JackeyDeng

yes, I want the pretrained model too.


Well, But those colorful noise is due to data out of bounds, this will lead to output's DCT totally different from expected. No frequency will be masked. ...

hello, I met the same problem when loading my self-trained stablesr model, have you solved the problem?

Hi, it seems it's the problem of sr scale, when I do 1XSR, the result lacks fidelity, but 4XSR result is much better. left is ori img(720*720), mid is 1XSR...

> > 好，看来是sr比例的问题，当我做1XSR时，结果缺乏保真度，但4XSR结果要好的分割。左边是ori img(720 _720)，中是1XSR结果(720_ 720)，右边是4XSR结果(2880*2880) 4XSR结果与您提供的结果几乎相同。为什么1XSR不那么好？  > > Hello, may I ask how to change the code to be able to 4XSR? In the python file...

Hi I am still a little confused. Why is the latent of HR image is needed when training CFW rather than the latent of LR image. I think the latter...