This is a true slider lora so it should not change the image to much compared to normal loras. Its also no problem combining this lora with other loras.
The lora is very weak, so if the prompt specify "high-waist" etc, the prompt will probably override most of the lora-effect.
I RECOMMEND COMBINING medium and strong for best results.
Strong have a tendency to unbutton or rip the pants. But with medium at around 4.0-5.0 combined with strong at around 1.0-1.5 its perfect imo
medium is has better quality, but strong works where medium is limited.
Recommended range
medium: -5 to 2 (negative = lower)
strong: -4 to 4 (negative = lower)
All my work is 100% free. The only thing that really matters to me is people leaving a review, good or bad. I will NEVER remove or block anyone for leaving a bad review, so don't be afraid to give me criticism.
I'm stating this because when a creator blocks someone for leaving a bad review, that person can no longer see any of the creator's models, essentially muting their critics. This is something I'm highly critical of, and I believe it's a fundamental quality problem on this site.
Description
This will pull the pants down to much.
It also have a tendency to unbutton the pants.
I recommend using this in combination with V1 if you dont want the pants to unbutton. It that case, this can be used at a very low strength at around 0.5 to 1.0
FAQ
Comments (4)
This works very well with all kinds of clothing from jeans to skirt so thank you!
If I had to make a critique, it has a strong preference for denim. In some cases, I couldn't get my skirts or pants to be anything but denim but I did not use it in conjunction with a skirt/pant LORA so that might help. If you train a V2, my suggestion (as a non-trainer person) is to try and mix the fabrics a little more.
With slider loras the dataset is not used directly to retrain the model. A true slider lora like my loras are, the lora just shift the model parameters towards a bias with prompting.
There is a dataset that is needed for training, but this is only used as a anchor for the model so it know what is "normal". (at least to my understanding)
So i prompt a positive and negative prompt to steer the model. And this is where i should have been aware of the denim situation. I have noticed the problem myself. But if you use a combination of both medium and strong its possible to work around this problem. At least in my exp.
This was a hard lora to train, so i dont think i'll be trying to make a V2 any time soon. But if i do, i'll be sure to prompt away the denim bias.
But anyways, thanks for the feedback.
Man why are you so good at making these sliders. <3
This is great! Could you please make a similar slider for skirts/dresses? :) The larger the value, the more the skirt/dress is lifted. Would be extremely cool if it was possible to prompt what kind of underwear is seen under the lifted skirt :) Thanks!