New RIFE filter - 3x faster AI interpolation possible in SVP!!! (Page 46 of 62)

I don't know what this means. Would you kindly explain?

I am using SVP with the models downloaded into the RIFE and RIFEV2 folders, with MPV video player.

How do I install what you mention, and what are the benefits? Will I get better performance? I am on a quest to get 4K60 @ 10-bit. The closest I have come is 4K48 @ 10-bit  - Thank you

Is the bigger the number of the scene change threshold, the better?And why is my maximum number only 15%?

According to the info about the code, v14 is no improvement over v13. Having personally tested the v14 versions I would say that if anything they might use a little more GPU resource. Maybe that's because they are designed for AI GPUs.

Tried using this in mpv but nothing plays its a crawl.

Can you share that setting with me ?

I use a number of videos highlighting different artefacts. But Alita might be the best because it has different types of fast movement and exposes a couple of minor artefacts. One of which has been fixed by Rife 4.14.

It's a change to the code in base.py. I got this from a previous post by @blackmickey1007 for completely disabling SC.

SVP4\script\base.py

input_m = input_m.misc.SCDetect(threshold= 0.1 or 0.2)

The threshold values are just suggestions. You will need to experiment to see what works for you. You won't find a pefect setting because when you fix double images from fast movement it will break slow panning. When you reset for slow panning you get double images in fast movement. But you can get a compromise which improves fast movement a little without breaking slow panning. I couldn't get even this minor improvement in 4.12/4.13 but 4.14 does seem to be better overall for fast movement so here it was possible.

Thanks for clarifying.  I just used that the 0.1/0.2 examples from the original post. I've tried 100 and other high values before and Rife is smooth with anything from 15% or 100% on my machine.

But the double image issue I'm talking about you may never see this issue depending on the the type of stuff you watch. I want to fix this while keeping the smooth motion which is pretty much impossible. With a low enough value, the stutters disappear but also causes slow pan stutters. My actual setting is a decimal fraction below 10% and rife_sc only accepts integers. Increasing fps actually fixes the issue but causes slow pan stutters and resource issues.  The only real solution is for the model to get better and I've noticed a couple of small improvements so hopefully that trend will continue.

BTW I didn't want to say it before without more testing but Rife 4.14 uses a little less GPU resources than 4.12/4.13. YMMV.

Biggest improvement in artifact masking I have seen in a long time, a must upgrade. I am testing 4.14 (v2)

No Time to Die (007 movie), 3 minutes onwards, when the masked man walked behind the curved glass door and opens it, then the curtain in the background behind the woman on the sofa.

From 14 to 17 minutes the fast action sequence now has no more artifacts in it.

The building time does take longer, around twice as long as before, so be patient at the start.

Sadly I can't test my usual full aspect ratio IMAX movies or TV shows that take the whole screen in 4K, the RTX 3090 is not strong enough.

So I am hoping 4.14 Lite will have the same level of artifact masking, because it is brilliant.

I can confirm 4.14 has improved a lot in eliminating artifacts in fast moving scenes.

Are you both updating your vsmlrt.py or not?

Go here: https://github.com/AmusementClub/vs-mlrt/releases

Currently, the latest version is v14.test3, scroll down and open Assets under the latest version. Download scripts.v14.test3.7z, which is 11.7 KB (that's very small and should take 1 second to download, don't download the big files).

Open it and keep it on the side, go to C:\Program Files (x86)\SVP 4\rife

Now drag and drop the vsmlrt.py from inside scripts.v14.test3.7z, into the folder above and replace the original file.

It should now be updated. Perhaps you're both using an outdated version of vsmlrt.py or an old nVidia driver. Your nVidia driver should also be up-to-date.

Generally you want to update vsmlrt.py every time they update it when you are always testing the latest versions.

Also this, make sure it's either 2x, 3x, 4x etc

Then open the drop down menu to the right of the slider, and enable at the bottom (Force Exact Value).