Femboy Chastity
Version 3.0 release tldr
Updated to focus more on flat/metal cages
USE CLIP SKIP=2
Inpainting works with 'closeup view' trigger word
This LoRA is intended to add chastity cages to characters you generate. Is is still a tad overfit so I have added grid images for you to see how the lora affects the base model at varying weights and CFG scales. Some of the model are very hard to prompt (for example deliberate does not like generating cages on the woman class) for that reason you might find that this model is better served as a inpainting lora.
Due to the training images, this model also has a propensity for cutting the heads off of characters, so you may need to use specific prompts to prevent this (i.e. "cute face", "whole body", etc.)
How To Use
Optimal weights for these models are 0.6-1.0 as a general rule. Generally you should use at least the triggers "chastity_cage" and "testicles" together. You might also consider adding keywords like "pussy" and "vagina" to the negative prompts as most of the training prompts consisted of the 'woman' class.
Most of the training prompts for this model were of the template "A woman in lingerie in a chastity_cage, testicles", for that reason it will probably conflict with any LoRAs of female characters.
You can also use this model for Inpainting, just add the 'closeup view' keyword to the prompt, for example the prompt "a closeup view of a chastity_cage, testicles" is usable for inpainting a chastity cage on another image. The same guidelines about the lower weights and CFG scales above applies.
Finally, if you find interesting ways to get consistent and reliable results, I would love to hear about it to improve the model.
Downloads
Please select the version that corresponds to the model you would like to use, currently I've only trained on PFG111, Comix v4.0, Protogen 2.2 Anime, MeinaMix, Deliberate 2.0, and UberRealisticPornMerge. There is also a version trained on the base pruned SD 1.5 model, that LoRA is a good option if you want to preserve as much of the base model as possible (See the gamer girl example in the Grapefruit version gallery as an example of the difference between the Model-specific LoRA and the general LoRA).
If in doubt grab a couple and run some grids to see which works best for you. If you have suggestions for other models please let me know.
Looking forward to seeing what people create <3
Description
Trained on the base SD 1.5 model
You should really only use this with fine tuned models as the base model probably won't perform too well.
FAQ
Comments (10)
femboys dont have boobs lmao
¯\_(ツ)_/¯
you'd be surprised
although mainly yes, some fems take hormones (oestrogen and the sorts) or try and get bewbs from using tape and push-up bras resulting in bewbs. but yes most fems dont have any and are very flat chested
Cannot get this to work at all, tried different models, real life and anime models (hassanblend and grapefruitmix for example), different samplers, numbers of steps between 30-50, CFG scales between 9-12, lora strength between 0.3-0.8, and it generates either nothing, or some weird mess.
Yeah, it doesn't seem to work with Hassan at all (retrained or not), but I also get terrible results for Hassan without the LoRA so its probably something about the prompting for Hassan. I'll look into Grapefruit tomorrow, but more realistic models like URPM seemed to be okay with the URPM version of this. I'll look into it a bit more.
There is a grapefruit model uploaded now that worked 'okay' the lora really removed alot of the base model, you might try the sd1.5 version of this lora with grapefruit to see what happens. The two gamer girl images in the grapefruit gallery show the differences between the 'grapefruit' and 'base' version of the lora with the grapefruit model. Hope it works!
@sasha_sore_captions Hey, I tested it with grapefruit and still having troubles generating a good looking cage most of the time. I uploaded my attempts, used your gaming girl prompt as a base. The metadata is available in the pictures, in case I did something wrong you can notice it from there. I'm guessing chastity cages are a hard concept for AI to learn as another model I tried for them has similar troubles.
@Disastrous_Cash Nothing in your prompts jumps out at me as something to change so its probably just an issue with the lora. Thanks for testing it, I'll try to see if I can improve things in later versions.
small limp cock version please?