[Lokr] Dagasi Style Lokr for Noob-Vpred Repost
详情
下载文件
关于此版本
模型描述
使用Dagasi画风训练的LoRA。之前被夹过,重新发布,第二次。
使用1300张较新的图片进行训练,截止至【休日はサーナイトと】系列。标签经过手工校对。训练图像包含男性和女性furry以及少量非furry内容。这些图像中包含了一些Dagasi发布的【限定】图像,不同于Dagasi老师此前发布的前两部分无码图,这些图带有条形马赛克,于是我使用PS手动去码。由于训练集足够大,该LoRA可生成furry、人类、纯兽等多种角色,与其他LoRA配合效果也应不错,有待测试,欢迎大家多返图,让我看看效果。
Dagasi的画风偏可爱,其特点之一是几乎每个角色脸上都会有脸红,因此如果你不喜欢常态脸红,可以将该tag加入负面提示,但效果不明显。此外,由本LoRA生成的所有角色都偏幼态,即便是成熟角色,头身比也会偏小,这是无法避免的,可使用ControlNet调整。
该模型还标注了几个Dagasi的角色,如下:
perro-kun: perro-kun, fox boy, fox ears, fox tail, yellow eyes, two-tone fur, orange fur, brown fur, hair bobbles, brown hair,
yuki-chan: yuki-chan, leopard girl, leopard print, snow leopard, leopard ears, leopard tail, blue eyes, light blue hair, multicolored hair, multicolored fur, blue fur, stomach mark(如需还原她肚子上的爱心花纹),
momo-chan: momo-chan, fox girl, fox ears, fox tail, ears down, red eyes, gradient eyes, two-tone fur, brown fur, pink hair,
kohaku-chan: kohaku-chan, tiger girl, tiger ears, tiger tail, tiger print, multicolored fur, tiger stripes, white fur, orange fur, black fur, green eyes, streaked hair, black hair, two-tone hair, orange hair, short hair, body markings(花纹效果不稳定),
buchi-chan: buchi-chan, hyena girl, hyena ears, multicolored hair, pink hair, brown hair, multicolored fur, brown fur, blue eyes, hairclip, hair bobbles, futanari(如需看牛牛),
haruka-chan: haruka-chan, rabbit girl, rabbit ears, rabbit tail, brown hair, carrot hair ornament, red eyes, ears down, short hair, one side up, asymmetrical bangs, two-tone fur, brown fur,
sora-chan: sora-chan, two-tone hair, white hair, short ponytail, low ponytail, body fur, two-tone fur, yellow fur, white fur, animal ears, animal nose, 4 fingers, medium hair, large tail, tail ribbon, pink ribbon, black eyes,
tamame: tamame, nekomata, mature female, calico, calico (pattern), multicolored fur, white fur, brown fur, huge breasts, cat girl, cat ears, cat tail, multiple tails, two tails, multicolored hair, long hair, brown hair, white hair, ponytail, sidelocks,
现存问题:该LoRA倾向于生成NSFW内容,且动作表现受限。
权重建议:若使用Noob本体,推荐0.5 - 0.7;若使用Wai Noob等微调模型,推荐0.6 - 0.9,不建议使用1或以上的权重。








