Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Tested on AnyLoRA ckpt at weight 1 with trigger spy x family style
. As a style LoRA this isn't made to reproduce characters on its own, but it can get close with accurate descriptions and can be decently accurate with good embeddings and character LoRA nets.
Works well with my Yor Briar character LoRA and with LottaLewds' AnyaHehFace 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
)