I still got the error after updating helpers, tried with mpv/mpc. also, everything runs without admin. here are my logs

https://cdn.discordapp.com/attachments/ … 1d44b96.py
https://cdn.discordapp.com/attachments/ … 165337.log

https://cdn.discordapp.com/attachments/290709370600423424/1173924675663966278/image.png

V1 runs fine for me.

V2 doesn't work for me either

rife_mnum = '4.6_v2'
trt_backend = Backend.TRT(force_fp16=True,device_id=0,num_streams=2,output_format=1,use_cuda_graph=True,workspace=None,static_shape=False,min_shapes=[64,64],opt_shapes=[1920,1088],max_shapes=[2560,1440])

        else:
                smooth = RIFE_imp(input_m,multi=rife_num,model=rife_mnum,backend=trt_backend)
               
I checked the code, "force_fp16=True" won't work with v2, should be replaced with "fp16=True"

also missing implementation = 2

I saw implementation = 2 before, but after the newest update, this was missing.

also, V1's caches stored in appdata
while V2's stored in C:\Program Files (x86)\SVP 4\rife\models\rife_v2

I freshly installed SVP and didn't modify anything.

subtitles issue you mentioned

I never mentioned this.

I don't know why you try to use the newest model, just pick the one you like the most. newer doesn't mean better.

also, I checked v2 4.6, and the antialias bug was gone.

maorgr wrote:

Now I run a fresh SVP installation, with 4.9.

check C:\Program Files (x86)\SVP 4\mpv64\vapoursynth64\plugins
is there a MiscFilters.dll file from there?

yes there is.

https://cdn.discordapp.com/attachments/290709370600423424/1172345332328300609/image.png

can you open the filter? does it show vapoursynth Filter v1.4.7 # svp?
also please post your SVP logs.


also this is just my personal benchmark, not related to your issue

all v2 1080@30 x2
4.10: 113
4.9: 145
4.8: 148
4.7: 149
4.6:  195

well, 4.10 is super heavy, good for ppl with HE graphics and want quality.

maorgr wrote:

Hi,

So I've just reinstalled svp pro 4 from scratch and I get the following error when switching to RIFE mode
I don't know python, so I would appreciate your guidance.
https://imgur.com/a/pp6Ky96


thank you in advance.


EDIT: now it does not throw the error messages, but it gets stuck when TRT ends processing the movie....

can you please help me ?

TensorRT version: 8.5.1
VapourSynth R65
rife_v4.8.onnx
4090rtx

check C:\Program Files (x86)\SVP 4\mpv64\vapoursynth64\plugins
is there a MiscFilters.dll file from there?

also uninstall vapoursynth if you installed it before, only use the one from SVP.



Transcoding speed from my testing:
all v2 1080@30 x2
4.9: 145
4.8: 148
4.7: 149
4.6:  195

is it just me or does 47-49 V2 require padding to make it work? I need to padding it to make it work.

4.0 - 46 v2 don't need padding to work.


RIFE v2 models which handle paddings internally and reduce memory transactions on heterogeneous devices.

to use the new V2 47>49 model with bug fixes you will need the new vsmlrt file.
https://github.com/AmusementClub/vs-mlrt/issues/66

for now just stick with 49 V1, 49 V2 need more testing.

Blackfyre wrote:
dawkinscm wrote:

I decided to compare Rife 4.9 v1 with Rife 4.9 v2.

Interesting on Github under 4.9 v2 notes it says this:

This improvement does not work after onnx file renaming

The full quote:

RIFE v4.7-v4.9 models with v2 representation for TRT backend now has improved accuracy, contributed by @charlessuh (#66 (comment)). This has been backported to master. This improvement does not work after onnx file renaming.

I tried the new V2 update but I cannot use the model above v4.7-v4.9 v2

I got the error when I ran V4.7>4.9 _v2
[E] Error[4]: [graphShapeAnalyzer.cpp::nvinfer1::builder::`anonymous-namespace'::ShapeAnalyzerImpl::analyzeShapes::2013] Error Code 4: Miscellaneous (IElementWiseLayer /Add: broadcast dimensions must be conformable)

Blackfyre wrote:

New nVidia driver, 545.84 WHQL

Additionally, this Game Ready Driver introduces TensorRT acceleration for Stable Diffusion to increase performance by up to 2x.

I assume this doesn't impact us, right? Would be nice if we can get a 2x performance lift.

I've just tested with the new driver, no performance boost

yeah, 4.7 is slower than 4.6

from my benchmark

4.7:
Output 8000 frames in 45.33 seconds (176.47 fps)

4.6:
Output 8000 frames in 34.61 seconds (231.17 fps)

61

(1 replies, posted in Using SVP)

it won't work on most video players.

but you can try MPV player, with the default config it will upscale SDR content to HDR content. Require HDR to turn on first.

or you can manually turn it on with specific configs
https://www.youtube.com/watch?v=Ys0noFWHrX8

1920*1080*24*3 = 150m
3840*2160*24*2 = 400m

in short, you need a stronger VGA, at least to x6 1080p to watch 4k x2.

Drakko01 wrote:
DragonicPrime wrote:
Drakko01 wrote:

Can someone remember me how to use ensemble model, in the model drop down I only see 4.4 and 4.6. I use Mpc-hc as a player.

copy the folder into SVP folder>rife>models. After that it should use it automatically. At least it does for me. If it worked correctly, it should pop up that command prompt window while it sets everything up for every resolution if you have performance mode enabled. Little warning. 4k content doesnt' seem to work very well with this version. The quality is noticeably worse for me and others in this thread if I remember correctly

Thanks for answering, but if understand correctly, by default use this model rife_v4.6.onnx from the v2 package. And my question is how to use this rife_v4.6_ensemble.onnx model.

you need to rewrite the vapoursynth code to set ensemble mode on first.

it's not worth using ensemble on real-time playback, it's slower at 50% performance, at least for me.
also don't use RIFE v2, its product image ringing artefacts, degraded image quality, and trade-off for a 5%~10% performance boost is not worth it...

just stick with RIFE v1 4.6 for now and wait for RIFE 4.7 or newer.

zSoi wrote:

Some newbie questions here :

Owner of a rtx3080 12600k, I like the smoothness SVP can get me, but sometimes artifacts are annoying.

What can I expect from this rife ai engine ? is it worth the time to set it up ? I'm watching movies on an ultrawide HDR display 3440x1440, usually x5 frames per sec. (and I don't know if its revelant but my movies are 4k and about 30/50 Gb per movie.

Just download SVP and install the RIFE pack. With your PC spec you can easily x2 any 4k 21:9 Video and x3 16:9 4k video (downscale video to monitor res then use RIFE)

65

(4 replies, posted in Using SVP)

just male a folder name "portable_config" on the same folder with your mpv.exe, then put the mpv.conf there

example: \MPV\portable_config\mpv.conf

if you want to add .lua scripts put them in
\MPV\portable_config\Scripts\ *.lua here

.conf for Lua scripts
\MPV\portable_config\script-opts\ *.conf here

66

(32 replies, posted in Using SVP)

https://github.com/stax76/awesome-mpv#shaders

there are a lot of shaders out there.

for general use, I only use AMD FSR, very lightweight and good enough to upscale anything.

AutoClickers wrote:
aloola wrote:

Unfortunately, it made the situation worse so I resorted back to Auto. I tried manually setting the threads and realized that Auto probably does a very good just using the correct setting.

8 threads are the best for RIFE, using all cores would slower the FPS.

you might try to downscale your 4k video to 3072 x 1728(20% lower res) or 2560*1440 with SVP options.

another option is to use RIFE V2, but it's having a degraded image bug for now. Still waiting for the fix.


picking a downscale option is the best IMO.

I tried using 8 threads but it the same performance as Auto so it looks like the Auto option is working correctly. Could you please link to where I can find the downscaling options just to check?

https://www.svp-team.com/wiki/Manual:Resizing

Unfortunately, it made the situation worse so I resorted back to Auto. I tried manually setting the threads and realized that Auto probably does a very good just using the correct setting.

8 threads are the best for RIFE, using all cores would slower the FPS.

you might try to downscale your 4k video to 3072 x 1728(20% lower res) or 2560*1440 with SVP options.

another option is to use RIFE V2, but it's having a degraded image bug for now. Still waiting for the fix.


picking a downscale option is the best IMO.

I tested with more videos, looks like V2 only looks bad on 4k video. 1440p looks fine.
so maybe we can use V1 for 4k video, and V2 for 2k and below.

zxcvbnm821 wrote:

Do I need replace the updated vsmlsrt.py if I don't use V2?

you only need to remove the V2 model

Blackfyre wrote:

For the ones above, after testing yesterday, the quality with RIFE that comes with SVP is better than the v2 I updated to via the links above.

Current RIFE with SVP shows less artifacts for example on intros when names are showing up, and smoother overall.

rife_V2 is creating artifacts and the quality seems to drop as well on 4K content looking like 1080p, at least with my MPV settings.

I have the same issue too.


I tested a 4k file with RIFE V2 4.4, 4.6, the image quality has degraded a lot.

https://cdn.discordapp.com/attachments/290709370600423424/1095130933562187847/image.png

I need more people to confirm the bug.

edit: I've just tested with MPV, has the same problem too.


NO RIFE: https://cdn.discordapp.com/attachments/ … _06_AM.png

with RIFE V2: https://cdn.discordapp.com/attachments/ … _37_AM.png

https://www.svp-team.com/wiki/RIFE_AI_interpolation
" Note: when it runs the optimization pass, it's OK for the command-line window to stay for 4-5 or even 8 mins. Don't close it! Wait! "

Rife V2
https://media.discordapp.net/attachments/290709370600423424/1084693213794795610/image.png
old 58.6FPS >61.3FPS

now I can watch 4k@30 x2 in realtime with 3070ti

Rife V1
https://cdn.discordapp.com/attachments/ … /image.png

DragonicPrime wrote:

Tried to do both. Same result. Not sure what's wrong

try to use AIDA64 to benchmark your DDRAM first.
https://cdn.discordapp.com/attachments/290709370600423424/1081482725715873792/image.png

I think 3070ti is the minimum to do 4k@25 x2. My gpu is >90% most of time.
https://cdn.discordapp.com/attachments/290709370600423424/1081170882828963850/image.png