Not recommended for realistic model
Main tag : mtu virus, Secondary tag : from below, multiple views, LoRA str : 1.0-1.2 Prompt str : 1.0-1.2 Denoising str : 0.25 to 0.40 [if use upscale by 2+ reduce step]
Training Powershell info :
DIM/Alpha : 16/8
Train batch size : 3
resolution : 768
mix/save_precision = BF16
optimizer_type = AdamW
GPU : RTX 4060 16GB 160W
Torch 2.3 + cu12.1 + Xformers + gradient_checkpointing
Vram used : 11.3GB
Speed : 1.96sec/it
Weight
UNet weight average strength: 0.007730846
Text Encoder (1) weight average strength: 0.0064005
Text Encoder (2) weight average strength: 0.0059844