You are not logged in. Please login or register.
SmoothVideo Project → Posts by donnieyeen
Pages 1
Did anybody try to manually update the TRT libraries to v15.1: latest TensorRT library? Any benefits over the standard TRT install from SVP?
New version 4.13_Lite just got posted here: https://github.com/AmusementClub/vs-mlr … nal-models
Happy testing 
The helpers.py update helped fixing the V2 models. I've tried 4.12 V2 model but its quite glitchy,.. not good to be honest, at least on my movies I tested.
I'll try 4.9 model today to see if its any better.
donnieyeen wrote:@Chainik @aloola did any of you try the new TensorRT 9.1.0?
v14.test2 pre-release uses trt 9.1.0 + cuda 12.2.2 + cudnn 8.9.5, which can only run on driver >= 525 and 10 series and later gpus, with improved support for self-attentions found in transformer models.
It does much faster compilation of cache. It used to work with previous version of SVP4, but now I can't get it to work anymore. I am going to buy the SVP4 licence today, really like this program and smooth playback.
9.1 just won't work and it won't boost RIFE performance. so well let's wait for trt 10
https://github.com/AmusementClub/vs-mlrt/discussions/65
I've had 9.1.0 working fine on previous version before this last update of SVP. And I was talking about the time it takes before it generated the engine cache files, its faster then 8.6.
@Chainik @aloola did any of you try the new TensorRT 9.1.0?
v14.test2 pre-release uses trt 9.1.0 + cuda 12.2.2 + cudnn 8.9.5, which can only run on driver >= 525 and 10 series and later gpus, with improved support for self-attentions found in transformer models.
It does much faster compilation of cache. It used to work with previous version of SVP4, but now I can't get it to work anymore. I am going to buy the SVP4 licence today, really like this program and smooth playback.
When I get home I'll test the V2 models, also @aloola shoot me your discord, can add you and we can talk some video players
I've tried all I could think of to make V2 models work but it won't. I've tried manually updating the TRTbackend files from the latest release package on the github. I've updated the vstrt.dll, and the files in vsmlrt-cuda with the latest version which enables TensorRT 9.1.0. The engine cache then gets built by the latest version, it's also much faster on building it compared to the current 8.5.x version.
However then both V1 and V2 models fail to work with SVP4. I've tried also updating the vsmlrt.py file with the latest one on the github, but it doesn't help.
Also both my V1 and V2 cache gets built in the C:\Program Files (x86)\SVP 4\rife\models folders and not appdata. Not like its a problem tbh, as it reads it from there also. I think this could be due to os.path not being available by the python or something.
Hopefully @Chainik can take a look and maybe also update the TRT backends, as they feature quite faster compilation of cache files.
why it reads cache from c:\program files\..., it should be the temp dir path here
I am unsure, but the default installation is now making cached models inside modules folders instead of the appdata. Does anybody else have such issues?
Nvm. I have managed to fix the SVP4 working fine now, only the folder issue is still present.
EDIT2:
The V2 models don't seem to work on my end. Anybody knows how to fix them? Here is what my TRTexec error log says:
[11/13/2023-21:34:53] [E] Unknown option: --precisionConstraints obey
SVP updated, there're a few changes regarding RIFE/trt:
- added 'akarin' plugin, which should improve seeking performance with v1 models up to v2 level
- put any models (including future ones) into SVP 4\rife\models\rife (for V1 models) and SVP 4\rife\models\rife_v2 (for V2 models) and restart SVP - they all will be listed in the video profile; "ensemble' models are supported too.
- a quick fix for DolbyVision playback (color blinking issue)
- "opt shapes" were not set with latest vsmlrt.py which resulted in engine rebuilding for every video resolution regardless of "perf. boost" option
- included model 4.9
Thanks for the update, however I can't get it to work. I've reinstalled SVP4 cleanly just to make sure I haven't messed up anything manually. I've tried using V1 models 4.6 and 4.9, however both times the engine is rebuilding for many resolutions, and then after it finishes the video doesn't play.. stuck or something.
Also getting such error:
These are my settings:
Not sure If I am doing something wrong..
Can someone help me with how to make v2 work?
I've updated to the latest Rife 4.11 model on the github, I've chosen the one that is in rife_v2 folder. I've also updated all the TRT backend files manually, and now can use 9.1.0.
I've manually updated the latest .py from master branch on github as well. Now the V1 models work perfectly fine. Forcing the Implementation like to 2 in py makes it use the rife_v2 folder. It starts to generate the cache and does it about 3 times for each video with v2 version. Then after it finishes, the video just doesn't work and mpv closes. Not sure how to fix this.
@donnieyeen
Before RIFE, I used to match the refresh rate with the screen refresh rate. Not anymore.
As I use 2x with RIFE, it is not necessary to match the refresh rate. As RIFE running at 48FPS appears smoother than previous methods at 120FPS.
For reference, I have an LG C2 set to 4K @ 120Hz @ 4:4:4 @ 10Bit, always. VRR Disabled (because with the C2 it causes flickering, it shouldn't with your monitor). If you have VRR, enable it (as it should match the FPS to the variable refresh rate).
You can just set it to 144Hz + GSync, and enable GSync for Windowed and Full Screen from the nVidia Control Panel. That should be fine.
If you watch 1080p content, you can probably push RIFE to 3x or 4x easily with an RTX 4090. I wouldn't push it more than 4x, as you're just creating extra noise from the fans for no reason tbh.
For 4K, I watch 95% of my content at 4K, I have it set to 2x with my RTX 3090.
Thanks for your reply. One issue that I have is, when I try to resize the 4K movies to my resolution which is ultra-wide 3440x1440, not sure how to best do this. if I use MPC-BE and use the Touch window from outside. I am not sure why but many movies will lag whole system and playback, even at 2x. I must have setup something wrong somewhere. How must I set madVR and MPC-BE settings in order to get the proper smooth playback on my resolution which is 3440x1440. Most movies I was are 4k hdr.
Hey all.
Just setup MPC-BE + MadVR + VapourSynth + Rife AI with TensorRT.
I am on 4090rtx also. I've manually updated the libraries from the github AmusmentClub, replaced the files with v14t and copied the new Rife model 4.7 to the folder.
Now instead of deleting or renaming the Rife to 4.4 or so, I've added the custom version in profile settings:
This then loads the 4.7 onyx and creates the cache file using new one. I must say the playback is quite smooth, but I am not actually sure how I should setup my monitor\framerate.
I am using AW3423DW OLED which is a 175hz display, but I am using it at 3440x1440 with 144hz which supports 10bit HDR. Actually shows as 143.97hz
The video I was testing, is a 4kHDR video with at 23.976. Unsure how I should set this to get best smoothest motion? Thanks for any tips.
Pages 1
SmoothVideo Project → Posts by donnieyeen
Powered by PunBB, supported by Informer Technologies, Inc.