LoRA trained on a set of upscaled pixel art, resulting in a style with sharp painting-like technique, natural colors, intricate fine details, rich and nuanced shading.
Recommended CFG is 6.5 when generating with strength of 1.
The samples in showcase are generated with KuromiwaMix v1.4
UPD: Someone asked for the training set, it's here: https://files.catbox.moe/tii6lk.zip (actually it's a merge of multiple smaller sets)
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights.