这个模型使用了超过500张高质量的原始图片进行训练。

这个模型拥有很好的画风模仿效果，训练图片全部来自该画师的原画集。

相同训练集和训练参数情况下，这个SDXL版本的LORA模型可以全面超越SD1.5，非常惊艳！

illustriousXL 版本：https://civarchive.com/models/1078792

Pony XL版本：https://civarchive.com/models/448326

SD1.5版本：https://civarchive.com/models/87208

推荐权重：0.6~1.0

推荐CFG：4~5

推荐模型：Animagine XL V3

--- --- --- --- --- --- --- ---

This model used more than 500 high-quality original pictures for training.

This model has a good effect of restoring the artist's style.The training pictures are all from the original painting collection of the artist.

With the same training set and training parameters, this SDXL version of the LORA model can completely surpass SD1.5, which is amazing!

illustriousXL version：https://civarchive.com/models/1078792

Pony XL version：https://civarchive.com/models/448326

SD1.5：https://civarchive.com/models/87208

Recommendation Weight：0.6~1.0

Recommendation Weight：4~5

Recommendation Model：Animagine XL V3