QualityScaler: Image/video deeplearning upscaler with any GPU

For anyone interested in different upscaling models, there is a collection in the wiki here:<p><a href="https:&#x2F;&#x2F;upscale.wiki&#x2F;wiki&#x2F;Model_Database" rel="nofollow">https:&#x2F;&#x2F;upscale.wiki&#x2F;wiki&#x2F;Model_Database</a><p>My personal favourite is Remacri for photographs, but you should download a few of them and try what works best for the photo&#x2F;image you have.<p>You can use either Automatic1111&#x27;s repo for stable diffusion to try them out (put the model file in the ESRGAN directory), or also chaiNNer (<a href="https:&#x2F;&#x2F;github.com&#x2F;chaiNNer-org&#x2F;chaiNNer" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;chaiNNer-org&#x2F;chaiNNer</a>)

A VERY similar project was submitted to Awesome F&#x2F;OSS, Upscayl:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;upscayl&#x2F;upscayl" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;upscayl&#x2F;upscayl</a><p>Wonder what the comparison is…

Windows Defender says that the binary has Trojan:Win32&#x2F;Wacatac.H!ml inside it.

This looks fancy. Any chance of anyone implementing this as a ffmpeg filter?

How does this compare to Real-ESRGAN?

Is it better than waifu2x?<p>Nothing I&#x27;ve tried is. I might try this one out to see, but if anyone who has can comment on how it compares, I&#x27;d appreciate it.

What kind of input do you need?<p>I&#x27;m getting poor results trying with some stamps I&#x27;ve scanned and some photos that were lower resolution than I liked.<p>Or does it need to be studio quality footage?

It looks pretty good, but especially with the Spiderman comparison you can notice a little smudging and it basically loses the pattern on the suit.

Looks to be limited to running on Windows only.

Anyone found something like this for audio?

Are any open source image denoisers available ?