Quoted By:
I finished training but apparently the lora is trash and only outputs garbage like pic related. I don't really know what's gone wrong here, since this is my first lora.
import network module: networks.lora
create LoRA network. base dim (rank): 128, alpha: 128.0
create LoRA for Text Encoder: 72 modules.
create LoRA for U-Net: 192 modules.
enable LoRA for text encoder
enable LoRA for U-Net
prepare optimizer, data loader etc.
use Lion optimizer | {}
override steps. steps for 6 epochs is / 指定エポックまでのステップ数: 6450
running training / 学習開始
num train images * repeats / 学習画像の数×繰り返し回数: 1075
num reg images / 正則化画像の数: 0
num batches per epoch / 1epochのバッチ数: 1075
num epochs / epoch数: 6
batch size per device / バッチサイズ: 1
gradient accumulation steps / 勾配を合計するステップ数 = 1
total optimization steps / 学習ステップ数: 6450
