bmaltais
bmaltais
@diazona Glad it is working. You can always check authenticity by checking digital signature on the application. I hope making the source code available will inspire others to improve the...
Short answer... I don't really use a python debug mode... I just run the command through the GUI and look at any tracefiles... If you run them outside the GUI...
Hi, I should have said `traceback` output when something crash while running the python code. This is usually what I go by to track the source of the issue. I...
Hummm... look like an issue I might have introduced... let me look at it...
OK, I have fixed it. The fix is in the `dev` branch until I merge changes into a new release.
I am not too sure what is going on... but I have added some code to the function to validate if the folder where the config file would be save...
Not sure what is the source. Can you share the json config file for it so I can try to reproduce the issue?
 Look like you forgor to select SDXL as your model type... Make sure you select SDXL whern you train an SDXL LoRA,
Have you tested with my test file in the test/config folder? Does it work with it? It does on my system. Load the finetuning config file and try to train...
This is strange. I will try to test things again today in case I can find something.