201 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

Xenocyde wrote:
RickyAstle98 wrote:
Xenocyde wrote:

Decided to test 4.13 and 4.13 v2.

4.13 works well, Win resource monitor shows ~50% GPU utilization regardless of the video resolution. I tested with 720p and 1080p videos at 60 Hz. Shouldn't there be some sort of difference between 720p and 1080p? 720p even reaches 60% more often on my RTX 4080. Also, the 4.9 model included with SPV by default now has almost the same performance, mostly sitting at ~50% regardless of resolution.

4.13 v2 doesn't seem to be working, however. Every time I try to play a video, it compiles the cache file and after around 50 seconds it stops and the video plays without RIFE. Can't really see if it gives an error cuz the window closes fast.

Something is wrong bruh >
I have 10700K and RTX 4070 and here is my performance!
4.4v2 720p24>144 (<45% GPU usage) at 165Hz
4.12v2 720p24>144 (<65% GPU usage) at 165Hz
4.13v2 720p24>144 (<70% GPU usage) at 165Hz

I only test with 60 Hz cuz my screen is old af big_smile Have you tested with 60 Hz? I feel like the utilization might not change too much even if refresh is X4+ for me.

dawkinscm wrote:

Make sure you have a 4.13 onnx file in the "v2" folder. If you do then delete it and any files created by it, download the v2 onnx file again and put the new onnx file into the "v2" folder.

Deleted, redownlaoded, still doesn't work. Do I need some new version of Python or TRT maybe?

Wait me here, I will edit my message in next 5 minutes! Check plz!!!
So you need  to put 4.13.onnx into v2 folder where SVP located
https://ibb.co.com/RYCzGRh
If your 1st timing cache build failed, you need enable TRT boost option, 4.7-4.9v2 cant stable buld timing cache for general optimization... Maybe 4.13v2 too? Me too cant build timing cache without TRT enabled!
Yes I tested 60Hz and only CPU usage change a little, anyway I have modern 165Hz GSync monitor, any FPS factor, smooth always!

Go to forum: Using SVP

202 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

Xenocyde wrote:

Decided to test 4.13 and 4.13 v2.

4.13 works well, Win resource monitor shows ~50% GPU utilization regardless of the video resolution. I tested with 720p and 1080p videos at 60 Hz. Shouldn't there be some sort of difference between 720p and 1080p? 720p even reaches 60% more often on my RTX 4080. Also, the 4.9 model included with SPV by default now has almost the same performance, mostly sitting at ~50% regardless of resolution.

4.13 v2 doesn't seem to be working, however. Every time I try to play a video, it compiles the cache file and after around 50 seconds it stops and the video plays without RIFE. Can't really see if it gives an error cuz the window closes fast.

Something is wrong bruh >
I have 10700K and RTX 4070 and here is my performance!
4.4v2 720p24>144 (<45% GPU usage) at 165Hz
4.12v2 720p24>144 (<65% GPU usage) at 165Hz
4.13v2 720p24>144 (<70% GPU usage) at 165Hz

Go to forum: Using SVP

203 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

hvs wrote:
RickyAstle98 wrote:
hvs wrote:

Thanks you so much for this. Yes it's true that MPV is much more stable.



Thanks for the recommendation. When searching the solution for my problem, I read in this post regarding how v2 has much more advantage than v1..
So I tried 4.9 v2... but it seems like there's even Ensemble version, which I didn't find anywhere about it said here, or probably just missed the conversation regarding it.

4.9 V2 seems very stable for me, and the wait isnt that long either, i just have to wait for no more than 1 minute or two.
Tried to encode Kagejitsu S2 Ep 12 using it before i went to sleep too, but iirc it finished around 3 hours (because my pc auto shut down around that time).
The result is so great. the artifacts are almost none, and even if its there, its very subtle, which makes it worth the wait than watching the anime with live interpolation. This is a good option for me if I had no need to watch the anime ASAP.


All those talk aside, what I actually want to achieve is that soap effect that everyone hates. I am weird in that I love that soap effect XD.
I'll try 4.13 later I guess.


eh that was just my estimate for max time i waited (not timed).. its actually less than that ig. mostly around 30-1 mins. Ig it depends on the scene to interpolate

---------------
Also talking about CPU..
Can't we use GPU as a main to transcode? or is it only just mainly CPU with GPU as backup?

As I can say, I test 720p30>720p90 transcode, SVP window show 25% all the time, but my CPU maxed at 7% only during transcoding, NVENC encoder!
So its GPU mostly transcode...

Thanks. My SVP Transcode page show the advanced mode so i didnt see the NVENC encoder, it was somewhat hidden but after changing it to that, it only use around 30% of my cpu, and my gpu usage rocketed to 95~100%.
it transcoded in less than 30 min now. sweet.

Btw which one would be better, and what is the difference between AV1, H.264 or H.265?

H265 and AV1 better because need 2/2.5x less bitrate for same amount of quality H264

Go to forum: Using SVP

204 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

Any possibility to implement SVP RIFE-TRT with SVP standard interpolation method work simultaneously? It will help to maintain targeted peformance!
Example >
1080p30 + TRT RIFE 3x = 90 + SVP method 4x after RIFE buffer with 32 or 24 pixel grid size (realtime) = 360FPS for 360Hz users (without significant artefacts because SVP have more detailed frames)
RIFE cant do 12x interpolation stable but with this method... Who knows?!

Go to forum: Using SVP

205 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

hvs wrote:
flowreen91 wrote:
hvs wrote:

Would love to use MPV but I can't find the way to enable fps counter.

Try Shift + I or hold I to enable fps counter.
MPV seems faster than MPC-HC. It gives more stable fps.

hvs wrote:

I hope someone can guide me in getting Soap Opera effect using RIFE in SVP.

Try this and say if you get stuck or instructions are unclear big_smile :
https://www.svp-team.com/forum/viewtopi … 352#p83352

Thanks you so much for this. Yes it's true that MPV is much more stable.

aloola wrote:
hvs wrote:

I hope someone can guide me in getting Soap Opera effect using RIFE in SVP.

currently, the best quality that almost gets rid of the soap effect is models 4.12 and 4.13.

4.0->4.6: about the same quality and same performance
4.7->4.9: about the same quality and same performance, the performance cost +20% than 4.0->4.6
4.10->4.13: about the same quality and same performance, the performance cost +20% than 4.7->4.9
4.12lite, 4.13lite: performance between 4.7->4.9 and 4.10->4.13

my recommended models are: 4.6, 4.9 and 4.13

Thanks for the recommendation. When searching the solution for my problem, I read in this post regarding how v2 has much more advantage than v1..
So I tried 4.9 v2... but it seems like there's even Ensemble version, which I didn't find anywhere about it said here, or probably just missed the conversation regarding it.

4.9 V2 seems very stable for me, and the wait isnt that long either, i just have to wait for no more than 1 minute or two.
Tried to encode Kagejitsu S2 Ep 12 using it before i went to sleep too, but iirc it finished around 3 hours (because my pc auto shut down around that time).
The result is so great. the artifacts are almost none, and even if its there, its very subtle, which makes it worth the wait than watching the anime with live interpolation. This is a good option for me if I had no need to watch the anime ASAP.


All those talk aside, what I actually want to achieve is that soap effect that everyone hates. I am weird in that I love that soap effect XD.
I'll try 4.13 later I guess.

RickyAstle98 wrote:

Idk why you wait 5 minutes, maybe engine build is CPU limited? I have 10700K and RTX 4070 and NVMe too, but slower cache build time was 2m24sec only!

eh that was just my estimate for max time i waited (not timed).. its actually less than that ig. mostly around 30-1 mins. Ig it depends on the scene to interpolate

---------------
Also talking about CPU..
Can't we use GPU as a main to transcode? or is it only just mainly CPU with GPU as backup?

As I can say, I test 720p30>720p90 transcode, SVP window show 25% all the time, but my CPU maxed at 7% only during transcoding, NVENC encoder!
So its GPU mostly transcode...

Go to forum: Using SVP

206 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

hvs wrote:

Hi, I was trying to use Rife in the SVP. I've been only watching anime using SVP with non-RIFE settings since I purchased it which is 3 years ago.
I am totally clueless about these RIFE feature and tried to do my own research and test but was stuck at one thing, which shown as below:

https://i.imgur.com/ThoFZn0.png

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

After this message is shown, my playback will be stuck and only audio plays, sometimes even audio didn't play.

This is my setting for the RIFE

https://i.imgur.com/C65rGPX.png
(that custom SC Threshold is because i tried following a youtube tutorial, but it still produced the same thing. Maybe I am doing it wrong)

I know there's probably an answer for this question already somewhere, I tried searching for it but there's too many too unrelated (probably) topic around it. a
I hope someone can guide me in getting Soap Opera effect using RIFE in SVP.
Sorry for the troubles and thanks for any consideration given.

-----------------------------------------------------------
Note that my pc setup is as such:

- Monitor 24" 144Hz
- AMD Ryzen 5 3600
- RTX 3080Ti 12GB
- 32GB DDR4 3200GHz ram
- around 500GB+ free space in the 1TB Adata S70 Blade M.2 NVme SSD

---------------------------------------------------------------
EDIT :

Nevermind, I am just too stupid. All i need to do is wait a bit longer and it'll works (using the settings in the picture)
But its weird, i swear i waited close to 30 mins before, hence I was thinking it's actually stuck/crashed. Now I just need to wait for 5 min at most.

Using MPC-HC since it has built-in fps counter. Would love to use MPV but I can't find the way to enable fps counter.

Idk why you wait 5 minutes, maybe engine build is CPU limited? I have 10700K and RTX 4070 and NVMe too, but slower cache build time was 2m24sec only!

Go to forum: Using SVP

207 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

flowreen91 wrote:
RickyAstle98 wrote:

What happen when someone upload already generated engine cache lock files for RTX 4070 users? Will it work without resolution optimization pass?

The actual generated files are all binary so you cannot understand what exactly they contain, but all we know it makes SVP interpolation faster which is good:
https://gyazo.com/7099f92f846ce0c57dab6ec3258ff4c5
And since a new one gets generated for every specific rife version + resolution + graphics card it would be safe to assume that it's always best to let it generate a fresh version for your specific configuration and never try to use already uploaded generated engine cache lock files for compatibility purposes.
If i just rename the engine cache files to use it on wrong configuration, MPC-HC mentions errors that it fails to start.
Wrong rife engine resolution error:
https://gyazo.com/6430b2a951b77dbc643ed9430f0be445
Wrong rife v2 engine found instead of v1 error:
https://gyazo.com/32117e51558d87e37f8c2451dd6fc7c3
But it seems to work if you run a v4.13 with a v4.10 engine file.
My suggestion would be to delete cache folder from here:
"C:\Users\username\AppData\Roaming\SVP4\cache"
every time you update rife models and let them generate fresh.

Tested before your reply, my friend can use my generated files without troubles, same performance at all wink

Go to forum: Using SVP

208 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

flowreen91 wrote:
RickyAstle98 wrote:

They have pattern match and random zigzag artefacts, where too many same lines onscreen or objects, interpolated by error too, regardless of the overall frame!

A v2 jaggedness/zigzag bug was fixed on 3 November: https://github.com/AmusementClub/vs-mlrt/issues/66
And the Rife devs re-uploaded the versions here: https://github.com/AmusementClub/vs-mlr … nal-models
Maybe try to redownload and check again if issue persists?

aloola/dawkinscm can you give step by step example on how you upgraded current SVP's TensorRT to newer versions?
and how to revert it back if something goes wrong (on Windows prefferably)
(i managed to increase the resize value from -10240576 to -10880612 at stable 240 fps by switching from MPC-HC to MPV and currently searching for other possible performance improvements you guys use on 4.13v2 that i didn't already summarized here https://www.svp-team.com/forum/viewtopi … 352#p83352 )
Thanks!

No because I get exactly what I said, my downloaded models dated November 9! Pattern match issue still persists!
I mean when you resize to resolution, TRT exec do optimization pass for selected resolution, its contains 3 files, engine/cache/lock types...

Go to forum: Using SVP

209 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

aloola wrote:

V2: faster, should use this as default if you not encountering any problems. model V2 47+ has a bug preventing you from using performance boost off.(It means it will run trt command on every video with a different resolution.)
4.13v1lite: lite is just a name, you may think of it as 4.135 which runs faster than 4.13
ensemble: this one will cost half the performance of the normal model. I couldn't see much difference from this, just use a better model instead.

try to use model in performance order: 4.6 > 4.9 > 4.13 lite > 4.13 and decide which one you like the most

4.9 is a sweet pot for me which has low artifact and runs faster than 4.13 20%

Anyway my post #1085 also applicable for RTX3080 users, what about 4.4 and 4.6 models?
They have pattern match and random zigzag artefacts, where too many same lines onscreen or objects, interpolated by error too, regardless of the overall frame!
Model 4.9 almost eliminates that effect, even with very low frame rate videos, but more GPU sensitive...

Go to forum: Using SVP

210 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

scb wrote:

So what about 4.13v2 lite, how does that rank?

IDK

Go to forum: Using SVP

211 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

scb wrote:

Could anyone fully clarify the difference between the regular models, the V2 models and lite models please?

e.g. 4.13 vs 4.13 lite vs 4.13v2 vs 4.13v2 lite.

It would help solidify my understanding!

V2 models faster

Go to forum: Using SVP

212 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

The RTX 4070 TensorRT performance (TRT boost enabled)
Model 4.4 (720p) singlethread 24>144 6x stable
Model 4.9 (720p) singlethread 24>120 5x stable
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
RIFE v2 models >
Model 4.4 (720p) singlethread 24>168 7x stable
Model 4.9 (720p) singlethread 24>144 6x stable
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Generally v2 models are 20% faster without noticeable intermediate frames quality drop, this peformance numbers achieved by single GPU thread, so you can go even higher, CPU utilization increase massively!
I dont recommend using more than 2 threads, but you can get upto 4x for 1080p videos easy!

Go to forum: Using SVP

213 Reply by RickyAstle98

(2,378 replies, posted in Using SVP)

What happens when someone upload onnx packages for 4070 users? Will work for anyone who has the same GPU or not? I have v1/v2 prebuilt for HD/FHD sources with TRT boost enabled!
What about reverse engineering method for 4060Ti and 4060 owners too?
Average onnx build time v1 ~1/1.5 min HD/FHD
Average onnx build time v2 ~2/2.5 min HD/FHD

Go to forum: Using SVP