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. 轉载模型僅供學習與交流分享,其版權及最終解释權归原作者。
2. 模型原作者如需認領模型,請通過官方渠道联系海藝AI工作人員進行認證。我們致力於保護每一位創作者的權益。 點擊去認領
