This is a LORA model for arm restraints trained on 30×5 artificial + internet data for z-image.
It supports a total of 5 variations with an accuracy of about 80%. (The model is overfitted and sometimes fails to distinguish restraint types; variations may occur in face, body shape, and style.)
Weight 0.6~0
Trigger word (sentence)
she is wearing a monoglove_armbinder which binds her arms behind her back.
she is confined in metal_yoke which locks her neck and wrists in a thick pipe.
she is confined,secured in dark oak wooden_yoke which locks her neck and wrists in a thick wood .
she is wearing a latex bolero_straitjacket_front_tie which confines her arms crossed tightly over her chest .
she is wearing a latex bolero_straitjacket_back_tie which confine and binds her arms tightly behind her back
For Devs
The LORA training parameters are as follows.
z-image LORA train adapter used
rank64,
batch 6 ,
steps 6600,
lr 0.0002
For v2:
Training z-image is difficult, so I plan to try again after the base model is released.
When creating synthetic data, I utilized @Joschek's LORA for post-processing some data. Thank you to @Joschek for creating such a great LORA.
Description
v1
FAQ
Comments (3)
v1.0 I'd like to use it, but the chance of getting a good image is very low. I'm using it with str 0.6 (any higher and it changes the whole image) and I'd like to use monoglove_armbinder and i use your trigger phrase. Out of 20 images, maybe 2 look realistic. I would love to use it because I love armbinder. I hope you can create a good version 2.0 :) thanks for your work
Thank you for your detailed feedback. I've created another new LORA that I think you'll like! https://civitai.com/models/2226139/armbinder-monoglove?modelVersionId=2506147
Thank you. We need more BDSM stuff for z-image.