Dullahan/Disembodied Head | Concept LoRA
Collecting Head or "Getting Head" ;)
V2: or getting no head at all xD
Weight can go from 0.7 up to 1. I recommend 1. ControlNet will streamline full body shots much easier, or more complex poses. Works with almost every Style, every Character and Photorealistic Models (kinda).
V2: Does include full "headless". "holding head" got improved. Keep in mind, that you have to remove all facial features like "red eyes", "black hair", etc for "headless" prompt to work.
WARNING: This LoRA is a little unstable. Will be updated in the near future.
Trigger Word:
DisembodiedHead
Helping prompt (only 1 of them):
holding head
headless
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!