Search options

@RickyAstle98

That was a joke?
Or was something like that stated by the RIFE developers? They would have to make use of the new features.

Correct.
Simply two BW-103 GPU-dies glued together (as Apple is doing with their M1 architecture since 2020 and Nvidia with Blackwell ML).
Of course (given technical leaks) Nvidias milking-strategy will be again, to castrate all GPU-dies of each model of their lineup (by 10 - 15 % as usually), as there is no competition and AMD+Nvidia is an Stackelberg-duopoly anyway for some years. Both companies are both manipulating the market for years, colluding on prices and products etc. There is no real competition; it's a public farce.
The currenlty sold RTX 4080 (super) are in fact relabeled RTX 4070 (AD104 GPU-die). The firstly introduced "RTX 4080 12GB" - which was then canceled - was in fact a RTX 4060 (AD-106 GPU-die).
There is no real RTX 4080 sold; same for rtx 4070 (is a rtx 4060 in fact) and the rtx 4060 (is a rtx 4050 in fact).
Renaming SKUs, giving them lower tier GPU-dies.
Looking at the leaks, it will be the same for consumer rtx 5000 again.

@dawkinscm

As mentioned, that will verly likely (if the leaks are true) not happening. Also: don't generalize the metrics.
At best a rtx 5080 (BW-103 GPU- die, so in fact a relabeled RTX 5070), will have 15 - 20 % less rasterization performance than a rtx 4090. In reality it should be more of +25  less%. Similar story with Tensor Cores (for RIFE) and other things.

1) The leaked BW-103 GPU-die (RTX 5080), has a whopping ~ 60 % less shading units, ROPs, RT-Cores, or TMUs, Tensor Cores than the GPU in the current RTX 4090, but should somehow magically achieve the same rasterization performance, machine learning, ray tracing or Tensor Core (for RIFE) performance? This is not happening. The last time there was this huge of GPU-architecture jump of > 50 % from Nvidia, was last in 2007 from the 8 series. https://en.wikipedia.org/wiki/GeForce_8_series
As said: Ampere rtx 3090 to 4090 is only so big because of the lithography 12 nm -> 5 nm jump. Two full nodes.
Performance jumps due to GPU-architecture from Nvidia, were all only 10 - 20 % for the last 5 generations. The rest was lithography or simply more transistors.
2) The leaks specifies only the full BW-103 GPu-die for the rtx 5080 (GPU SM 84 (84 Full)). Nvidias has never sold a full GPU-die for consumers, for the last 4 - 5 generations or so. It will be castrated by at least 10 % as usual, just as every other model.
So it won't be 84 SM, but more like ~ 76 again, which means 70 % less units than the current rtx 4090.
3) Moores Law is effectively dead since 2012 TSMC's 28 nm lithography node (whatever other people say is wrong, or lying marketing).
4) For many generations (2012, especially since CUDA) Nvidia's pro/quadro/server and consumer lineup, have the same GPU architecture basis. They only swap out/leave out certain components as display output, video accelerators etc.
TMU, ROP, Tensor Core, RT Cores are verly much alike.
AMD's leading people, finally realized that this unified approach is the smarter way and will soon start doing the same
https://overclock3d.net/news/gpu-displa … nd-gamers/
4) GH100 to B100 has only 30 % overall more transistors (Hopper to Blackwell architecture). Together with the previous things mentioned, this is a leak in itself, already giving away how much better Nvidias engineer can make the RTX 5000 lineup, comparing equal GPU-die to GPU-die.
20 - 30 % in all aspects. The rest will be ML ("AI") marketing-gimmicks as "fake frames" Frame Generation x-4 times, or DLSS 4.

So anyone pondering about buying a graphics card for RIFE for usage of 3840x1600 or 4K-UHD (3840x2160): Either continue with the rtx 4090 or grab upcoming rtx 5090. Sorry to "burst some bubbles".
It's all a illegal, colluding Stackelberg Duopoly since at least 2006 (Nvidia is here the Stackelberg leader)
https://www.tomshardware.com/news/nvidi … ,6311.html
https://hexus.net/business/news/corpora … itigation/
AMD is not selling "cheaper products for less money" aka offering better price/performance for at least 5 graphic cards generations (since 2014).
The simly price them 10 - 20 % below Nvidia's graphics card models (e.g. current rtx 7900xtx versus rtx 4080), but are worse 50 - 200 % in nearly all aspects (efficacy, features as image reconstruction DLSS 3 vs. FSR 2, raytracing or ML-performance, streaming etc.).
Hardly anyone uses a AMD RDNA 1,2,3 graphics card for RIFE, with via ncnn/Vulkan, right? It sucks in performance.

Same goes for Intel+AMD duopoly, controlling the consumer and server market, with their x86/x64 patents for decades, eliminating any real competition.
All company execs only want to maximize product margin to the moon, and please financial shareholders.
The stuff about "fair and legal competition" based on capitalistic markets doctrine and laws, is a lie and a public farce for at least 10 -20 years.
It's all an elaborated show, but 99 % of the media continues to report as if there were some real, fair and legal competition going on ...

Sorry a bit for the offtopic part. I think it has to be commented, especially since hardly anyone mentions it in the current state of nonsense 08/15-media brainwashing.

@Blackfyre
After my third testing, I disagree. The 4.26 model is overall and noticeably, for animation/cartoon and real scene movies, the best for most scenes.
As already linked https://www.svp-team.com/forum/viewtopi … 248#p85248
I was correct with the 4.18 model (as many here also, came to the same conclusion after testing), that it was overall the best for most scenes.

Few weeks after that I did the same tests again, with 4.18 versus 4.22 & 4.22 lite models.
I haven't commented it, by I reached the same conclusion as the authors in their readme file (4.18 was the best back then for real scene and 4.22 & LITE for animation) https://github.com/hzwer/Practical-RIFE … /README.md
I had thus used 4.22 lite for animation/cartoons few weeks ago.

And two weeks ago I sat down for more than 1 hour again, tested more than 40+ different scenes (animation and real scene), always with 0.25 speed to catch every artifact, warping, image smoothness and pacing etc. used again A-B repeat, again and again to loop through etc.
I again reached the same conclusion as the authors "Currently, it is recommended to choose 4.26 by default for most scenes."

I think the difference in our findings is simply our differences in how we test. I think here lies the fallacy of conclusion.
I think if you would test more and especially stricter (you did or didn't?), I'm sure you would come to the same conclusion as the authors and me.
I mean: How can the authors who train the models etc. be wrong with their conclusions and findings? Not possible.

It's not better in all scenes, but most scenes. I also found 4 - 5 scenes were the 4.18 models was still somewhat better (either in artifact, warping, image smoothness or pacing), but the rest 4.26 was better.
And yes, I also specifically tested 4.25 versus 4.26, with the same conclusion.

And the best part about the 4.25 & 4.26 models is how little electricity they need to achieve that. Tested with latest v15.5: latest TensorRT library, and a couple of movies at 3840x1600 resolution and 48 fps.
4.17 lite ~ 145 watts average gpu power consumption.
4.22 lite ~ 150 watts
4.18 ~ 176 watts
4.22 ~ 187 watts
4.25 ~ 158 watts
4.26 ~ 158 watts

I'm using it for everything, as recommened.

@Blackfyre
So here is a general buying advice for everyone, and a bit prediction of the future - and I'm 99 % sure I will be correct with that:
https://www.tomshardware.com/pc-compone … 12-bit-bus
https://wccftech.com/nvidia-24-gb-gefor … s-spotted/
So given how big greedy fuckers the AMD & Nvidia execs have become since 2018's Turing generation (prices weren't nearly as bad from 2000 - 2018), that nvidias is a first a "machine learning company" (marketing "AI") now, and that the leaks from twitter user "kopite7kimi" are 90 % always correct, I think with certainty the upcoming RTX 5080 won't be enough.
The measly 10k Shading units & Tensor Cores won't do it, given rtx 4090's 16384 shading units and 512 Tensor Cores aren't able to handle it.
Nvidia's milking strategy will likely again be releasing "super" graphics cards lineup in 2026, so a future "rtx 5080 Super" with ~ 14k Shading cores and ~ 450 Tensor Cores might be able to run current RIFE's 4.15 to 4.26 models.

But given how the RIFE developers are always matching their models and keep increasing their ML & inference demand, I wager to say that for future RIFE models, running them on the same resolutions near 4K-UHD 48 - 60 fps, the future top dog GPU-die in the rtx 5090/6090 will be needed again

And btw. Nvidias engineers won't be able to do miracles with this upcoming consumer rtx 5000 generation. The measly lithography node jump from 5nm to 4nm, will maximum give 20 - 25 % more performance (already the same for their Blackwell ML lineup, that's why they glued two Blackwell GPU-dies together and can now market x2 performance).
At best, they will crank up their Tensor- and RT-cores amount by 30 - 40 % this generation (because they prioritize Machine Learning and Ray/Path tracing performance over rasterization performance), and that's it.
So better wait for 2027 rtx 6000 lineup, because this will be a big overall jump again.

Maybe, maybe, maybe, thus RIFE's developers will see it the same way as me, and change their doing and will match their upcoming models, so at least the rtx 4090 will continue be able to handle the ~3840 x 1600 resolution at 48 fps, and the rtx 5090 at 60 fps (including 4K-UHD, which is 3840 x 2160), for their future models.
I can't know that. Someone would have to ask them.
In other words: The overall performance/efficacy jump from e.g. Nvidias rtx 3090 -> rtx 4090 (xx102 to xx102 gpu-die) was only so large (thus performance for RIFE models) because they switched from Samsungs 8nm lithography node (which is almost equal to TSMC's 12 nm node), to TSMC's 5 nm node; so 12 nm to 5 nm. This time it's from 5nm to 4nm.
So it's obvious for me that this generation, far far less people will buy the consumer RTX 5000 series.

@Xenocyde
@Blackfyre

I've (again) tested RIFE 17.v2 , v17.v2 Lite, 18.v2, 19.v2 and 20.v2, with my usual blend of test scenes, in slow motion (x0.25),
looking for usual things as distortions, warping of patterns and objects, artifacts, especially when camera panning etc.
My observations match yours.

1) For me18.v2 is by far the best model regarding all things mentioned.
2) 17.v2 second best model, but with noticeably increase in distortion and warping of patterns and objects, especially when panning.
3) Followed by third best 19.v2 with same issues.
4) Fourth best version 17.v2 Lite with the same artifacts.
5) 20.v2 the worst of them. Not sure what happened here during training. :-(

Especially watching in slowmotion x0.25, artifacts, distortions etc. can be observed with all models, but it's suprising how good 18v2 and 17v2 Lite are looking.
For 1080p@60 fps I keep using 17v2 Lite, and for everything up to
3840x1600 - 4K-UHD resolution, @48 fps, it's v18.v2.

@Asking a question out loud
Anyone having an explanation why even a nvidia rtx 4090 can best do 48 fps up to 3840x1600 - 4K-UHD resolution?
Increasingly, above 3840x1600 resolution @60 fps, playback keeps stuttering no matter what. Already removed other bottlenecks.

Observing hwinfo64 metrics for
- GPU-utilization
- power draw etc.
- task manager
there is a strange discrepancy between all those.

Up to 3840x1600 resolution @48 fps,
- GPU-utilization keeps around 40 - 60 %
- power draw hovers around 170 - 240 watts
- Task Manager: Tensor Cores, 3D, Video Encode & Decode and Copy also far from being fully utilized.

Then, getting close to 3840x1600 resolution @60 fps and above, a sudden disproportionate jumps happens and stuttering keeps occuring.
The ~ 25 % increase in resolution does not warrant the overall increase ... is the GPU bottlenecked by the Tensor Cores? Not enough of them?

@flowreen91
@Chainik
Thanks for providing a tip.

4) Switching to Tensor RT 15.x, it works swapping "vstrt.dll and the folder vsmlrt-cuda" only.
I noticed a bump of graphic card total power consumption (undervolted rtx 4090), about 5 - 10 % (differs in resolution, framerate, upscaling etc.)

5) If swapping the newer "vsmlrt.py" also from the TensorRT 15 file also, nothing works anymore; that means any machine learning based RIFE model and SVP's own interpolation. See image attached "error swapping vsmlrt_py".
Any way to fix from my side, you SVP developers side, or simply not swap the file?

6)
@flowreen91
Made the line change ("True"), nothing works.
See image attached.

Thanks in advance!

@Chainik

With the newest update, please write down here, for laymen to understand, what's the best opion to use, i.e. achieving highest image quality, image artifacts, smoothness, when using RIFE 4.17 (or older versions) with the newest TensorRT (or not), regarding
- SVP motion vectors
- NVOF motion vectors
- image comparison

I use a graphics card RTX 4090. Is there a diference in performance, so users with less or more performant graphic cards have to care?

I previously used "image comparison 12 %" because someone mentioned it here.

Someone wrote smt. about it already, but I like to hear you detailed opinion.

Thanks in advance.

7) Using an nvidia graphics card, it's possible to add a profile to a program, where various things can be set. Is this usefull or not needed? What about g-sync (adaptive sync)? Is it working with svp 4? I know that's it's not working and should be deactivated for mp-hc or madVR.

5) There is sometime a message shown by svp in mpc-hc: "SVP: Playback at 142.657 Automatic Black bars:276-276, 0-2". Is this due too heavy load or frames being dropped?

attachment pictures:
stuttermessage.jpg

3) In the svp 4 Manager, gpu-acceleration is activated. As expected, using 1) svp 4 + madVR, puts an immense load on the cpu. The slider in the svp 4 manager is set to the middle position;  watching 1080p content puts the cpu utilization to ~ 40 - 50 %, watching uhd-media (2160p) puts the cpu to 70 - 90 % utilization. More option than the svp 4 manager slider to tackle this?
3.1) Mpc-hc shows that frames are being droped, even when the cpu is at 50 % utilization.
What to do against frames being dropped?
3.2)  Now that the graphic card has to render not 24 or 30 frames, but 60, the gpu load is very high. Now matter what profile settings I put in madVR: chroma upscaling to Lanczos, Jinc, NGU ... the gpu load is always around 90 %.
I found the solution to this in the madVR settings: scaling algorithms ->  "your profile" -> image downscaling -> processing done by GPU video logic: set to "DXVA2".
Keeping the same other madVR settings, now, even with 2160p content, the gpu utilization is way lower. This the correct way to tackle it?