
This is a funny style of the artist Vasya Lozhkin. Makes all your art a little bit funnier. LORA was trained on Pony Diffusion V6 XL/Anything-v3.1 model (with vae from SD). Suitable for both t2i, i2i and mixing styles as well.
For PonyXL
The recommended weight is 0.7-1.0
0.5-0.7 is for light stylization, 0.9-1.0 for hard stylization (close to original style).
Recommended trigger words: lozhkin, open mouth, big smile, teeth
My optimal settings:
CFG: 5-7
Steps: 30
Clip skip: 2
Sampler: Euler a
LORA weight: 0.7-1.0
Use Adetailer and Hires.fix for better results!
And have fun! Kva!
For 1.5
The recommended weight is 0.6-0.8, with the settings higher you will most likely get Vasya's signature characters.
Recommended trigger words: lozhkin, open mouth, big smile, accurate teeth with gaps
My optimal settings:
CFG: 5
Steps: 20
Clip skip: 2
Sampler: DPM++ 2M Karras
LORA weight: 0.6-0.8
Use Hires.fix for better results!
And have fun! Kva!
描述:
1st release
训练词语: lozhkin, big smile, accurate teeth with gaps,open mouth
名称: lozhkin.safetensors
大小 (KB): 147572
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success