08.10.2024, 04:53
Using aWarpsharp2 with Depth 32 on chroma only and then SCUNet, I get:
![[Image: grafik.png]](https://i.ibb.co/PWsdL0B/grafik.png)
Using SCUNet and then aWarpsharp2 with Depth 32 on chroma only, I get:
![[Image: grafik.png]](https://i.ibb.co/GQrkgVm/grafik.png)
You could add some sharpening or even try CodeFormer(on some sources CodeFormer will perform well, on others not; CodeFormer requires the torchAddon) or maybe both.
![[Image: grafik.png]](https://i.ibb.co/6RsrS90/grafik.png)
If content seems too flat after denoising, try adding some grain.
![[Image: grafik.png]](https://i.ibb.co/TKR5GRF/grafik.png)
You could even use some machine learning based upscaler:
![[Image: grafik.png]](https://i.ibb.co/7WY0MVx/grafik.png)
(side note: Hybrid currently does not allow switching the resizer per scene and when using machine learning based resizers/filters make sure to check different scene, since their effects can vary a lot depending on the scene/source )
There is ton if stuff you can do, but it will require computational power, tweaking to find good value and time.![Smile Smile](https://forum.selur.net/images/smilies/smile.png)
=> Happy tweaking and finding the best settings for your preferences.
Cu Selur
Ps.: if you got the time and motivation, you can adjust settings per scene.
![[Image: grafik.png]](https://i.ibb.co/PWsdL0B/grafik.png)
Using SCUNet and then aWarpsharp2 with Depth 32 on chroma only, I get:
![[Image: grafik.png]](https://i.ibb.co/GQrkgVm/grafik.png)
You could add some sharpening or even try CodeFormer(on some sources CodeFormer will perform well, on others not; CodeFormer requires the torchAddon) or maybe both.
![[Image: grafik.png]](https://i.ibb.co/6RsrS90/grafik.png)
If content seems too flat after denoising, try adding some grain.
![[Image: grafik.png]](https://i.ibb.co/TKR5GRF/grafik.png)
You could even use some machine learning based upscaler:
![[Image: grafik.png]](https://i.ibb.co/7WY0MVx/grafik.png)
(side note: Hybrid currently does not allow switching the resizer per scene and when using machine learning based resizers/filters make sure to check different scene, since their effects can vary a lot depending on the scene/source )
There is ton if stuff you can do, but it will require computational power, tweaking to find good value and time.
![Smile Smile](https://forum.selur.net/images/smilies/smile.png)
=> Happy tweaking and finding the best settings for your preferences.
Cu Selur
Ps.: if you got the time and motivation, you can adjust settings per scene.
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.