A LoHa model trained by a friend qslengjing with multires noise.

This is a LoHa model that trained by 100+ img,and it's the multires noise version.

This model can achieve more detailed shadow segmentation effects and depict the different parts of scenery under light in the afternoon.

This will make the lighting effect more similar to afternoon and dusk at Niji v5.

weight 1.0 maybe generates better img.

由朋友qslengjing 训练的具有多分辨率噪声的 LoHa 模型。

这是一个经过 100+ img 训练的 LoHa 模型，它是多分辨率噪声版本。

该模型可以实现更细致的阴影分割效果，描绘出午后光线下风景的不同部分。

这将使光照效果更类似于Niji v5的下午和黄昏。

权重 1.0 可能会生成更好的图像。