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)
描述:
训练词语:
名称: 1133784_training_data.zip
大小 (KB): 29536
类型: Training Data
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
名称: pixelhd.safetensors
大小 (KB): 223121
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success
