This was made mainly for slime girl penetration. I have not tested other cases where transparency would make sense.
v2 update:
There are more penetration types supported and a better distribution of colors & styles now.
Getting proper transparency to work with slime girl penetration is a pain. Most approaches either use x-ray (which looks weird for slime girls), do some complicated prompting workarounds, or just deal with low annoyingly low success rates.
This is my first attempt at a LoRA so I can't guarantee it will work properly for you. The dataset is a mix of different aspect ratios, slime colors, and positions. There also aren't any oral or double penetration images in the dataset (for now) so those might not work either. I added more penetration types in v2 but they are still WIP. The dataset still isn't finished yet.
translucent penetration should be the only thing needed to trigger it, but you might get better results with additional tags/phrases such as slime girl, transparent skin deep penetration, perspective, monster girl, (color) skin (such as blue skin, green skin, multicolored skin, etc), penis visible through transparent body, etc. Some penetration types might work better with specific angles (especially the types that are still WIP).
I recommend pairing this with a dedicated slime girl LoRA (such as DaSiWa-Illustrious-Slime-Girl, Realistic Slime Girls, or Slime Girls - Concept) and a checkpoint that is able to handle NSFW concepts well such as DaSiWa Illustrious | Anime (SweetPoison was used to train v1 & v2). The style and positions will likely be overpowering when using with other LoRAs if the strength is too high. Setting it to 0.7 is enough to basically guarantee the concept in most cases, but a good LoRA combination with some good prompting can get it to work with as low as ~0.25.
My typical generation args are either:
steps: 50
cfg: 8.0
sampler: euler
scheduler: simpleor
steps: 37
cfg: 4.0
sampler: euler ancestral
scheduler: simple
If you are having issues with six fingers I would recommend looking into Smooth Negative Hands to help with that
Description
Changes
Cleaned & reorganized the dataset
More style variations
Less quality degradation when using with other LoRAs. Turn the strength down if you are having issues with this
WIP support for oral, fingering, fisting, tentacles, and arbitrary penetration
Better success rates & with rear view & close-up angles
Issues
Some angles have a bias towards straight penises (that don't follow the angle of the body)
There is likely a bias towards anal especially with close-up rear view shots
There is a bias towards penis-shaped tentacles
Fingering & fisting may only work from specific angles. Fisting can be especially finnicky