A first try at making a character LoRA for SDXL 1.0. This is Loona from Helluva Boss, the lora was trained with 100 pictures and e621 tags, so please use them in order to prompt the lora correctly.
As of now this is still in alpha! Details are rough and you might need a few gens to get what you want.
To prompt : Use "loonasdxl" and then all the tags you want. Note that tags such as "solo", "female", "canine", "white fur" and such won't change anything as they have been pruned from the dataset in order to allow for minimal tag prompting.
Weighting this LoRA is fairly straightforward : anything between 0.6 to 1 goes, with a preference for 0.8 weight.
Description
better faces and eyes
better poses
general quality improvement
FAQ
Comments (4)
you know the kind of FREAKS!!!!!!!! up there who drool ALLLL over you
the important question here... is which 100 images 🤣🤣
it doesn't show up in A1111 when i put it in the folder, anyone know why?
Getting an error saying this is a regular SD and not SDXL LoRA, what's the problem?