CivArchive
    Yojouhan/Asian Kungfu Generation Album cover/Yoru wa Mijikashi/Nakamura Yusuke Styled Lora (四畳半/夜は短し歩けよ乙女/亚洲功夫小子/中村佑介) - v1.0
    Preview 4987785
    Preview 4987792
    Preview 4987835
    Preview 4987780
    Preview 4987793
    Preview 4987805
    Preview 4987836
    Preview 4987786
    Preview 4987790
    Preview 4987916
    Preview 4987829
    Preview 4987789
    Preview 4987787
    Preview 4987781
    Preview 4987784
    Preview 4987783

    Overall

    This is an stable diffusion lora model, the training dataset with tag words have been placed in training set file. If you would like to use this model just use the safetensors with weight:1 would be ok. Feel Free to use my dataset! https://github.com/RuotongX/SD-Nakamura-Yusuke-lora The base model checkpoint is Anylora(LCM), this lora perform best in this checkpoint. The other checkpoint works but not perform good.

    Tag

    You don't need any trigger word, just import this lora would be ok.

    The keywords could be found in my showcases, if you need more you could go to my github and see my training set's tag.

    Recommanded checkpoint

    In version 2, since the base model has been switch to NAI, this lora has pretty decent suitability. But from my test, currently the TMND V checkpoint has the best performance.

    https://civarchive.com/models/27259?modelVersionId=93612

    Description

    Initial release.