You are not logged in. Please login or register.
SmoothVideo Project → Using SVP → New RIFE filter - 3x faster AI interpolation possible in SVP!!!
Are you sure you followed all the steps?
You should put the v2 models in the new directory `C:\Program Files (x86)\SVP 4\rife\models\rife_v2`.
Thanks. Power consumption has been reduced by 10-15% in the second version.
From my testing comparing v4.6 to v4.8, I only saw the transcoding fps drop by around 3 on average. Not bad. In most cases, artifacts were reduced with the newer model. In rare cases, frames contained new artifacts and are slightly worse than what v4.6 produced. As I said though, this is rare. v4.8 is certainly an overall visual improvement. I did not notice any major difference with my thermals, but I did not measure. I just checked during a v4.8 test and the numbers I was getting seemed similar to what I remember getting previously with v4.6.
It is also worth noting that I measured slight savings in file sizes with the newer v4.8 model. My guess is that this is related to how video data is saved and processed. With less artifacts and random, inconsistent splotches of stray pixels, there are less pixel changes to store between video frames. This leads to minor reductions in the size of the outputted file. On a 3-pass interpolation test, I got a file roughly 10% smaller in size. For normal transcoding usages, I wouldn't expect 10% though. Maybe others can comment on their results and correct me on the logic here if I am wrong.
I just wanted to update and say that I performed visual testing with v4.9, and the results were, in most cases, worse compared to v4.8. In frame comparisons, v4.9 won in only a few cases, but v4.8 was far more consistent and preserved more details in both 2D and 3D scenes. It seems like the consensus on here is that v4.9 provided some performance improvements, but it seems to have worsened the visuals in my testing. Maybe coincidentally, my previous theory seems to be holding up, as v4.9 transcoding outputs yielded slight file size increases rather than decreases.
EDIT:
Forgot to specify that I was running v4.9, NOT v4.9 v2.
Hi,
So I've just reinstalled svp pro 4 from scratch and I get the following error when switching to RIFE mode
I don't know python, so I would appreciate your guidance.
https://imgur.com/a/pp6Ky96
thank you in advance.
EDIT: now it does not throw the error messages, but it gets stuck when TRT ends processing the movie....
can you please help me ?
TensorRT version: 8.5.1
VapourSynth R65
rife_v4.8.onnx
4090rtx
Hi,
So I've just reinstalled svp pro 4 from scratch and I get the following error when switching to RIFE mode
I don't know python, so I would appreciate your guidance.
https://imgur.com/a/pp6Ky96thank you in advance.
EDIT: now it does not throw the error messages, but it gets stuck when TRT ends processing the movie....
can you please help me ?
TensorRT version: 8.5.1
VapourSynth R65
rife_v4.8.onnx
4090rtx
check C:\Program Files (x86)\SVP 4\mpv64\vapoursynth64\plugins
is there a MiscFilters.dll file from there?
also uninstall vapoursynth if you installed it before, only use the one from SVP.
Transcoding speed from my testing:
all v2 1080@30 x2
4.9: 145
4.8: 148
4.7: 149
4.6: 195
Rife 4.10 is out but I strongly recommend leaving it alone because of excessively high GPU usage. But if you wish to try it then YMMV.
Update: I tried v2. After reboot it only made a 1-2% difference for me.
I tried RIFE 4.10 and thought it greatly improved hard coded subs, with previous versions of RIFE the letters mostly get warped to a point when encountering fast motion scenes, now with RIFE 4.10 it's a lot more stable.
The recent Rife networks are being specifically trained for Anime so I suppose any improvements in live video processing is a bonus. But there are so many Anime models I'm not sure why we need another one 
maorgr wrote:Hi,
So I've just reinstalled svp pro 4 from scratch and I get the following error when switching to RIFE mode
I don't know python, so I would appreciate your guidance.
https://imgur.com/a/pp6Ky96thank you in advance.
EDIT: now it does not throw the error messages, but it gets stuck when TRT ends processing the movie....
can you please help me ?
TensorRT version: 8.5.1
VapourSynth R65
rife_v4.8.onnx
4090rtxcheck C:\Program Files (x86)\SVP 4\mpv64\vapoursynth64\plugins
is there a MiscFilters.dll file from there?also uninstall vapoursynth if you installed it before, only use the one from SVP.
Transcoding speed from my testing:
all v2 1080@30 x2
4.9: 145
4.8: 148
4.7: 149
4.6: 195
Hi,
Now I run a fresh SVP installation, with 4.9.
check C:\Program Files (x86)\SVP 4\mpv64\vapoursynth64\plugins
is there a MiscFilters.dll file from there?
yes there is.
Transcoding speed from my testing:
all v2 1080@30 x2
4.9: 145
4.8: 148
4.7: 149
4.6: 195
where do I set it up ? what if I have a 4k movie ?
Thanks for your help, sir.
Now I run a fresh SVP installation, with 4.9.
check C:\Program Files (x86)\SVP 4\mpv64\vapoursynth64\plugins
is there a MiscFilters.dll file from there?yes there is.
can you open the filter? does it show vapoursynth Filter v1.4.7 # svp?
also please post your SVP logs.
also this is just my personal benchmark, not related to your issue
all v2 1080@30 x2
4.10: 113
4.9: 145
4.8: 148
4.7: 149
4.6: 195
well, 4.10 is super heavy, good for ppl with HE graphics and want quality.
...
also this is just my personal benchmark, not related to your issueall v2 1080@30 x2
4.10: 113
4.9: 145
4.8: 148
4.7: 149
4.6: 195well, 4.10 is super heavy, good for ppl with HE graphics and want quality.
Your figures confirm my findings about GPU usage. Rife 4.10 is by far the worst. There is very little quality difference between 4.9 and 4.10 but there is a massive hit on GPU performance. I will probably check out the subtitles issue you mentioned because that would be a major problem.
I tried RIFE 4.10 and thought it greatly improved hard coded subs, with previous versions of RIFE the letters mostly get warped to a point when encountering fast motion scenes, now with RIFE 4.10 it's a lot more stable.
Tested and can confirm my RTX 3090 is not strong enough to be able to push 4K @ 2x
Back to 4.9 for me, so far the best results, but still very demanding 99% GPU usage, so RTX 3090 overclocked is just barely enough for 4K @ 2x
subtitles issue you mentioned
I never mentioned this.
I don't know why you try to use the newest model, just pick the one you like the most. newer doesn't mean better.
also, I checked v2 4.6, and the antialias bug was gone.
zerosoul9901 wrote:I tried RIFE 4.10 and thought it greatly improved hard coded subs, with previous versions of RIFE the letters mostly get warped to a point when encountering fast motion scenes, now with RIFE 4.10 it's a lot more stable.
Tested and can confirm my RTX 3090 is not strong enough to be able to push 4K @ 2x
Back to 4.9 for me, so far the best results, but still very demanding 99% GPU usage, so RTX 3090 overclocked is just barely enough for 4K @ 2x
For Hardcoded Subtitles that are permanently embedded into a video, 4.9 is even worse than 4.8, more Distorted/Warped Subtitles in dynamic scenes, 4.10 is the most stable version i've tested even though the gpu usage is the heaviest
For watching Anime in 1080p with a lot of Hardcoded Subtitles, 4.10 is the best.
Rife 4.11 is out. The file is much smaller than any other Rife model but is just as computationally intensive for GPUs and it has a couple of other small issues. Also I checked 4.9 with my hard coded subtitled files but I didn't have any warping issues so I'm staying with that.
subtitles issue you mentioned
I never mentioned this.
Subtitles was someone else.
I don't know why you try to use the newest model, just pick the one you like the most. newer doesn't mean better.
The reason new models are being released is because they are still evolving through training, so what you are suggesting makes no sense. If 4.6 works for you then fine. But the one I like the most is the one with the least artefacts and best motion and that is currently 4.9+.
Can someone help me with how to make v2 work?
I've updated to the latest Rife 4.11 model on the github, I've chosen the one that is in rife_v2 folder. I've also updated all the TRT backend files manually, and now can use 9.1.0.
I've manually updated the latest .py from master branch on github as well. Now the V1 models work perfectly fine. Forcing the Implementation like to 2 in py makes it use the rife_v2 folder. It starts to generate the cache and does it about 3 times for each video with v2 version. Then after it finishes, the video just doesn't work and mpv closes. Not sure how to fix this.
SVP updated, there're a few changes regarding RIFE/trt:
- added 'akarin' plugin, which should improve seeking performance with v1 models up to v2 level
- put any models (including future ones) into SVP 4\rife\models\rife (for V1 models) and SVP 4\rife\models\rife_v2 (for V2 models) and restart SVP - they all will be listed in the video profile; "ensemble' models are supported too.
- a quick fix for DolbyVision playback (color blinking issue)
- "opt shapes" were not set with latest vsmlrt.py which resulted in engine rebuilding for every video resolution regardless of "perf. boost" option
- included model 4.9
SVP updated, there're a few changes regarding RIFE/trt:
- added 'akarin' plugin, which should improve seeking performance with v1 models up to v2 level
- put any models (including future ones) into SVP 4\rife\models\rife (for V1 models) and SVP 4\rife\models\rife_v2 (for V2 models) and restart SVP - they all will be listed in the video profile; "ensemble' models are supported too.
- a quick fix for DolbyVision playback (color blinking issue)
- "opt shapes" were not set with latest vsmlrt.py which resulted in engine rebuilding for every video resolution regardless of "perf. boost" option
- included model 4.9
Excellent! The new helper script detect any model you add without having to make manual changes, although v12 currently doesn't work. Rife v2 seeking was almost immediate, with akarin the seeking is immediate.
Great update! Nice work and thank you
Edit: They've literally just released an update to v12 and it is working. Will update with results.
Results: Rife 4.12 almost identical to 4.11 but has some fixes. Rife 4.9 still the best overall for me.
SVP updated, there're a few changes regarding RIFE/trt:
- added 'akarin' plugin, which should improve seeking performance with v1 models up to v2 level
- put any models (including future ones) into SVP 4\rife\models\rife (for V1 models) and SVP 4\rife\models\rife_v2 (for V2 models) and restart SVP - they all will be listed in the video profile; "ensemble' models are supported too.
- a quick fix for DolbyVision playback (color blinking issue)
- "opt shapes" were not set with latest vsmlrt.py which resulted in engine rebuilding for every video resolution regardless of "perf. boost" option
- included model 4.9
Thank you!
This should make things a lot easier
SVP updated, there're a few changes regarding RIFE/trt:
- added 'akarin' plugin, which should improve seeking performance with v1 models up to v2 level
- put any models (including future ones) into SVP 4\rife\models\rife (for V1 models) and SVP 4\rife\models\rife_v2 (for V2 models) and restart SVP - they all will be listed in the video profile; "ensemble' models are supported too.
- a quick fix for DolbyVision playback (color blinking issue)
- "opt shapes" were not set with latest vsmlrt.py which resulted in engine rebuilding for every video resolution regardless of "perf. boost" option
- included model 4.9
Thanks for the update, however I can't get it to work. I've reinstalled SVP4 cleanly just to make sure I haven't messed up anything manually. I've tried using V1 models 4.6 and 4.9, however both times the engine is rebuilding for many resolutions, and then after it finishes the video doesn't play.. stuck or something.
Also getting such error:
These are my settings:
Not sure If I am doing something wrong..
why it reads cache from c:\program files\..., it should be the temp dir path here
Which model is currently the best for non-anime content? Most discussions I see are based around anime.
Also, what exactly do the ensemble models do differently?
Which model is currently the best for non-anime content? Most discussions I see are based around anime.
Also, what exactly do the ensemble models do differently?
Don't bother with the ensemble models. Whatever they are supposed to do isn't worth it. Also don't worry about the "anime" tag because they all work fine with non anime stuff. If you have a 30 series Nvidia GPU or above and use TensorRT then try Rife 4.9 if your GPU can handle it or Rife 4.6 and below if it can't.
SVP updated, there're a few changes regarding RIFE/trt:
- added 'akarin' plugin, which should improve seeking performance with v1 models up to v2 level
- put any models (including future ones) into SVP 4\rife\models\rife (for V1 models) and SVP 4\rife\models\rife_v2 (for V2 models) and restart SVP - they all will be listed in the video profile; "ensemble' models are supported too.
- a quick fix for DolbyVision playback (color blinking issue)
- "opt shapes" were not set with latest vsmlrt.py which resulted in engine rebuilding for every video resolution regardless of "perf. boost" option
- included model 4.9
Woah, the default 4.9 model you added cached in like 15 seconds. The 4.9 I added some time ago took a minute and a few seconds to cache.
why it reads cache from c:\program files\..., it should be the temp dir path here
I am unsure, but the default installation is now making cached models inside modules folders instead of the appdata. Does anybody else have such issues?
Nvm. I have managed to fix the SVP4 working fine now, only the folder issue is still present.
EDIT2:
The V2 models don't seem to work on my end. Anybody knows how to fix them? Here is what my TRTexec error log says:
[11/13/2023-21:34:53] [E] Unknown option: --precisionConstraints obey
> only the folder issue is still present
no idea, it's still
> os.path.expandvars("%APPDATA%\\SVP4\\cache\\")
in vsmlrt.py
SmoothVideo Project → Using SVP → New RIFE filter - 3x faster AI interpolation possible in SVP!!!
Powered by PunBB, supported by Informer Technologies, Inc.