https://civitai.com/models/305659?modelVersionId=424330
4/2 Update:new Locon version available now.Trained on animagineXLV3.1weight around 0.8 ~ 1.0 works just finestabler and much smaller in size.Trained on animagineXLV3weight around 0.8 ~ 1.0 works just fineMight increase mistakes in drawing hands, but I think it's acceptable.Train with this free colab notebook:kohya-trainer/kohya-LoRA-trainer-XL.ipynb at main · Linaqruf/kohya-trainer · GitHubwith almost conpletely default setting, in free tier底模为 animagineXLV3权重0.8~1.0左右都很好使用之后有可能画手会更容易出错但是体感还好，所以凑合用吧（使用的以下colab脚本：kohya-trainer/kohya-LoRA-trainer-XL.ipynb at main · Linaqruf/kohya-trainer · GitHub几乎全用的默认参数，免费用户也可以白嫖
