Version 2 - trained on 51 images
Improved dataset quality











V2 Update note -> the goal of this update was to get more character likeness and improve details by improving the dataset and increasing training resolution
Trained on AnyLora
To get the best results, please read the description below:
Recommended weight for V1/V2: 0.6-0.8
Activation word for V1: JewelryBonney
Activation word for V2: JewelryBonneyV2
Upscale to 1.5
Using anime SD models is recommended, some semi-realistic checkpoints also work
I would appreciate any reviews, positive or negative!
I would very much appreciate you sharing your results ^_^
If you have any suggestions on what LoRA i should do next, please share them in the comments
Enjoy :)
Version 2 - trained on 51 images
Improved dataset quality
1. 转载模型仅供学习与交流分享,其版权及最终解释权归原作者。
2. 模型原作者如需认领模型,请通过官方渠道联系海艺AI工作人员进行认证。我们致力于保护每一位创作者的权益。 点击去认领
