[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]

/vt/ - Virtual Youtubers

Search:


View post   

>> No.82122682 [View]
File: 2.68 MB, 1920x1296, 03719-uruka,_[blue_streaked_multicolored_hair],_long_hair,_blue_hair,_blue_eyes,_[gradient_eyes],_bear_ears,_sitting,_eating_burger,_m.png [View same] [iqdb] [saucenao] [google]
82122682

>>82121872
I agree, having knowledge of specifics is overrated. That's the entire purpose of loras. Even when a model natively supports a style I still like having a style lora. That's why you'll see a concept or character spelled with leet speak in a lora, to avoid bleed from the model while invoking those tags.

Navigation
View posts[+24][+48][+96]