bchalk V1

LoRA Use Base Model Illustrious xl v2.0 Base Trigger words butterchalk_style Image Processing Parameters Repeat 22 Epoch 9 Save Every N Epochs 1 Training Parameters Seed - Clip Skip - Text Encoder learning rate 0.00001 Unet learning rate 0.0005 LR Scheduler cosine_with_restarts Optimizer AdamW8bit Network Dim 16 Network Alpha 8 Gradient Accumulation Steps - Label Parameters Shuffle caption true Keep n tokens 1 Advanced Parameters Noise offset 0.03 Multires noise discount 0.1 Multires noise iterations 10 conv_dim - conv_alpha - Batch Size 2