Ohisashiburi(お久しぶり) Style lora

使用お久しぶり老师的PIXIV非会员图像生成，仅供学习参考，禁止商业使用，若有侵权联系删除。

需要注意的是，由于我脸部和画风训练均作了分别训练，在生成图像时推荐使用After Detailer重绘。在我的384×640图像中，迭代步数设置为35，同时After Detailer为设置边缘模糊度8，蒙版模糊7，独立迭代步数28.推荐使用Silicon29作为sd模型。

同时我还有更高迭代步数的模型，但多若是训练步数过高就少有点画蛇添足了，这里选择我经过x-y轴测试后与久见老师画风最相似的模型上传。若有需要我也可以再次上传更高步数的。

Google Translate:

Generated using the pixiv NON-member images of Ohisashiburi, it is for learning reference only. If there is any infringement, please contact us and delete it.

It should be noted that since I trained the face and painting style separately, it is recommended to use After Detailer generating images. In my 384×640 image, the number of iteration steps is set to 35, while the After Detailer using face_yolov8n.pt sets the edge blur to 8, the mask blur to 7, and the number of independent iteration steps to 28. Recommended to use Silicon29 as the SD model.