# Training summary

This model was trained by using 40 manually sampled images for 10 epochs, with 100 iterations per epoch.

The following is an excerpt of some of the learning commands by sd-script for reference

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

# Problems
This model is a bit overfitted, but it works comfortably with an intensity of around 0.5-0.7 depending on the model.
I'm looking for information about optimal parameter information for character learning with LoRA. Also, if you have a request for a LoRA model using large-scale data, please contact us. The challenge now is to acquire that know-how.