RickyAstle98 wrote:

You didnt understand my post, its only realtime playback bug, the models are normal, just a MPV bug, which I can fix just reencode source files! Thats because I dont give rendered example, models frame handling broken only with realtime playback! Anyway I found a fix, maybe someone facing this bug, just reencode files, voila! And how strange its sounds, I record realtime playback, and there I didnt see issue, thats why I dont give examples, even recording ontop!

So maybe I also misunderstood. I thought the video would show the artefacts but I see none. Are you saying that I have to play the clip on PC using Rife?

RickyAstle98 wrote:

This is how issue look like (video is predelayed for showcase purposes) >
https://drive.google.com/file/d/1tGmkW6 … ojEPp/view

I don't see anything even after slowing it down. What am I supposed to see?

RickyAstle98 wrote:

Yes and no, because someone maybe facing my issue with 4.10+ models, for MKV (especially HEVC coded) containers, where 4.10+ models provides improper frame handling!

I mostly have AVC encoded files but I do have a couple of HEVC encoded files which I regularly use as part of my testing and I haven't seen anything obvious.

RickyAstle98 wrote:

Also one more thing, yesterday I tested 4.15 lite and see one artefact, which 4.9 is properly mask! The lite models are less precise I think?

What I noticed was that I saw less artefacts with v4.15 when using TRT 9.2 than using TRT 8.5.1. Meanwhile 4.15 lite/72fps is still pretty good. I'm wondering if it is to do with the other changes I made to the scripts which I reverted back to default. I'm happy with 4.15 lite but I might do some experiments to see if I can improve it further by modding the scripts again.

scb wrote:
RickyAstle98 wrote:
Insindro wrote:

Could someone let me know how I’d be able to change my builder optimization level?

Line 137
Line 1179
Line 1297

Please do elaborate.. what is the impact of this? What are my options and how does it help? smile

There's very little benefit in changing it. I've played with many of the options including this one and the default settings are mostly the best settings.


RickyAstle98 wrote:
Insindro wrote:

In your opinions, which rife model is currently the smoothest?

4.4 smoothest (for me)

For me they are all about as smooth as each other but 4.15 and 4.15 lite have by far the least artefacts. 4.15 lite is the best all round.

Did you follow the MPC-HC/BE installation instructions in the SVP manual pages?

surmast14 wrote:

Thank you so much Dawkin. Your absolutely right. The bits of advice got me all the way to the last step and took days lol. That site you gave me was so much easier and 10 minutes. My copy and paste messed up too, so i reset svp and everything seems to be fine now i think. When I transcode videos it doesn't say rife engine but ignore hfr sources, but i think it's working since i put 72fps and 60fps.

You are welcome. You are almost there but not quite because if it says "ignore hfr sources" then you are still not running Rife. However if you follow the instructions on this page https://www.svp-team.com/wiki/Manual:SVPcode you should get there. Good luck smile

surmast14 wrote:

Please help me sad. Been emailing SVP4 for months. My rife tensor ai not working at all. a command prompt pops up every time.  vsmrt download not working. got a 4080 laptop. Im trying to get the best video possible. Also many youtube videos usually m3u8 8k and hdr aren't downloading for me.

It sounds like you are trying to copy bits of advice you see on here rather than just follow SVP instructions. All the information you need is here: https://www.svp-team.com/wiki/RIFE_AI_interpolation. Check the "Problems" section at the bottom of the page for help. If that doesn't work then uninstall SVP and start again, following the instructions on this page. SVP does almost everything for you.

Using Lanczos resize makes a noticeable difference to GPU usage and performance plus I'm not seeing any scaling issues. So I'm guessing that the resize happens before the interpolation.

dawkinscm wrote:
flowreen91 wrote:

3. Search "resize" in settings and specify your exact resolution downscale value. Try to add various shaders to regain visual quality.

This is interesting. I've tried downscaling before but the quality is clearly worse than mpv's class leading scaling. I think there is an option to change the scaling from bicubic to something better but it's been a while.

Chainik wrote:

> What is the downscale algorithm in SVP?

bicubic resize

SVP 4\script\generate.js line 477 big_smile
available options: https://www.vapoursynth.com/doc/functio … esize.html

This is what I was talking about but I rarely ask direct questions on here nowadays because I rarely get an answer from devs unless it's to correct an assumption I made because the devs didn't answer a previous question. Round and round it goes.

flowreen91 wrote:

Interesting. Are you talking about this particular instance? https://www.svp-team.com/forum/viewtopi … 121#p84121
Share the video if not.

Sorry I didn't see this earlier. No I'm talking about the intro to the movie Hugo which is a little difficult for Rife unless you get the SCT right or turn it off completely. But after more testing I find I can use SCT at 12 for just about everything now.

It's interesting to see how many of the changes I have recently made have now been reverted since yesterday because of how well Rife v4.15 lite works. I'm back to using the default SVP install and TRT and back to using SCT set to 12. The only remaining change is vmslrt. With v4.15 lite/72fps the remaining stubbon artefacts I come across have definitely improved over any other version while still using only 60-70% GPU.

pensioner600 wrote:

Installed MPV. Did I understand correctly that this is a player without a settings interface and everything needs to be written manually in files? And this will take a very long time to figure out.

If you installed MPV using SVP then you don't "need" to do anything else because SVP comes with a default mpv.conf file in the mpv64 folder. If you installed it separately then you will need to manually add a couple of things. I suggest you install using the SVP installer if you haven't already done so.

So this is a little weird. Before I got v4.15 Lite to be "almost" as good as v4.15/60fps by running the lite version at 72fps. But now, for the Alita battle drome scenes the Lite/72fps version actually handles artefacts a little better than base 4.15/60fps. I've made chages to my Nvidia Low latency settings which might make a processing speed difference. But I think maybe v4.15 has regressed a little with TRT 8.5 because I don't remember seeing these artefacts before but I have no actual evidence for this. I'm not prepared to do any new TRT testing until maybe 10.0.0.1 because even running at 72fps, the Lite version uses between 30 and 40% less GPU.

flowreen91 wrote:

If you set a low Scene change threshold like 1-15 then it will compare the two images and it might come to the conclusion that the difference between the two source images is big enough that it will consider it a scene transition.

On a related note, while I have been using the features of later vsmlrt versions I also set my SCT to 100.  After reseting everything to default (but still using the latest vsmlrt), I found I had to turn SCT on for best overall smoothness.The default value of 10 works best although 12 works better for one particular instance. YMMV.


flowreen91 wrote:

1. Both work, MPV slightly faster.

I would say MPV is significantly faster when stressed.


flowreen91 wrote:

3. Search "resize" in settings and specify your exact resolution downscale value. Try to add various shaders to regain visual quality.

This is interesting. I've tried downscaling before but the quality is clearly worse than mpv's class leading scaling. I think there is an option to change the scaling from bicubic to something better but it's been a while. BTW Is the number being used in your attachment 2560x1440 resolution?


flowreen91 wrote:

4. 2 threads+, enabled. Use which one you have better results.

I leave 2 threads on by default but tbh with my card I see no real difference between 1 and 4 threads.


flowreen91 wrote:

5.  Lite = uses less resources,

Except v4.14 "lite" which depending on your card can actually use more GPU resources.

OK so I'm using the latest vsmlrt script because it supposedly properly detects the TRT version. When I did that I notice that I loose some performance with the 9.2 test versions. So I reset everything back to default including the default SVP TRT version (8.5.1) and got the performance back. So where I am now is similar to where I was before. Rife 4.15v2 lite should be the new SVP default version because it uses similar GPU to v4.9 but has better artefact handling. But Rife v4.15v2 is still the best version overall because it removes or reduces every artefact I've ever come across.

abraxas wrote:

But - your milage may vary, I suggest doing some testing yourself. Especially if you are using VR.

Already have. HAGS is a problem for the VR streaming app I use.

RickyAstle98 wrote:
aloola wrote:
unrealit wrote:

Hi!

Sorry for the stupid Question!

But , How can i get Benchmark Values?

And what is HAGS?

What do you mean?

Thanks smile

use the script here.
https://github.com/AmusementClub/vs-mlrt/discussions/19

HAGS = Hardware Accelerated GPU Scheduling
you could google it for more info.

In RIFE with HAGS on performance might drop up to 25%.

HAGS ON is 25% perf drop? I think it would increase performance, no?

The reviews I've read of the feature suggests that any difference it makes to games is minimal at best. But it seems that for non games it can make things worse. I think I learned about turning it off a year ago or so from a chat I was having about VR performance issues.

Xenocyde wrote:

Nice, thank you! Do you guys test with pre-rendered RIFE or real-time RIFE rendering.

I've never even tried pre-rendered Rife. Real time Rife ALWAYS!

Xenocyde wrote:

Interestingly enough, the short clip is yielding different results on 4.16 V2 Lite. The long clip shows faint artifacts on the bottom left side of the net, but the short clip shows no artifacts in that area, although I can see faint artifacts on the right side of the net now.

Maybe try a longer clip of 20 seconds or so?

Xenocyde wrote:
dawkinscm wrote:
Xenocyde wrote:

How do you guys activate Rife in a short clip like that one I linked above? I play the clip but Rife does not activate. I have the long clip of 47 minutes, and I can see more interference artifacts in the goal net on 4.15 V2 towards the left bottom side. Those artifacts are barely visible on 4.16 V2 Lite.

As you have found, only clips above a certain duration will cause SVP to trigger. When I had this issue some time back, I found the setting for the video duration threshold and I think I set it to zero which means SVP will run on any length of video clip. I can't remember if it's code or an actual SVP setting because it's not in the SVP manual.

Welp, if anyone knows how to reduce that threshold to 0, please let me know.

OK found it. In the settings it's under setup and it's called min_duration.

Xenocyde wrote:

How do you guys activate Rife in a short clip like that one I linked above? I play the clip but Rife does not activate. I have the long clip of 47 minutes, and I can see more interference artifacts in the goal net on 4.15 V2 towards the left bottom side. Those artifacts are barely visible on 4.16 V2 Lite.

As you have found, only clips above a certain duration will cause SVP to trigger. When I had this issue some time back, I found the setting for the video duration threshold and I think I set it to zero which means SVP will run on any length of video clip. I can't remember if it's code or an actual SVP setting because it's not in the SVP manual.

Xenocyde wrote:
dawkinscm wrote:

Thanks but it says I need to request access.

Try this.

Thanks for this. I had a look with Rife v4.15 v2 lite and even slowed it down to make sure. I saw no fast movement artefacts when panning or anything else.

Xenocyde wrote:
dawkinscm wrote:

Fair enough. All the fast motion artefacts I see are improved with v4.15 but left untouched by v4.16. Can you could post a clip? It might be useful to  add it to my test collection.

Here it is.

Thanks but it says I need to request access.

Xenocyde wrote:
dawkinscm wrote:

I don't know about Anime but for live action both versions of 4.15 are much better for fast movement artefacts. Also mpv has nothing to do with Rife AI generated artefacts because they are "AI generated" artefacts.

I'm testing with live action, never tested anime. I have a specific scene from a BBC documentary abut the 1990 football cup in Italy where the camera pans from right to left and the football net usually shows interference artifacts. This scene looks a bit better on 4.16 V2 Lite compared to 4.15 V2.

Fair enough. All the fast motion artefacts I see are improved with v4.15 but left untouched by v4.16. Can you could post a clip? It might be useful to  add it to my test collection.

Xenocyde wrote:

Tried 4.16 V2 Lite with the new MPV update a few days ago and it looks like the fast movement interference artifacts are almost gone now.

I don't know about Anime but for live action both versions of 4.15 are much better for fast movement artefacts. Also mpv has nothing to do with Rife AI generated artefacts because they are "AI generated" artefacts.


scb wrote:

I noticed there is only a 'Lite' version available for 4.16. Does anyone know if that's how things will be from now on, just 'Lite' versions?

They were planning to use the "lite" from now starting from v4.16. But v4.15 is much better so that might have been a miscommunication. Either way it looks like they want to start using "lite" models.

scb wrote:

What does Lite even mean in practice?

With the exception of 4.14 lite, they use less GPU resources than the non "lite" models.

SHTH34D wrote:

Does this showing up in the command line mean I need to change something?

"Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32."

Yep just ignore it. Internal stuff.

RickyAstle98 wrote:

Please reatach my reedited comment again, dont reply to it, will be deleted smile

I deleted my reply so i don't have anything to reattach. Don't worry about it smile