Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Elinerd on Discord asked me to do this one. I like this illustrator a lot, but I was a bit afraid because of the lack of good labeled data available. However I think it turned out good. I used AnythingElse and AnyLoRA for those examples but I guess that most of the neutral anime mix will work decently. I suggest weight 1 for the offset version (0.6 for the old one).
Because the dataset was small and had many repetitions this LoRA also picked up some of the characters, but it's mainly a style LoRA.
How to use LoRA's in auto1111:
Update webui (use git pull
like here or redownload it)
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA like in this video
Make sure to change the weight (by default it's :1
which is usually too high)