各位观众姥爷们,大家好!我今天要为大家介绍一款十分独特而有趣的虚拟形象——盲盒Lora。话不多说,先上效果图,看看是不是你喜欢的样子。
盲盒Lora是一款画风非常特别的虚拟人物。它几乎可以与任何人物或服装完美匹配,展现出惊人的兼容性。和一般的写实风格虚拟人物完美搭配,产生的这种Q版的照片很像是手办的写照,一种有趣的效果。
主要使用的绘图工具是Stable Diffusion,这里主要涉及到的是 blindbox的lora,模型可以选择任意模型进行组合,最好使用写实类的,不然感觉出来的结果有点怪怪的。
参考参数如下:
CKPT模型: revAnimated_v11
lora:blindbox
Steps(采样迭代步数): 25
Sampler(采样方法):DPM++ SDE Karras,
CFG scale(提示词相关性): 7
正向关键词:(masterpiece, best quality, absurdres, foreshortening), photo of a highly detailed,(full body:1.2), smile,cute face , eyepatch, bow, gloves, breasts, bowtie, bangs, ribbon, fishnets, bodystocking, green eyes, long hair, blonde hair, hair ribbon, purple bow, bare shoulders, black gloves, purple bowtie, detached sleeves, hair over one eye, elbow gloves,<lora:fischlGenshinImpact_fischlGenshinImpact:1> ,(studio background),(clean background),(blurry background), 1girl, chibi, (beautiful detailed face), (beautiful detailed eyes),standing in chinese garden, rendered in blender
负向关键词:
(low quality:1.3), (worst quality:1.3),pointy ears, animal ears, watermark, logo, text, badhandv4,(naked/nude, )
注意:负向关键词可以通用,正向关键词可以自己通过不同的修改尝试,需要注意一下身体的比例,chibi和lora的比重对身体影响比较大。
(best quality,masterpiece, absurdres, foreshortening), photo of a highly detailed, (chibi:1.7),(full body:1.2), (studio background), (clean background), (beautiful detailed face), (beautiful detailed eyes)