have all my other args), saved the file, ran it once, then removed the —reinstall-torch
argument.
Is there an existing issue for this?
What happened?
updated to the most recent version 1.6.0. Afterwards I was unable to start the UI without the program giving me a runtime error when it had to load the model.
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cpu and cuda:0! (when checking argument for argument index in method wrapper_CUDA__index_select)
Steps to reproduce the problem
Put --medvram in the commandline_args for any .bat you use to launch the webui
What should have happened?
it should have loaded
Sysinfo
sysinfo-2023-09-07-23-27.txt
What browsers do you use to access the UI ?
Mozilla Firefox
Console logs
Additional information
No response