https://github.com/deepghs/waifuc/tree/main
The model data source is derived from Waifuc, a highly robust tool for crawling, filtering, and processing training sets. With the aid of the Waifuc tool and a single 5600g machine, it is possible to efficiently crawl and process over 3000 training images within a span of 2 hours. Training the character "Lora" on this extensive dataset yields significant performance advantages compared to situations with limited data availability.
↑ Translation from gpt.
My english is not good and can‘t directly show my thoughts.
waifuc is really a powerful and fantasy tool.
please use v2.0 ,it train base more than 2000 images from internet.
it's better than v1.0.
temp final ver, before train methods get big enough boots.
用v2.0就行,筛选处理完用2000多张图训练的。
效果会比之前的强很多,训练集大了以后很多问题都没了。
在训练方法有大更新前暂定为终稿了