这是半成品lora模型，使用超过150张高质量图片进行训练。训练图片全部来自该画师的原画，得到纯净的高田裕三风格LORA。碎碎念：这个画师的lora挺难炼的，不是说角色不像，而是细节太丰富，lora的细节模仿能力有点堪忧，需要增加更多的训练素材和细节打标，可能会有更好的效果，待收集到更多有用的素材会更新。推荐权重：0.8~1.5--- --- --- --- --- --- --- ---This is a semi-finished lora model, which is trained with more than 150 high-quality pictures.All the training pictures are from the original painting collection of the artist, so that the pure Artist style lora is obtained.Recommendation Weight：0.8~1.5

Files with SHA256: 002f7dda158a2a9a7f83b1daea9268ec05eb522e6753c56421156a70cb0d89a1