When using this LoRA, it may be a better image to redraw only face or eyes using inpaint.Or, it is recommended to reduce the Weight of LoRA.base model: <a target="_blank" rel="ugc" href="https://huggingface.co/syaimu/7th_test">7th_anime_3.1_Cg</a>

Empty Eyes LoRA / Utsurome / Hypnotic Suggestion

v3 has improved image quality compared to v2.The data set used for training was changed.training dataset: <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/xenon3134-mc/empty-eyes-dataset/tree/main/empty_eyes">empty-eyes-dataset</a>

Files with SHA256: ad6a6f9bbf91a5c120db5f2a5b66525c5c47741e3172f98d16f35af71ed2da77