>>52292533I 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.
>>52292771I 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.
>>52292718You can use supermerge to merge lora into model:
https://github.com/hako-mikan/sd-webui-supermergerFor 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