This LoRA tries to replicate the style used by Koyama Hirokazu. This was a paid request, and was done as the requester liked, as such this has two safetensors files, the base one for the previews, and one that is far far more baked, play with both and pick whichever you like.

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 as much as others.

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 just opened a Discord server where you can go and bother me about which style I'm working rn, or suggest