Yep rife works properly with mpv only

Pezede wrote:
Chainik wrote:

I mean, switch the video profile to movie x2 and start transcoding. Will it only give 72 fps?

Yes that's the case:

https://i.imgur.com/1QMZ4fL.png

Something wrong here. 4090 should be twice as fast (at least). Note that a have few vms in background + game

https://i.imgur.com/EIiZM1L.png

XKCorp wrote:

Hello

In SVP the option "scene change threshold" set to 15% has resolved the slowdowns in fast scenes, I think it sould be set to this value by default.

I am happy with AI model 4.6, there is a noticable improvement since model 4.0. There are still some artifacts (like on vertical bars or subtitles) maybe it could be improved with futur models.

Thanks for your work!

Subs shouldnt affect interpolation. Just get release without hardcoded ones

79

(13 replies, posted in Using SVP)

cemaydnlar wrote:

I found out that svp index changes constantly between 0.98 to 1.01 when i use rife. Is that normal ?

do you see dropped frames ? yes -> bad, no -> good

5) Попробуй Nvenc H265 max bitrate
4) Там есть Loseless флаг. Это точно, я даже пару раз использовал
3) 3070ти умеет 3х (та же нагрузка как 2.5) с небольшим даунскейлом вроде 900р. 2.5x кстати в 2 раза сложнее чем 2х
2) https://www.svp-team.com/forum/viewtopi … 1&p=13 мы вот тут обсуждали сборку. Если задать число пискселей видеокарта обрабатывает в секунду, то оно само даунскейлит
maxIpps = 65000000                  # Max interpolated pixels per second the GPU is capable of
3070ти умеет 65кк, 1080ти около 40кк
Оно в итого неплохо работает
1) https://i.imgur.com/icOP2YN.png

Insindro wrote:
dlr5668 wrote:
aloola wrote:

you can also resize the video to 1600x900 then x3 fps. Work for me, I have a 3070ti.


also, I wish  "ignore HFR source" profile has an option to turn off the "alter video frame size".

I think https://0bin.net/paste/NKODt3ka#aCSb+rh … Uu7S3e2JiD can be ported to svp as well. Ideally it should track dropped frames and reduce resolution based on these. Current iteration just uses hardcode value

maxIpps = 65000000                  # Max interpolated pixels per second the GPU is capable of

I watch 720p and below (old content) x3 and everything else x2 (1080p no changes and 4k downscale to about 1440p)

I'd like to try this out. Where would I put this exactly? I already tried in mpv/scripts however, I get an error regarding the coding in mpv's console. "Unexpected symbol near "#". So I removed any "#" but then I get hit with another error: '=' expected near 'vapoursynth'. Any help would be much appreciated.

I am not sure if it can be used directly. https://www.svp-team.com/forum/viewtopi … 051#p81051 better try portable mpv. Can be unpacked anywhere

82

(13 replies, posted in Using SVP)

cemaydnlar wrote:
Chainik wrote:

none is better or smoother
difference is more threads could rise GPU utilization in case it's too low while output fps is not enough


With 2 threads it uses around 50-55 % of my gpu. With 4 it goes up to 60. Which one should i use ?

Thats interesting. 2 threads @ 3070ti maxes it out. I guess you need more for 3090/4090. Watch for power usage instead of load

aloola wrote:
Insindro wrote:
Chainik wrote:

> Although, anywhere above 48 fps my GPU usage sky rockets from 46% to 90%

because x2.5 interpolation (i.e. 24->60 fps) need generating TWO times more intermediate frames than x2 (24->48)

> I added another model from github and when selected I get a flickering sensation on any video

then add another model big_smile and post a bug report on the Github regarding the flickering one

Ah yes I understand now. I was just basing off from what you said on the rife AI wiki: "1080p@60-72 atleast rtx 3080". I guess a better video card is needed to achieve those frames without dealing with the drop in frames. Also the Github I was testing with was the one you provided on the wiki, all of them flicker through svp, which is odd. I wonder if I'm the only one. Nonetheless, this is better than anything I've used previously.

you can also resize the video to 1600x900 then x3 fps. Work for me, I have a 3070ti.


also, I wish  "ignore HFR source" profile has an option to turn off the "alter video frame size".

I think https://0bin.net/paste/NKODt3ka#aCSb+rh … Uu7S3e2JiD can be ported to svp as well. Ideally it should track dropped frames and reduce resolution based on these. Current iteration just uses hardcode value

maxIpps = 65000000                  # Max interpolated pixels per second the GPU is capable of

I watch 720p and below (old content) x3 and everything else x2 (1080p no changes and 4k downscale to about 1440p)

updated portable rife mpv for 4.4/4.6
Download https://www.playbook.com/s/vadash/ssp9p … ben53VKR1k
VT https://www.virustotal.com/gui/file-ana … M5ODg3Mg==

Original script by Elexor. It can do some cool stuff like auto scale resolution based on GPU performance. This way you can use x3 interpolation even without RTX 3080 (minimum for 1080p)

Chainik wrote:

> and leave 4.4

why 4.4? just because the numbers are higher than 4.0?

ok, 4.0 was removed from the list, but 4.2, 4.3 and 4.4 are still there, w/o any changelog or something like that
is 4.4 better than 4.2?

From flowframes discord

quality 2D:
2.3 > 4.6 ≥ 4.5 > 4.4 > 4.0 > 4.3 > 2.4 > 4.1 > 3.1 > 3.8 > 3.9
quality 3D:
2.3 > 4.6 > 4.5 > 4.3 > 4.4 > 4.0 > 2.4 > 4.1 > 3.1 > 3.9 > 3.8
simple pattern resilience 2D:
4.0 ≥ 3.9 ≥ 3.1 ≥ 3.8 > 4.6 > 4.5 ≥ 4.3 > 4.1 > 2.3 > 2.4 > 4.4
complex pattern resilience 2D:
4.0 > 4.6 ≥ 4.5 ≥ 2.4 > 4.3 > 4.1 > 4.4 > 3.9 > 3.1 > 2.3 > 3.8
pattern resilience 3D:
2.3 > 3.1 > 2.4 > 4.6 > 4.5 > 3.8 > 4.3 > 4.1 > 4.4 > 3.9 > 4.0
speed:
4.0-4.4 > 4.6/4.5 > 3.9 > 3.8 > 3.1 > 2.3/2.4

note:
quality = sharpness and accuracy
2.3 CUDA > 2.3 NCNN | complex pattern resilience 2D: 4.0 > 2.3 CUDA > rest > 2.3 NCNN > 3.x
pattern resilience 2D/3D: 2.3 TTA >> everything 
TTA reduces sharpness, ensemble does not
4.x is preffered over 2.x/3.x in UHD mode (default ≥1600p)
Chainik wrote:

> Do you plan to update SVP with the newer models?

kind of... not exactly like this
there will be only ONE model bundled (*), plus you'll be able to add whatever model you want manually, by copying model's folder

(*) if you _know_ which one from 4.0 to 4.4 is the best in terms of overall quality - this is the right moment to tell

Why should we stick with one ? Remove old ones and leave 4.4 and 4.6 (17,21)

If someone wants to try new models

0 update SVP
1 Download dll and source https://github.com/styler00dollar/Vapou … /r9_mod_v3
2 Unpack models C:\Program Files (x86)\SVP 4\rife\models

Model 4.6 is 7% slower than default svp model

del

UHD wrote:

This is great news!

Until now, I thought there would be some problems based on statements from n00mkrad, who uses RIFE in his Flowframes:

n00mkrad wrote:

HDR is currently not supported as the neural networks only work with 8bpp content.

I can't say if there will ever be HDR support.

https://github.com/n00mkrad/flowframes/ … -803571016

I tried this one https://4kmedia.org/lg-new-york-hdr-uhd-4k-demo/

https://i.imgur.com/nht2Q49.png

18 fps or 1/3 realtime for 4K HDR x2 fps 3070ti

https://i.imgur.com/6kKfAQS.png

and it lost HDR data

UHD wrote:
Chainik wrote:

"Avisynth Filter" is a confusing naming cause there're _two_ different filters there, one for Avisynth and one for Vapoursynth
both supporting 10-bit and hdr

Thanks for your reply. I'm guessing you mean:
avisynth_filter: https://github.com/CrendKing/avisynth_filter

So if I understand correctly whichever combination:

AviSynthPlus-RIFE +avisynth_filter
or
VapourSynth-RIFE-ncnn-Vulkan +avisynth_filter

should be sufficient in SVP for real-time interpolation of 4K 10-bit HDR files using RIFE?

Only for 4090 4k@24fps x2

Chainik wrote:

ну дай т.н. б-г
и всего-то от 1000 евро big_smile (от 1500 в наших широтах)

а я вообще думал что dlss это суперсэмплинг, ну и fps растет за счет того что рендер идет в маленьком разрешении
при чем тут optical flow? или тут теперь дополнительно к суперсэмплингу еще и fps прямо увеличивают интерполяцией?

ага dlss3 состоит из 2 частей - увеличение разрешения и вставка доп кадров как SVP

https://i.redd.it/im94428ll3p91.png

Новый улучшенный (и более быстрый) Optical flow

cjmanca wrote:

I fixed that problem. Apparently Windows has it's own version of Python hidden in "WindowsApps". I got rid of it, and now that error is gone, but it's still not working.

Now when I try to play a video it plays for a half a second and then freezes indefinitely. There aren't any errors in the logs when this happens.

EDIT: So, in Plex it freezes as I said, but in MPC-HC, it just doesn't work. The performance monitor shows the SVP Index at a constant 0.5 (normal framerate, since I have RIFE set to x2). Setting the profile back to Automatic works as expected, it's just RIFE that isn't working (both the CUDA version and the normal version of RIFE in MPC-HC, although in Plex, the normal version works, and CUDA version freezes playback).

EDIT 2: I just found the note at the bottom of the wiki page saying it doesn't work for real-time transcoding, which is what I've been testing it with. That's unfortunate. Any plans to make that work? Also maybe getting it to use the tensor cores?

pytorch version is obsolete. RTX 3xxx works better with VS

94

(4 replies, posted in Using SVP)

Just use x3 and it will work. For example I use x6 for 144hz display (its actually 165 but x6 multiplier is superior)

https://i.imgur.com/TNu3ix5.png

Bonus points for forcing exact rate with CRU

https://i.imgur.com/qIS8gV3.png

kellykline wrote:

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

Enif wrote:

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

forgetikiss wrote:

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

UHD wrote:

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 )

https://i.imgur.com/HAvOxjQ.png