Originally this was about my CPU Text encoder issue but I resolved that one below. The other questions are still relevant though! It just runs on a single thread whereas in the inference script it ...
I got v25.2.1. Checked 2 tutorials to set up lora training, kinda followed both. Executing command: Z:\ComfyUI\kohya_ss\.venv\Scripts\accelerate.EXE launch --dynamo_backend no --dynamo_mode default ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback