Search options (Page 5 of 8)

SVP devs please provide the avisynth rife.dll too with same fix applied. Maybe it won't have the seek crash.
Thanks!

We want this:
1. to just keep stuff up to date whenever possible
2. to see if gerappa can use 2 threads if that line was turned into a warning:
more specifically it mentions on this commit that they changed the crashing "gpu_thread must be between 1 and 1 inclusive" into a warning:
https://github.com/styler00dollar/Vapou … r9_mod_v14
3. maybe u can recompile the old SVP compatible vs_rife.dll file with that fix so gerappa can check if it unlocks that extra thread?

Refund the Radeon RX 7900 XT and get any cheap RTX.
Or downgrade the driver like gerappa managed to fix it here:
https://www.svp-team.com/forum/viewtopi … 001#p84001

According to this video it says that installing "Driver Only" prevents issues:
https://www.youtube.com/watch?v=xCX3acP3At4&t=128s
Does the GPU thread issue persists even in this case?

gerappa try to go to
https://github.com/styler00dollar/Vapou … n/releases
and download each windows .dll from recent releases, rename it to rife_vs.dll and replace the initial "C:\Program Files (x86)\SVP 4\rife\rife_vs.dll"

more specifically it mentions on this commit that they changed the crashing "gpu_thread must be between 1 and 1 inclusive" into a warning:
https://github.com/styler00dollar/Vapou … r9_mod_v14

not sure if it would actually fix anything, but please take a look.
Thanks!

Sounds like you made it work, well done!

From what i see if i revert the following step, the old SVP vsmlrt.py file still works for all models including latest 4.17_lite.

Step 5: Edit helpers.py replace line 52
old TensorRT 8.5:
return RIFE(clip,multi,1.0,None,None,None,model_num,backend,ensemble,implementation)
new TensorRT 10.1:
return RIFE(clip,multi,1.0,None,None,None,model_num,backend,ensemble,True,implementation)

And i didn't see any signficant improvements if i replace it with latest vsmlrt.py file from last week:
https://github.com/AmusementClub/vs-mlr … /vsmlrt.py

So for now we can continue using the old file until somebody notices something.

I noticed that if i exit specific background apps like TeamViewer, i suddenly get 20-30 extra fps with SVP.
I believe TeamViewer reads the memory and causes a bottleneck even when it's minimized in taskbar.

Xenocyde try to close your 200 Chrome tabs and other background apps and see if u find the specific app that causes that microstuttering. It's good to know.
Try it with the 4.17 lite version cause it's easier on the GPU:
https://github.com/AmusementClub/vs-mlr … nal-models
Or... nevermind, try with other models.

Poor developers, they haven't heard of 60 fps yet.

2-3 stutters per 40+ minute sounds actually OK.
In mpv.conf the lines with "#"  in front are actually comments, so u can delete them. I only wanted u to check if u add these to see if it improves anything:

gpu-api=d3d11
video-sync=audio
d3d11-sync-interval=0

"but I was getting screen tears"
If u see these then try above commands while keeping Nvidia Control Panel Vsync enabled.
The commands are meant for mpv to display stuff faster internally
If no visible improvements, then keep what u were using before that had the most stable fps.

There are specific scenes where RIFE doesn't know how to scene change and might cause microstutters, but otherwise seems fine to me.

Joke: Double your fps target so it will half the microstutters duration.

Did u try to enable Statistics in Nvidia App and check if you are giving extra breathing room for your GPU?

For example if it mentions your assigned fps target but it shows something like 98% GPU usage and the FPS value keeps dropping under it like this:
https://gyazo.com/1d9f9788ebecaadbca8a74f8ccd5bb0d
then u should resize it down a bit until your GPU usage % goes down and your FPS value is more stable like this:
https://gyazo.com/a4829e2299a9c51fec02e24ff41c8e29
That should lower significantly the instances when micro stutters happen cause of low resources.

Ooh by the way if u accidentally use the vsmlrt.py from 9.2 archive it will fail to find the rife_v2 folder models.
Attaching below the out of the box SVP vsmlrt.py file cause it still works with 9.2 and can also find the rife_v2 folder models.

I would recommend converting them all to .mp4 using any online video converters you can still find, before Indeo 5 becomes fully abandoned.
Try this one
https://video-converter.com/
or this one
https://convertall.com/en/ivf-converter
Then you should be able to see them in 60 fps with MPC-HC.

Anime4K has a guide on how to add shaders in Plex Media Player, try to see if works
https://github.com/bloc97/Anime4K/blob/ … ws_Plex.md

Gram loss is a type of loss function used in style transfer tasks to capture and preserve the texture and style of an image.
In the context of neural networks and machine learning, FILM stands for Frame Interpolation for Large Motion. It refers to a specific model or algorithm designed to perform frame interpolation, which is the process of generating intermediate frames between existing ones to create smooth transitions, typically in video sequences.
So i think it improves this type of scenarios where the character is hidden temporarily behind an object:
https://github.com/hzwer/Practical-RIFE/pull/23