Not recommended for realistic models
Main tag : Milking machine,
Secondary tag : nipples, lactation,
Pose tag : leaning forward,
norm retention: 98.14% | std: 0.010
Training Powershell info :
Image Train : 160
DIM/Alpha : 12/6
Train batch size : 2
resolution : 768
mix/save_precision = BF16
optimizer_type = AdamW
GPU : RTX 4060 16GB 160W [Training Load 110W]
Torch 2.5 + cu12.1 + Xformers + gradient_checkpointing
Vram used : 10.1GB
Speed : 1.58s/it
Description
This version still have problem tag not working well enough
FAQ
Comments (13)
It's perfect!!! Thank you!
Why i can't use this lora,what's wrong with it or my program?
that's my error report:
LoRA weight: 0.9, model: milkingMachine_v11(fd2c363b)
Error running process: D:\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\additional_networks.py
Traceback (most recent call last):
File "D:\stable-diffusion-webui\modules\scripts.py", line 386, in process
script.process(p, *script_args)
File "D:\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\additional_networks.py", line 238, in process
network, info = lora_compvis.create_network_and_apply_compvis(du_state_dict, weight, text_encoder, unet)
File "D:\stable-diffusion-webui\extensions\sd-webui-additional-networks\scripts\lora_compvis.py", line 73, in create_network_and_apply_compvis
network_dim = min([s for s in size if s > 1])
ValueError: min() arg is an empty sequence
Very frustrating to get to work :(
Copied all of the settings and could barely get 1 full generation that makes sense.
Tried changing ENSD, ancestral eta, checkpoints, and stuff
Changing the vae to the kl-f8-anime2 improved consistency a fair amount. A superb idea! However currently the flexibility is too low (and therefore consistency) to be named simply "milking machine". Looking forward to more 😊
@EarNugget2 low flexibility because The practiced data is focused on leaning forward.
If used with a standing, use prompt : upper body,
Cant get it to work sadge
very sexy, thanks the author!
Most of the time when trying to use this LORA for me it seems to just not generate it im unsure if I am doing something incorrectly would appreciate any help i add in the prompts Milking machine and lactation although neither seem to appear in most images
One thing i noticed is with the results here is the PNG-info shows different models used from the one here, i guess using a base model is a requirement. Im obviously new to stable-diffusion, but can someone guide me into the right direction? I'm using Automatic1111, do i need to install something like an addon?
I found it works by using trigger: large breast, or never works