Memo-Ray is a model finetuned on ACertainty.

Compared to the Merge model, the Merge model tends to be overfitted. It does not always adhere to your prompts and may add irrelevant details. In contrast, the finetune model does not have these issues.

Memo-Ray model is a finetuned model trained on carefully selected illustration images and characters, at a resolution of 768. During training, offset noise is used to enhance the perception of light and shadow in the generated images. Just as the name suggests, this model focuses on ray formation, shadows, and addresses the limitations in accurately generating night, twilight, and lighting effects.And i think it's good at generate young anime girl.

Of course, there are many other aspects of this model that I haven't specified. However, given the limitations imposed by Civitai's guidelines, I cannot provide further details here. You are encouraged to explore and discover them on your own.

NOTE:

I strongly recommend using hire.fix to generate images.

Because of offset noise include the model,so it is not compatible with LoRA that also include offset noise.An evident manifestation would be color distortion and blurred images. If you insist on using both, the suggested solution is to download the offset noise lora and set the weight to a negative value, such as -1 or -2.

And refrain from using this Lora when using the model under normal circumstances.

If you wish to merge this model and release, please mark out the model.

Introduce_CN

Memo-Ray是在ACertainty上微调的模型。

相对于Merge模型，Merge模型往往会过拟合。它并不总是遵循您的提示，并可能添加不相关的细节。相比之下，微调模型没有这些问题。

Memo-Ray模型是在精心挑选的插图图像和人物上进行微调的模型，在768分辨率上训练。在训练过程中，使用偏移噪声来增强生成图像中的光影感知。正如其名称所示，该模型专注于光线、阴影的形成，并解决了准确生成夜晚、黄昏和照明效果等问题。我认为它擅长生成年轻的动漫女孩。

当然，还有模型的许多其他方面我没有具体说明。然而，考虑到Civitai的限制，我无法在此提供进一步的细节。建议您自行探索和发现。

注意：

强烈建议使用高清修复(hire.fix)来生成图片

由于模型中包含了偏移噪声，所以与同样包含偏移噪声的LoRA不兼容。明显的表现将是颜色失真和画面模糊。如果您坚持同时使用它们，建议下载推荐资源中的LoRA，并将权重设置为负值，例如-1或-2。

请在正常情况下避免在使用该模型时使用这个LoRA。

如果您希望Merge并发布此模型，请标注出该模型的出处。