You are not logged in. Please login or register.
SmoothVideo Project → Posts by dlr5668
Would a 4080 or 4090 be capable of running RIFE on full HDR 4K ?
How does it perform currently on a 3090?
Its not out so its hard to gauge. Its reasonably to expect 4090 if 80% faster in rife compare to 3090. And 3090 is 70% faster than my 3070ti (10496 vs 6140 cuda cores)
22 * 1.7 * 1.8 = 67 > 48 so it seems doable. I dont have HDR source so its SDR math
Hello!
.
Sadly GTX wont be able to do realtime. Your best bet is to get 3060 for 1080p realtime x2. 4k is still not possible, maybe with 4090
UHD - Thank you very much for the feedback. I am wondering, with whatever graphics card you have, how many fps can you get when transcoding a 4k or 1080p video with rife in SVP?
Also, I seemed to have found some kind of solution for the video choppyness/stuttering when played back at very slow speeds.
In the MPV config file I changed this setting: "video-sync-max-video-change=5"
to =0 and that seemed to help a lot, the videos run a lot smoother at slower speeds although occassionaly they may still stutter, it seems much improved from before.
I have no idea why this works or what the setting is, it seems to have something to do with a reclock replacement in MPV or something, I have no idea.
I am just glad it seems to work well now!
Thank you very much everyone for all your help with this!
Check rife thread. For example 3060 can do 1080p x2, 3070ti - 1440p x2
I recently helped friend setting up SVP. It was as easy as manual install + copy mpv setting folder to appdata (optional). RIFE worked fine out of the gate
WOW! Thanks for the instant reply!
Yes, I'm planning on undervolting as well.
Are these really the results for x5 interpolation tests for a 1920x1080 23.976 fps?
What exactly is the card model without coil whine?
its after 30 sec of 1080p x2 encoding (I dont think it matters). Its https://www.zotac.com/us/product/graphi … treme-holo Encoding always use all GPU resources
GeForce RTX 3070 Ti
stock - 260W - 90 fps
All tests below run with undervolt 0.9v @ 1920. No coil whine as well
110% - 205W - 89 fps. Thats why you undervolt you RTX
50% - 155W - 81 fps
45% - 140W - 68 fps
40% - 125W - 50 fps
32% - 100W - 26 fps
My curve is not optimal. With some dedication you can increase result for below max TDP. I am sure you can run 0.825V @ 1800 (stock curve is 0.825V @ 1600 )
FSR1 was ported long ago https://gist.github.com/agyild/82219c54 … 65ce0b0ce5 as shader. It OKayge, nothing crazy
FSR2 is worthless for us since its based on engine data like depth, motion vectors. It can be used only in games
You can already downscale source here 
and use FSR on top as shader
And DLSS > FSR1 (and 2 probably) any day. QHD with DLSS Performance (second to worse option) is better than best FSR. DLSS is already builtin in new version of UE4/5, Unity so we will see spike in 2-3 years with new releases
Chainik wrote:I wouldn't run RIFE on GT 710...
Any particular reason?
Again, I'm only looking to transcode files, I'm not looking to affect streaming video in real time.
Its old card https://forums.developer.nvidia.com/t/h … 1-0/147053
Best case you will get 1 fps realtime with it. Not worth hassle
PS minimum card u should try rife on is 2060 mobile
Is there a way to downscale 1080p/4K content down to 720p BEFORE RIFE interpolates it live?
The objective is to have my high resolution videos downscaled to 720p so that I can use x3/x4/x5 RIFE.
With MPC/ffdshow, this was easily done by just rescaling the video in a step above AVISynth, in the FFDshow settings... I can't figure out a way to do it on mpv...
Thank you.
my spec. AMD RX 5900 + RTX 3070ti + Win 11 + nvidia driver 512.59
RTX 2x/3x should skip pytorch. It actually slower
Working great, thanks. Using x4 for 720p or less (old content) and x2 for 1080p
Short version: how to get started with RIFE and SVP. when i select RIFE AI nothing happens. it would be great if someone point me correct directions (specs: I7 12700F, RTX 3080 and 32 GB RAM)
LONG VERSION: HI guys, i am using vapoursynth with pot player and it works flawless and SVPcode to transcode and save videos locally. Recently I started using SVFI (steam) to permanently convert videos and there is noticeable difference both in video quality/smoothness and very minimal artifacts. So i am wondering if anyone could teach me to setup SVP with RIFE with MPC/potplayer. Thank you all.
uninstall svp, reboot, install rife + mpv
I hadn't used SVP for 4 months, and the 4px mode didn't work in nVidia Optical Flow before (it made everything look blocky and jerky). But it appears to work well now!
Is it working now?
Was it broken before? Or was it just my installation?
svp just call driver. So new version of hardware / new driver can make it better
last ncnn optimizations are nuts yep
2.3x for RTX 3000 and 1.7x for RTX 2000
Seems like PyTorch is not needed anymore
function gen_vs()
{
// RIFE override for low resolution
// Make sure default profile for such content is set to Automatic and interpolation disabled
// https://imgur.com/a/cx6cKo5
if(media.src_fps < 51 && media.dst_h_par * media.src_fps <= 1.2 * 1080 * 30)
{
profile.rife = true;
profile.rife_model = 9;
profile.rife_threads = 2;
profile.rife_gpu = 0;
}> Is it possible to now run RIFE at real time on a RTX 2070 Super & 5800X CPU?
1080p - probably yes, you'd better try it yourself
any progress on making rife profile use generic rules ?
dlr5668 wrote:
demo 1 720p file - v4 model - 3070ti from https://www.svp-team.com/forum/viewtopi … 721#p79721
Thanks for the test! Amazing performance boost!
Interpolation x2 and 188.2fps means 94.1 original frames and 94.1 interpolated frames per second. This means that we can have real-time x4 interpolation without any problem - 25 original frames and 75 interpolated frames!!!!!
Am I counting correctly?
Dlr5668, have you tried x3 and x4 realtime interpolation with this new RIFE filter?
Does the "gpu_thread" setting affect fps, %GPU, VRAM?
1)only x2 works
2)each thread takes 0.5 GB VRAM for 1080p. 1 gives - 50% fps, 2 and more - 100%
Can we enable rife profile as default ? I want to use it for <1080p content. Regular rules dont work
SVP updated.
rtx 2060, 720p: ~70 fps with v4 model, ~35 fps with v3 model (was ~8 fps before)
real time: works in mpv but for some unknown reason doesn't work well in MPC-HC + Vapoursynth Filter (only gives 0.25 SVP index)
demo 1 720p file - v4 model - 3070ti from https://www.svp-team.com/forum/viewtopi … 721#p79721
So, if anyone had the knowledge and skills on how to run RIFE ncnn Vulkan and compare performance I would greatly appreciate it.
RIFE ncnn Vulkan versions for comparison:
1. Release 20210520: https://github.com/nihui/rife-ncnn-vulk … g/20210520
RIFE 3.1This version is based on the current VapourSynth filter: https://github.com/HomeOfVapourSynthEvo … cnn-Vulkan used by SVP
2. Release 20220330: https://github.com/nihui/rife-ncnn-vulk … g/20220330
RIFE 4.0It is important to use both versions to get an idea of how much the performance of the new version of the VapourSynth filter should increase by, which we request here: https://github.com/HomeOfVapourSynthEvo … /issues/14
The file is the comparisons: the same one on which tests have already been performed several times on this thread:
original demo video from the creator of RIFE at: https://github.com/hzwer/arXiv2020-RIFE
720p (1280x720), 25FPS, 53 s 680 ms, 4:2:0 YUV, 8 bits
direct link: https://drive.google.com/file/d/1i3xlKb … sp=sharing
From discord
And since a few days we also have a new v4.1 model: https://github.com/hzwer/Practical-RIFE
Has anyone already tested the interpolation quality of the new model and its performance?
Good news that we can just replace 4.0 flownet file and it will work without errors. No need to wait vs rife update
A few hours ago:
RIFE ncnn Vulkan - Release 20220330:
https://github.com/nihui/rife-ncnn-vulk … g/20220330"update ncnn with nvidia tensorcore optimization"
I'm extremely curious, how much of a performance boost can this give?
If it could manage to get performance close to vs-rife: https://github.com/HolyWu/vs-rife that would be something great
Dont think it will be faster than cuda version
Nurk still looks better https://www.svp-team.com/forum/search.p … er_id=7145 if you dont have GPU/time for RIFE
Chainik wrote:Instruction simplified: Python & Vapoursynth updated via SVP's maintenance tool
=== RIFE / PyTorch installation ===
0. Switch to Python 3.9 and Vapoursynth R57
===> Run SVP's update tool!
1. Dependencies installation:
--------------
download https://bootstrap.pypa.io/get-pip.py into SVP 4\mpv64run cmd as Administrator
cd SVP 4\mpv64run
python get-pip.pyrun
python -m pip install torch==1.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html python -m pip install vsrifewill download 3+ GB and unpack it into 6+ GB of data
2. SVP modification
---------------
replace SVP 4\script\base.py and SVP 4\script\generate.js, restart SVPin the "RIFE AI engine" video profile set
- "Test-Time Augmentation" (TTA) = Disabled -> use RIFE/ncnn/Vulkan
- TTA = enabled -> use RIFE/torch/CUDA"Math precision" = fp16 or fp32
"GPU device" -> choose device in case there're several CUDA devices in the system."AI model" and "GPU threads" change nothing.
Thank you very much. I am not an advanced user, I just followed this easy explanation and now I have a RIFE that works, because the one built in RIFE in SVP did not work for me, it just gave me black screens in every other frames.
I want to ask which RIFE model I now use with the default setting that came with the explanation? I have tried all RIFE model with the program "Flowframes" and know that 3.8 is much better than all the others. Model 4 is fast, but comes with much more artifacts than 3.8 for example. I hope that I am now using 3.8.
I like SVP much better than Flowframes when using RIFE, because with SVP the interpolation starts instantly, so I not have to wait for the program to identifying scen changes, extracting every frame in the movie, and then interpolating those frames on disk so I end upp with some million pictures on disk for every movie I want to interpolate. That is to much hammering on the SSD.
I also want to know if anybody have find a way to make RIFE in SVP work with 4k and not only 1080p, because I know that RIFE is able to handle that, because in Flowframes it works. When I try to use RIFE in SVP, it produces vertical lines in the video when transcoding 4K material, but only half of the screen gets this vertical artifacts.
An other thing is that when using RIFE on 4k material, I can only use math precision 16 and not 32, because that made the 4 gb in the graphic card not being enough. How can I solve that without buying a new card? (HP support tells me that I can not put in another graphic card in my Pavillion All in one :-( ). I know there are some methods to solve this because math precision 32 in Flowframes, did not exceed the limits of my graphic card. The error report that I got gave me some indications that it may be a memory handeling method for solving this. I tried all options conserning GPU threads.
Remember that I am not an advanced user. Please talk to me as I am 7 years old. Lol. I managed to Install the Cuda capable RIFE in SVP but I have not understood what was really happening and why this can not be the default RIFE and so on. 6 gb pytorch is not normal? :-)))
4.0 works the best for me. I watched at least 10 hours with it
SmoothVideo Project → Posts by dlr5668
Powered by PunBB, supported by Informer Technologies, Inc.
