
v2 Should be better, less overbaked, a bit more flexible.
You already know the drill LoRA that tries to replicate Fukuro's style.
Recommended VAE are Counterfeit and OrangeMix or any NAI renamed, recommended Weight is 0.6 to 1.0, this was trained on NAI so it should be quite compatible.
All preview images have Hires and Adetailer, LoRA likes VectorScope but not for saturation you've been warned.
Any and all reviews are very much appreciated so I can know what to improve for this LoRA or for other models, thank you~
I opened a Discord server where you can suggest me styles to try.
描述:
训练词语:
名称: Fukuro-Style-v2-000015.safetensors
大小 (KB): 73887
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success