Trigger words:
Spank (or any of its variations like Spanks, Spanking, Spanked, etc)Example prompt:
You can download any of the showcase videos and drag them into ComfyUI. They all have the metadata attached.
A gorgeous 25-year-old redhead woman with her hair in a ponytail and with her round butt towards the camera. She is wearing a a red bra and red lace thong. She is bent over a bed. She is being spanked. Her butt jiggles with each spank.
Realistic. Rear-view shot.TIPS:
This is being re-trained. it has only been trained for rear-view shots as of right now. It is still being trained, but is already more consistent than the previous version.
I will introduce other angles (Side-view, Front-view) in the future as training progresses. I'm hoping breaking it into separate training sessions helps.
Description
More flexible model that can be adapted to more novel scenarios and mixed with other LoRAs.
FAQ
Comments (5)
does your dataset contains slow motion clips? almost every generation you shared looks kindof "slowmotioned" xD
im preparing a new dataset and when i "normalized" the fps across the clips to be 24fps i realized some of the clips became slowmo, i managed to fix it.. but as i asked gpt, it told me that the generations from that lora will be in slowmo as well..
i gues you can fix it by adjusting the number of frames in the video combine modules..
Some clips were slower motion, but most are actually regular motion speed. Some of my examples are actually generated in 12fps and interpolated to 24fps, which is why they look "slow".
@ComfyTinker interpolation fills in the gaps to make motion appear smoother.. It wouldn't make a video slow motion unless you chose that option separately
@civitai7_ The most recent release adjusted for this.
Good job, I'm sure things will improve over the next months, the technology is still so young !