【Lora训练及场景】
根据方块世界的角色及风格为训练集,可生成Q版的方块脸型人物,也支持跟其他风格的配合(如机甲,古风等),训练底模根据Anything-V5,兼容性较好。生成人像的发色,瞳色,衣服及首饰等均可替换生成;
【Lora应用】
推荐使用大模型:AWPainting,ChilloutMix_Chilloutmix。偏动漫类的模型出图效果都不错
推荐参数:Steps: 20, Sampler: Euler a, CFG scale: 7
分辨率设置:768*768
正向提示词参考:1girl,solo,brown hair,chibi,blue eyes,white background,simple background,hair flower,running towards viewer,earrings,full body,
反向提示词:lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry