
I'm back with another dumb loRA :D
This time it's a style loRA (aka an attempt of mine)
Most images in the dataset come from VRoid Hub while others were made by me in VRoid Studio so yeah
SOME DUMB INFO:
-
trained on 87 handpicked images (some were homemade)
-
works best with AnyLoRA
-
when doing full bodies or cowboy shots, use a higher res then 512x512 or turn on hires. fix
-
tags such as "Cel Shading" or "Anime" might help
-
I haven't tested this with NSFW stuff so I'm not sure if this loRA can even do NSFW content
(probably not since all dataset images are sfw). Feel free to play around with the model tho. -
Feel free to play with the loRA weight. 1 should be enough tho
-
to do male characters, you might need to force it (example: instead of "1boy", use "(1boy:1.4)")
CONTACT INFO!:
Twitter: YuriMayori
DeviantArt: CappyAdams
Other Socials (Link to my Website): Click here or smthin idk
描述:
-
trained on 87 images
-
keyword is "vroidstyle"
-
the loRA weight can stay at 1. but feel free to play around with it
-
not sure if it can do NSFW
trained on 87 images
keyword is "vroidstyle"
the loRA weight can stay at 1. but feel free to play around with it
not sure if it can do NSFW
训练词语: vroidstyle
名称: VRoid_Style-01.safetensors
大小 (KB): 36995
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success