Main tag : naked towel, or bath towel,
LoRA str : 1
Denoising str : 0.3
Image Train : 271
Training Pony LoRA Powershell info :
resolution = 768
Batch size = 3
network_dim = 8
network alpha = 4
mix/save_precision = BF16
optimizer_type = AdEMAMix
optimizer_args_other = [Default optimizer]
caption_tag_dropout_rate = 0
GPU RTX 4060Ti 16GB
Torch 2.3+cu121 + Xformers + gradient_checkpointing
Vram used = 11.2GB
Speed = 2.03sec/it
Weight
UNet weight average strength: 0.009245851497508216
Text Encoder (1) weight average strength: 0.008643580151570865
Text Encoder (2) weight average strength: 0.006763563477906089
Description
FAQ
Comments (5)
loading Lora D:\AI\stable-diffusion-webui\models\Lora\nakedtowel.safetensors: RuntimeError | 0/15 [00:00<?, ?it/s]
Traceback (most recent call last):
File "D:\AI\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 215, in load_loras
lora = load_lora(name, lora_on_disk.filename)
File "D:\AI\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 176, in load_lora
module.weight.copy_(weight)
RuntimeError: output with shape [4, 320, 1, 1] doesn't match the broadcast shape [4, 320, 3, 3]
Tried download back and was doing the same thing..
Since training with Conv2D requires
https://github.com/KohakuBlueleaf/a1111-sd-webui-locon
Is there a way to change the color of the towels?
white only
Add onsite generation please 🫥
Details
Files
towelConv2D2.5e-5_BF16.safetensors
Mirrors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors
naked towel - towelConv2D2.5e-5_BF16.safetensors
towelConv2D2.5e-5_BF16.safetensors




