【lora简介】模型可稳定输出简笔画风格的人物全身图，发色，衣物等均作了泛化测试，适配性好。可用于一些PPT的插图，海报主视觉也可。【模型使用】大模型：<a rel="ugc" href="https://civarchive.com/models/66/anything-v3?modelVersionId=75">Anything V3</a>采样方法：DPM++ 2M Karras图片尺寸：768x1024lora权重：0.5及以上，建议1.0以下【提示词】正向提示词：1girl,solo,simple background,(white background:1.3),smile,blue shirt,shoes,full body,short sleeves,standing,short hair,skirt,pink hat,socks,closed mouth,looking at viewer,负向提示词：(worst quality, low quality:2),(normal quality:1.5),((watermark:1.4)),artist name,character name,text,bad anatomy,sketch,duplicate,(ng_deepnegative_v1_75t),negative_hand-neg,bad_pictures,EasyNegative,

Files with SHA256: 1514bbe51f698dc04b12ce47cd3ec19e5d2b8b8be606bd8e36065fbbe6330bcf