UpdatedUsed PonyXL to train this one. Updated dataset to achieve better performance. It enhanced this concept on PonyXL and related models.With PonyXL many concepts can be easily generated. So I will focus on the weak concept in PonyXL. Concept like hyper_futanari that can easily generated with Pony model will not updated to XL version.Strength 0.8 recommended.IntroductionThis is the subLyCORIS of hyperfuta | Stable Diffusion LORA | CivitaiUse this to generate futanari with larger glan. It can be used alone. But it seems a little overbaked.How to use itI recommand using it in weight 0.6-0.7 or lower combined with hyperfuta LyCORIS.Not enough tests for other tags. It seemsworks well.Training details:Traingset is of about 130 images. They are mirrored before training. Total steps are about 5500.Regularization = falseresolution=768batch_size=1epoch=10network_dim=32network_alpha=32clip_skip=2Using AdamW8bits as optimizer:lr="1e-4"unet_lr="1e-4"text_encoder_lr="1e-5"Locon parameters:conv_dim=4conv_alpha=4
