大家好我是bilibili的【陈二哈是个技术宅】<a target="_blank" rel="ugc" href="https://space.bilibili.com/1895182543?spm_id_from=333.1007.0.0">https://space.bilibili.com/1895182543?spm_id_from=333.1007.0.0</a>这是一个水墨画的画风类lora模型，训练素材弓27张，全部由AI产出，训练步数约2800步。我已经做好了分层调试，加载即用，无需触发词，无需调整权重。可以兼容其他的角色类lora，同时对原始的提示词不会造成太大的影响。推荐使用anything等二次元模型。不推荐和写实类的模型搭配使用。===========================================================Hi，guys，I am Erha Chen.This is a lora model in the style of an ink painting, trained with 27 images all produced by AI, about 2800 steps in training. I have already prepared the layered debugging, it’s plug-and-play, with no need for trigger words or weight adjustments. It can be compatible with other character lora as well, and it won’t cause too much impact on the original prompts. I recommend using models :anything . I do not recommend using it in conjunction with realistic models.

Files with SHA256: 3085d066731d8febefcacfbf575e92f9cc5f2f9911aca8e3e34760fcfa4d88a5