Anmi Cute

【v1.1】 重新整理了素材，删除了一些质量较低的图片，然后重新训练了一遍，效果应该比1.0更好。

---

更新了一个使用 LoRA 训练的版本，不一定比之前的更好：

An updated version trained with LoRA is not necessarily better than the previous one:

---

该模型基于 /model/28169?modelVersionId=154252 训练的 Loha 得到，我将其以 0.65 的权重合并为一个 checkpoint，因此需要额外的 VAE，推荐：/model/22354/clearvae。

没有特别推荐的参数，可自行尝试，hires fix 效果非常好。

This model is obtained from training LoRA at /model/28169?modelVersionId=154252. I merged it into a checkpoint with a weight of 0.65, so additional VAE is required. Recommended: /model/22354/clearvae.

There are no particularly recommended parameters, you can try it yourself, hires fix works very well.