This is an experimental LoRA trained with the r34 tag "embedded_penetrable_sex_toy" in mind. It's pretty much a Proof Of Concept than a stable and user friendly LoRA to use, but I still hope you can have a good time trying it for yourself.
Even with a very small dataset, it do work with realistic and furry style.
For the Strength of this LoRA, it seem to work fine with 1, but I would recommend trying lowers values and work around trigger word to adjust the result
For all versions
The keyword is 'embedded_penetrable_sex_toy' but you can use specific keyword style like :
'human, sexdoll,' for a human character
'humanoid, robot girl, sexbot, mechanical, mechanical body,' for a robotic character, with a more raw mechanical interior
'robot furry, anthro, sexfurry,' to help furry and smoother skin generation
'robot furry, anthro, sexfnaf,' for a mechanical and rounder furry result, with more robotic attributes
For the color of the internal sextoy, you can use 'artificial vagina, <COLOR> fleshlight,' and custom it.
For Illustrious V2.0
There is different style of belly transformations, those are :
'inside view, mechanical body, womb window' : small womb window
'internal view, open body, exposed mechanical body, robotic body,' : larger window
'x-ray, inside view, see-through, see-through womb, transparent body, translucent body,' : largest internal exposition, you may want to use 'metallic skeleton' to increase the effect
In this last version the internal sextoy texture can be modified like so :
'solid fleshlight' : no texture visible, only rigs on surface
'transparent fleshlight' : visible inside texture
'see-through fleshlight' : fully clear internal texture
To increase the robotic aspect you can change weight of this new trigger word :
'grey metallic skeleton, shiny metallic skeleton' : chromed internal structure
'([light grey|grey|dark grey|black] metallic skeleton:0.7), translucent body part,' : all available nuance for the internal structure
Description
Increased bucket max size from 832x832 to 1024x1024
removed bad training data for more precise internal sleeve
FAQ
Comments (5)
ILXL version 1.1 seems to have learned the art style included in the training data strongly. It is very difficult to apply the model's own art style or the art style of other artists.
Hey, sorry for the late response.
Depending the type of character you want there isn't that much sample style, and so make the generation like the style of the desired character type.
You may try to use less trigger words like "sexdoll,sexbot,sexfurry,sexfnaf" and perhaps robot and furry to reduce style issue
Hi, I tried several times before getting a relatively good result. Could you help me see where I can improve? Especially, the mechanical structure doesn't seem to be very elegant. I have already shared the generated image
Hey, I removed all your generic quality prompt and tried mine, you may want to try the proposition I made in the description and weaken the lora to 0.8 to avoid skeleton artefact :
https://civitai.com/posts/26875063
Also, it seem like the pantyhose is doing weird interference with the lora, try to add skin color in positive and white / black body in negative to distinguish both upper body and leg
@Lazius benefit greatly!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.















