Finally, my first Lora is complete. After many failures and retries, I made some major
changes to the trigger words. Please see the details here for how to use them, or you can directly view my image.
Version 1.2 features further fine-tuning of the trigger words and introduces a new "Full Coverage" stage. During testing, I discovered that this update enables a range of additional effects—such as rendering genitalia beneath clothing or adding an organic, biological texture to garments. I utilized higher parameter settings during training to ensure that all elements remain as controllable as possible. So go ahead—unleash your creativity and show me just what kind of spectacular results this model can produce!
However, too much data can make the image look cluttered; for a cleaner portrait, try V0.7.
Basic prompts for portrait：ff000,close-up, portrait, slime suit, glossy skin, viscous, tendrils, veins on face, organic armor, dripping, covered neck, tentacles on face, tentacles in mouth, tentacles in nose, live clothing, [color] substance, [color] bodysuit
1. hh101,covered jaw,
2. hh102,covered mouth, mouth mask,
3. hh100,live helmet,short hair,
4. hh103,live helmet, blindfold, no eyes, covered eyes, no hair
Basic prompts for full-body images：hf101, full body, glowing veins, tendrils, slime suit, glossy skin, viscosities, veins on face, organic armor, dripping, covered neck, tentacles on face, tentacles in nose, tentacles in mouth, live clothing, [color] substance, [color] bodysuit, glowing [color2] lines,
1. fh101,covered jaw,
2. fh102,,covered mouth,mouth mask,
3. fh100,Living Helmet,Mask open,short hair,
4. fh103,blindfold,no eyes,covered eyes,no hair,
hf351, no eyes, covered eyes, no hair, long tongue, sharp teeth, pointed tongue, eyes on chest, monster girl, completely covered, parasitic, tongue out, chest pattern
other
futanari,covered penis,covered testicles,
If necessary, I can optimize the dataset to generate a cleaner, more streamlined version.
Thank you for your interest in my humble work.
Description
Due to the limitations of the dataset, it only works almost exclusively with close-up shots, so it's not yet version 1.0. For usage instructions, please refer to the details. If you're interested, please click "add post" and send me some free blue buzz images. Once I have enough, I'll upgrade it to version 1.0 as soon as possible.
FAQ
Comments (7)
Are you interested in creating the effect of a face under a mask or a partially shattered mask, Lora.
I can certainly give it a try, though it will likely have to be scheduled for after the 1.0 release of this LoRA model. The current dataset is already quite massive; adding anything further would likely just degrade the overall quality of the results. In fact, I actually need to trim down the existing dataset slightly to prioritize better rendering of bust and full-body shots. Additionally, could you send me an example of the specific effect you're looking for? That would help me create a more accurate dataset when I get around to working on it.
(^_^)v
@1016183941431 During training, the model seems to respond poorly to unfamiliar words. I could try training the bubble to look like an X-ray.
@futa2088 Thank you,Because no one has ever posted a suitable model on the entire website, it has been a headache for me for a long time. However, I am not good at computer technology and cannot make it myself
@1016183941431 However, I would appreciate it if you could bear with me for just a little while longer, as I am currently still in the process of building the dataset. May I ask if you would like me to incorporate any "furry" elements into it? Additionally—since I still have some offline work to attend to—I will only be able to work on this project during my spare time, though I will do my utmost to move things forward as quickly as possible.
@futa2088 I'm truly grateful that you're willing to give it a try. Thank you