
Visit my Gumroad/Ko-fi for exclusive access to all 60+ of my LoRAs! ▼▼▼▼▼
I'll be releasing 1-2 LoRAs on Civit every month, with early access on my stores, and over 60 exclusive models ? Members can get full access to my entire archive plus my private TG for my steamiest content!
-
This is a LoRA trained on the 1.5 base SD model, at 768px. Please share your SFW results and feedback for any future training improvements. I'm going to need a bit more training data to get this 100% of my personal expectations, so I'm dropping it now for testing.
Recommendations:
-
Trigger token: hook
-
If you use LoRA block weights, set this one to :OUTALL for better results
-
Strength: 0.6-0.9, I usually start at 0.75
-
Tags
-
Use 'tattoos' for more accuracy
-
He'll almost always generates with a necklace and his wrestling shorts, negative prompt those if needed
-
Use 'brown eyes' in positive or 'blue eyes' in negative prompts for better results
-
-
I recommend using After Detailer + Hires Fix, or IMG2IMG double upscaling using MultiDiffusion and ControlNet Tile for highly accurate faces
I am not responsible for your use of this resource, which is not for commercial use and is for research purposes only.
描述:
训练词语: hook
名称: diffusiondudes_Hook_V1-12.safetensors
大小 (KB): 36983
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success