Search options (Page 1 of 3)

Hello everyone. Video image upscaling is around with varying degrees of quality, but I am curious if anyone has gotten this done with svp? Here is an example https://www.youtube.com/watch?v=FtP4Hv665Yg

The video is rather old, and I havent looked into the various other softwares that claim to do this, but there are whole communities that are dedicated to restoring old tv shows in this manner.

DragonicPrime wrote:

arizer wrote:

I have exclusive fullscreen enabled in MPC video renderer, have tried switching all the available settings but my LG CX fps meter stays at 118fps when playing video at 48fps or whatever fps.
Edit: I actually got it working in MPV now, but would prefer MPC-HC.

How did you get it working in MPV? It used to work for me, then it just stopped at one point and I haven't been able to enable it again

I have these in my mpv.conf which is located at c:\Users\username\AppData\Roaming\mpv. Create the file if it's not there.

fullscreen=yes
d3d11-exclusive-fs=yes
input-ipc-server=mpvpipe

volume=100
volume-max=100
video-sync=audio
hr-seek-framedrop=no

fbo-format=rgba16hf

vo=gpu-next
gpu-api=d3d11
hwdec=auto-copy
hwdec-codecs=all
gpu-context=d3d11
drm-vrr-enabled=no
d3d11-sync-interval=1

This is my full mpv.conf which also enables Dolby Vision decoding:
"target-peak=800" is screen's maximum peak brightness in nits, in my case (LG CX) it's 800 nits.

fullscreen=yes
d3d11-exclusive-fs=yes
input-ipc-server=mpvpipe

volume=100
volume-max=100
video-sync=audio
hr-seek-framedrop=no

fbo-format=rgba16hf

vo=gpu-next
gpu-api=d3d11
hwdec=auto-copy
hwdec-codecs=all
gpu-context=d3d11
drm-vrr-enabled=no
d3d11-sync-interval=1

target-peak=800
target-trc=pq
target-prim=bt.2020

tone-mapping=spline
tone-mapping-mode=luma
gamut-mapping-mode=perceptual
tone-mapping-param=bt.2390
tone-mapping-max-boost=2.0

dither=error-diffusion
error-diffusion=burkes
dither-depth=10
spirv-compiler=auto

target-contrast=inf
target-colorspace-hint=yes
hdr-compute-peak=yes

osd-level=1
osd-bar-w=25
osd-color=0.5
osd-bar-align-x=0
osd-bar-align-y=-1

scale=ewa_lanczos
cscale=ewa_lanczos
dscale=ewa_lanczos
tscale=ewa_lanczos

Hello guys.♥
I have downloaded and activated RIFE AI engine. But every movie I run, it's still on automatic mode!
I resrtart the PC, but it was not fixed.
Please help me to disable the program from automatic mode.
i have windows 11 & RTX 4090.

https://imgtr.ee/image/I7C5vD
https://imgtr.ee/image/I7C69s

I run SVP with 1920x2160 files. With 4.7 GPU utilisation averages about 75%. With 4.6 the average was around 53%. That's a pretty big jump which as I said I'm fine with. But I do wonder if there is any optimisation that is still to be done or is the new model simply more dense with information so it is what it is?

DragonicPrime wrote:

Thanks for the post. This sounds interesting. I'm not a programmer or anything so idk how much I can help, but I'd love to test it and share my results when possible. The thing I'm most curious about is probably the performance. A big benefit of Rife is being able to run it in real time now, so would love to see how this new model would perform and how the quality is in different videos. I'm looking forward to seeing more on this.

Unfortunately, this method is relatively slow, at least compared to RIFE, see Table 1: https://arxiv.org/pdf/2211.11423.pdf

Tensor Cores optimisation will probably significantly speed up the inference. For now, however, we need to have a model that is most useful to us, then we will think about what to do next.

I don't think anything is going to replace RIFE in the near future in terms of performance speed, but for lower resolution video, for video encoding where the highest possible quality is needed we may be looking for something better, albeit slower.

If graphics cards double in power every 2 years, who knows if BiT won't replace RIFE for real-time interpolation in a while, even though it will be slower. After all, for 4K the bottleneck for RIFE is probably no longer the graphics card but RAM.

Then there is the issue of directing researchers to move towards Joint Video Deblurring and Frame Interpolation, which I want to do, through my project, which still needs a lot of work: https://github.com/AIVFI/Video-Frame-In … g-Rankings

DragonicPrime wrote:

cemaydnlar wrote:

Is there a way to get a better quality without upscaling. I am using a 1080p monitor. I watch 1080p anime but can i make it look better with some sort of glsl ? Does anime4k work like this or do i need a 4k monitor ?

I used to use anime4k on my 1080p monitor and it still worked even in 1080p videos

Can u give me a fast guide for anime4k and how to use it ?

DragonicPrime wrote:

I just use Anime4k. Might not be as good as full upscalers, but it gets the job done for me and makes anime looks significantly better imo. here's the link in case anyone wants it. https://github.com/bloc97/Anime4K

Its pretty good. Just press ctrl+1 for 1080p anime and ctrl+2 or 3 for low quality old one

DragonicPrime wrote:

Tried to do both. Same result. Not sure what's wrong

try to use AIDA64 to benchmark your DDRAM first.