[ 3 / biz / cgl / ck / diy / fa / ic / jp / lit / sci / vr / vt ] [ index / top / reports ] [ become a patron ] [ status ]
2023-11: Warosu is now out of extended maintenance.

/vt/ - Virtual Youtubers

Search:


View post   

>> No.52294112 [View]
File: 1.82 MB, 1024x1536, 00029-2550414054.png [View same] [iqdb] [saucenao] [google]
52294112

>>52292533
I feel like her labcoat is really unique design to her model, it feels menacing and alluring to look at I'm dumb with words . And thanks for the link.

>>52292771
I almost bought 4060 too before finding 3060 has more VRAM within my budget. I mean 4060 have more cuda cores but only using them to prompt anime art, just tensor cores is enough since its doesn't differ much than 4060.

>>52292718
You can use supermerge to merge lora into model: https://github.com/hako-mikan/sd-webui-supermerger

For retraining method, I heard the best possible way is by doing data augmentation, gening while training at the same time. Idk the detail since I never tried it. Some github ref: https://github.com/DevArqSangoi/das-dataAugmentation

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