
Soejima Shigenori (Persona /Catherine) style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon ?️ or feel free to buy me a coffee ☕
One of my favorite artists from one of my favorite game series. I'm quite happy that the net managed to also keep some character concepts, as you can see from the examples, but also the uniforms and various aspects of the style. Triggers with soejima shigenori
and other related game tags, character tags and description tags. Weight around 0.5-0.6, but depends on how much of a defined and overpowering style you want. The 1st and 6th image have been made by also using Doctor Shotgun's character LoRA's, while the 4th image was made by mixing this LoRA at 0.6 and Zipsy's "all out attack" LoRA at 0.5. Mixing them makes the lines much sharper like the Persona 5 artstyle.
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)
描述:
训练词语: soejima shigenori
名称: soejima_shigenori.safetensors
大小 (KB): 294990
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success