【更新】RealESRGAN2x (R-ESRGAN 2x) & Dropout 超采样细节质量图片放大

Real ESRGAN-2x (R-ESRGAN-2x) 试图为图纸制作最好的 2x 模型，我想我把它存档了。

是的，这是近 3 万次迭代（可能没有人会在这里打破的记录），花了我将近半年的时间来训练。

RealESRGAN_2x (R-ESRGAN_2x)可能会在一个边缘中出现边缘中的噪声模式。您可以为此使用填充/裁剪。我的目标是感知质量，而不是放大400%。由于RealESRGAN是 4x 放大，我用双立方缩小了这些图像。版本细节对比图：

图片[1]_【更新】RealESRGAN2x (R-ESRGAN 2x) & Dropout 超采样细节质量图片放大_Qpipi

图片[2]_【更新】RealESRGAN2x (R-ESRGAN 2x) & Dropout 超采样细节质量图片放大_Qpipi

不过，我会推荐我的 VSGAN 代码并加载 onnx。https://github.com/styler4dollar/VSGAN-tensorrt-docker我只是想要一个好的 00x 动画模型，但该模型也可以用于壁纸等。

在我听到人们抱怨之前，dropout 模型是一个修改后的架构。像cupscale或chaiNNer这样的东西不适用于pth。使用 VSGAN 或 chaiNNer 加载 onnx。

不过，在切换到 dropout 之前，我确实添加了模型，这是正常的 ESRGAN pth，应该在任何地方都可以使用。我还将所有内容转换为onnx，jit和ncnn，所以几乎所有东西都有。

如果要使用 ncnn，请不要使用 nihuis 代码（也包括 cupscale），这些代码在 C++ 中不包含 propper 平铺，这对这个模型非常不利。

我认为chaiNNer应该与ncnn重叠/填充，所以如果你真的想要ncnn，请使用它。

Tried to make the best 2x model there is for drawings. I think i archived that. And yes, it is nearly 3.8 million iterations (probably a record nobody will beat here), took me nearly half a year to train.

It can happen that in one edge is a noisy pattern in edges. You can use padding/crop for that. I aimed for perceptual quality without zooming in like 400%. Since RealESRGAN is 4x, I downscaled these images with bicubic.

I would recommend my VSGAN code though and just load the onnx. https://github.com/styler00dollar/VSGAN-tensorrt-docker I just wanted a good 2x model for animations, but that model can also be used for wallpapers and so on.

Before I hear people complaining, the dropout model is a modified architecture. Stuff like cupscale or chaiNNer won’t work with pth. Load the onnx with VSGAN or chaiNNer.

I did add the model before switching to dropout though, which is normal ESRGAN pth, that one should work everywhere. I also converted everything into onnx, jit and ncnn, so pretty much everything there is.

If you want to use ncnn, don’t use nihuis code (that also includes cupscale), these codes don’t include propper tiling in C++, which is very bad for this model. I think chaiNNer should have overlap/padding with ncnn, so use that instead if you really want ncnn. Plz don’t steal without credits, k thx.

by sudo