Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
This one got commissioned by a friend. I don't think that current SD can reproduce the style of this author perfectly. That's because they tend to add a lot of noise, which is not easy to mimic for a denoiser. Anyway, this still turned out pretty nice as an artstyle, and I don't feel bad because it's still very far from the original author. I suggest using this with anime models (AnyLoRA as it's mostly neutral) at 0.6-0.8 weight. Triggers with rolua
.
Careful because it tends to destroy hands. 1/5 turns out decent.
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)