可以理解为LORA V1略微过拟合，而V1.5。。见正文

by wizardt - opened Feb 13, 2023

Feb 13, 2023

可以理解为LORA V1训练时使用了较为单一的数据集，脸部风格会比较统一，略微overfitting；
而V1.5的数据集更多元化？不知道是否是这样，请教

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment