Dataset trained on 768
Dataset cleaned out
Trigger changed
Works best with females, but no much with males
Halloween | Clothing Style LoRA
HAPPY HALLOWEEN! Why now do u ask? It just depends, when u are gonna download this LoRA. :)
V2:
Weight can go from 0.5 up to 1. I recommend 0.7. Works with almost every Character, Style, Concept and Photorealistic Models. Might be a little bias, because of the amount of unbalanced dataset between male and female.
Trigger Word:
IncrsHlwn
Helping Prompt:
halloween, halloween costume, night sky
Outfit Prompt:
(see previews or add some yourself)
V1:
Weight can go from 0.3 up to 1.0. I recommend 0.7. ControlNet will streamline full body shots much easier, or more complex poses. Works with almost every Style, every Character, Photorealistic Models and LoRA's. For some reason not with every Checkpoint. I will fix that soon.
The Main triggerword is Halloween. I recommend using more weight on this like (Halloween:1.2). You can go higher, like (Halloween:1.7) and it will give most of the time ruined makeup. Also changes most of the time the Background, if unprompted.
This LoRA most of the time combines the main Outfit from the Character with Halloween Outfit. If you don't want that, then add dress, thighhighs, or leotard.
Trigger Word:
Halloween or (Halloween:1.2)
Helping Prompt:dress, thighhighs, leotard
How to use LoRA's in auto1111:
Download LoRA
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA and use the triggerword
Make sure to change the weight if needed (by default it's :1)
Have Fun!
Dataset trained on 768
Dataset cleaned out
Trigger changed
Works best with females, but no much with males
1. 재게시된 모델의 권리는 원 제작자에게 있습니다.
2. 모델 원작자가 모델을 인증받으려면 공식 채널을 통해 SeaArt.AI 직원에게 문의하세요. 저희는 모든 창작자의 권리를 보호하기 위해 노력합니다. 인증하러 이동
