Type | |
Stats | 7,838 50,631 127 |
Reviews | (1,027) |
Published | Aug 27, 2023 |
Base Model | |
Training | Steps: 5,000 Epochs: 6 |
Usage Tips | Clip Skip: 2 |
Trigger Words | pov_strangling |
Hash | AutoV2 F42846E6CC |
A lora for creating pov asphyxiation/strangling scenes
or a way to discipline your misbehaved pet
Trained on 54 images
Notes
The loras tends to prefer scenes where the girl is on her back to avoid this write (lying,on back) in your negatives
The loras works well for both non sex scenes and sex scenes
sex scenes work better in a portrait resolution (512x768)
Using gigantic breasts will increase the chance of the hands getting messed up as well as the male torso being visible in some non sex gens to avoid this simply add strength to the (solo focus) tag
This lora works with other loras very well so feel free to experiment
Training settings?
The most important part of training is getting a good dataset!
Training settings can be found by installing the additional networks extension in auto1111
Extensions -> available -> load from -> additional networks
Restart webui
place lora into stable-diffusion-webui\extensions\sd-webui-additional-networks\models\lora
To view the training settings
Go to additional network tab -> choose model -> training parameters