<h3>I'm sorry, please be careful as the file size is very large</h3>This model was trained by using 1913 random sampled images. I'm looking for examples and information on LoRA learning with large datasets. Please contact us.

Uruha rushia - 潤羽るしあ

# Training summaryThis model was trained by using 1913 random sampled images for 10 epochs, with 10 iterations per epoch.The following is an excerpt of some of the learning commands by sd-script for reference<pre><code>train_network.py --pretrained_model_name_or_path="JosephusCheung/ACertainty" --prior_loss_weight=1.0 --enable_bucket --min_bucket_reso=384 --max_bucket_reso=1280 --train_batch_size=12 --learning_rate=1e-4 --text_encoder_lr 5e-5 --use_8bit_adam --xformers --mixed_precision=fp16 --save_every_n_epochs=10 --save_model_as=safetensors --clip_skip=2 --seed=42 --color_aug --flip_aug --network_module=networks.lora --resolution=768,512 --network_dim 256 --max_train_epochs 4 --shuffle_caption</code></pre>

Files with SHA256: a9613b429dff317e9a797a49ac42c636d4c414d30f0546e437103681ffac2845