Note:
This is a LoHa model, and you need to install a1111-sd-webui-locon extension to use this model.
And don't use sd-webui-additional-networks to load this model.
Place the model in the path '.\stable-diffusion-webui\models\Lora' to use it.
Suggest weight: around 1.
Suggest CFG scale:1.5-4
Trained on 1,300 painting images by Claude Monet.
I once used native training to make it, but the results didn't seem as good as LyCORIS.
It is not guaranteed to work well with other LoRA , The art style may not affect the LoRa characters.(If that's what you want) .It is recommended to increase the weight and use low CFG scale.
Based on novel-anime-full model.
Description
Optimized hyperparameters and removed the training text encoder. Theoretically, this should result in better performance. Originally, I intended to include some regularization images to aid in training, but the effect was not satisfactory.