Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Quickly made for a request that was later dismissed. I still had it so why not share?
Should work perfectly on AnyLoRA at weight 1, but it's more style-accurate with Anime Pastel Dream - Soft. Increase accuracy with doyora
.
Keep in mind most of the dataset was NSFW. Despite that, depending on thebase model, this doesn't seem to be overfitted on nsfw stuff and can make SFW images reliably (as well as NSFW ones if you want it)
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 according to the instructions (by default it's :1
)