All scripts and entire research and development process shared at below link
https://www.patreon.com/posts/kohya-flux-lora-110293257
10 GB, 16 GB, 24 GB and 48 GB GPU configs added - 10 GB config is like 3x to 5x slower sadly
Massed Compute, RunPod and Windows Kohya SS GUI LoRA installers added to the zip file
Testing new 16 GB FLUX LoRA training config and new way of regularization images. Moreover testing Apply T5 Attention Mask too. Lets see if Kohya FLUX LoRA workflow will become even better or not