
Tried to recrate xFate's style with a VERY SLOW cook with the intent of allowing expressions already present in the checkpoints without too much bleeding from the ones in the dataset, I think this LoRA manages that decently well allowing for a bit more of creative freedom without external LoRAs or LECOs, while also taking other LoRAs and LECOs without much issue, and I really liked how this one turned out, but beware, it might create Honkai Valkyrie's suits at weight 1.0, recommended weight goes from 0.5 to 1.1
Trained for 150 epochs with 166 images at 768x768 resolution, for a total of 32400 global steps
All preview images have Hires and Adetailer, LoRA likes VectorScope for saturation, like a lot.
As expected Genshin and Honkai character LoRAs seem to mesh well with this one.
描述:
First release
训练词语:
名称: xFate-Style-000150.safetensors
大小 (KB): 147591
类型: Model
Pickle 扫描结果: Success
Pickle 扫描信息: No Pickle imports
病毒扫描结果: Success