Search options (Page 15 of 18)
defensive.display90 wrote:Which model is currently the best for non-anime content? Most discussions I see are based around anime.
Also, what exactly do the ensemble models do differently?
Don't bother with the ensemble models. Whatever they are supposed to do isn't worth it. Also don't worry about the "anime" tag because they all work fine with non anime stuff. If you have a 30 series Nvidia GPU or above and use TensorRT then try Rife 4.9 if your GPU can handle it or Rife 4.6 and below if it can't.
Chainik wrote: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
Excellent! The new helper script detect any model you add without having to make manual changes, although v12 currently doesn't work. Rife v2 seeking was almost immediate, with akarin the seeking is immediate.
Great update! Nice work and thank you 
Edit: They've literally just released an update to v12 and it is working. Will update with results.
Results: Rife 4.12 almost identical to 4.11 but has some fixes. Rife 4.9 still the best overall for me.
Rife 4.11 is out. The file is much smaller than any other Rife model but is just as computationally intensive for GPUs and it has a couple of other small issues. Also I checked 4.9 with my hard coded subtitled files but I didn't have any warping issues so I'm staying with that.
aloola wrote:subtitles issue you mentioned
I never mentioned this.
Subtitles was someone else.
aloola wrote: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.
The reason new models are being released is because they are still evolving through training, so what you are suggesting makes no sense. If 4.6 works for you then fine. But the one I like the most is the one with the least artefacts and best motion and that is currently 4.9+.
aloola wrote:...
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.
Your figures confirm my findings about GPU usage. Rife 4.10 is by far the worst. There is very little quality difference between 4.9 and 4.10 but there is a massive hit on GPU performance. I will probably check out the subtitles issue you mentioned because that would be a major problem.
The recent Rife networks are being specifically trained for Anime so I suppose any improvements in live video processing is a bonus. But there are so many Anime models I'm not sure why we need another one
Rife 4.10 is out but I strongly recommend leaving it alone because of excessively high GPU usage. But if you wish to try it then YMMV.
Update: I tried v2. After reboot it only made a 1-2% difference for me.
It's been a while since I properly looked at the Python wrapper code. Looking at your post reminded me of how I handled the v2 code previously and not the "hack" I did this time.
I also added the lines below to the Python script (replacing the temp dir conditional) but it didn't work.
cws wrote:You can update `vsmlrt.py` by getting a copy from the `AmusementClub/vs-mlrt` repo, then modifying:
alter_engine_path = os.path.join(
os.path.expandvars("%APPDATA%\\SVP4\\cache\\"),
os.path.splitdrive(engine_path)[1][1:]
)
I had this issue before but I can't remember how I fixed it. But since it makes no obvious difference to how Rife works I'll probably just leave it as it is for now.
maorgr wrote:it didn't change anything - i can only do rife 49 with avisynth... vapoursynth doesn't work and keeps spitting out errors.
i dont know python, but this is the error message i'm getting when using Vapoursyth:
[11/05/2023-17:16:04] [E] Error[4]: [network.cpp::nvinfer1::Network::validate::3100] Error Code 4: Internal Error (input: for dimension number 1 in profile 0 does not match network definition (got min=11, opt=11, max=11), expected min=opt=max=7).)
[11/05/2023-17:16:04] [E] Error[2]: [builder.cpp::nvinfer1::builder::Builder::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
[11/05/2023-17:16:04] [E] Engine could not be created from network
[11/05/2023-17:16:04] [E] Building engine failed
[11/05/2023-17:16:04] [E] Failed to create engine from model or file.
[11/05/2023-17:16:04] [E] Engine set up failed
Check that you don't have your own local copies of vapoursynth or avisynth installed. That will cause problems.
cws wrote: alter_engine_path = os.path.join(
os.path.expandvars("%APPDATA%\\SVP4\\cache\\"),
os.path.splitdrive(engine_path)[1][1:]
)
I always forget about this. It doesn't really matter because Rife still works without it. But it is neater and I might add it back for any future update.
maorgr wrote:dawkinscm wrote:The simplest way to install a new Rife model is to copy the Rife onnx file to the SVP rife directory then modify the rife_trt_model property under the video profiles options settings in SVP.
I decided to compare Rife 4.9 v1 with Rife 4.9 v2. The good news is that as expected seek speed is almost instantaneous seeking and for me it uses about 4 percent less GPU than v1. However, even though it technically uses a little less GPU power, my GPU temps went up about 4 degrees. BTW I don't watch 4K with Rife, but so far I haven't seen any resolution issues with v2.
Could you be kind and specify where could I get 4.9 v2, please ?
https://github.com/AmusementClub/vs-mlr … e_v2_v2.7z
This is the specific URL but the page itself has lots of other models too
Today I decided to compare Rife 4.6 v2 with 4.9 v2. After a full reboot, Rife 4.9 v2 GPU usage dips below 70% into the high 60s and averages around 74%. This is better than I reported yesterday. But Rife 4.6 v2 is below 50% Both models use about 8.6GB of RAM. Please note that my GPU stats are always a little higher than most because the GPU is doing multiple things.
thericeking wrote:I get the following message on the dos window when I used 4.9 for the first time. I'm driving a RTX 3080 "Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32."
We all get that. It's a warning, not an error. It's mostly fine.
The simplest way to install a new Rife model is to copy the Rife onnx file to the SVP rife directory then modify the rife_trt_model property under the video profiles options settings in SVP.
I decided to compare Rife 4.9 v1 with Rife 4.9 v2. The good news is that as expected seek speed is almost instantaneous seeking and for me it uses about 4 percent less GPU than v1. However, even though it technically uses a little less GPU power, my GPU temps went up about 4 degrees. BTW I don't watch 4K with Rife, but so far I haven't seen any resolution issues with v2.
Rife 4.9 is out. First I've got "some" GPU peformance back. Before I was peaking at 83% now I'm peaking at 79%. One of my test files no longer shows any artefacts. Another test file shows improvement and the artefact can be mitigated by reducing SC. One related artefact is still present but seems to have slightly improved as well.
Drakko01 wrote:s Rife 4.9 better or improved for movies in general or only focused on anime, thanks in advance.
They said Rife 4.7 was focused on Anime but it also reduced or removed artefacts from my test movies. Rife 4.9 improves upon 4.7 by removing or reducing more artefacts.
I use Rife almost 100% of the time but I don't think SVP itself has changed much in the last few years. If you are using Rife 4.4 or 4.6 then there should be no issues since both are working fine for most of us. If you are trying to use 4.7/4.8 then many will have problems because they are a lot harder on GPUs.
Xenocyde wrote:dawkinscm wrote:Xenocyde wrote:Can you please post the link?
L.E.: Found in another thread, never mind.
L.E.2: Ah but this is not an onnx file. How do I install this in SVP?
You can't because you probably found the source files like I did at first. This https://github.com/AmusementClub/vs-mlr … l-20220923 is the link to the onnx files
Thanks for the onnx link! Tested it a bit, some artifacts are still there, but at least it fixes the microstuttering issues from 4.7. Optimization took 1 minute and 5 seconds for me on an RTX 4080.
I have a standard set of test files I use that highlight various issues with interpolation. Rife 4.6 is smooth with fewer artefacts that SVP. But the few artefacts it had were much worse than any seen in non Rife modes. Those nasty artefacts are either gone or very much lessened with 4.7. Rife 4.8 optimization is much faster but nothing else has changed. Except I do get a few more microstutters which is the opposite to what you see. But then my setup is hypersensitive to stutters so I probably see a few more than you or other people.
Xenocyde wrote:dawkinscm wrote:Thanks to @Minimunch57 for posting the latest Rife 4.8 update. At one point I saw a massive GPU usage improvement, but that was temporary. With Rife 4.7 there is a clear visual improvement over 4.6. The only difference I see in 4.8 is that the optimization completes in less than a minute as opposed to the 3-5 minutes on previous versions.
Can you please post the link?
L.E.: Found in another thread, never mind.
L.E.2: Ah but this is not an onnx file. How do I install this in SVP?
You can't because you probably found the source files like I did at first. This https://github.com/AmusementClub/vs-mlr … l-20220923 is the link to the onnx files
Thanks to @Minimunch57 for posting the latest Rife 4.8 update. At one point I saw a massive GPU usage improvement, but that was temporary. With Rife 4.7 there is a clear visual improvement over 4.6. The only difference I see in 4.8 is that the optimization completes in less than a minute as opposed to the 3-5 minutes on previous versions.
DragonicPrime wrote:As far as I know, DLSS 3.5 only helped the denoising technique used in Ray Tracing workloads like Path Tracing in cyberpunk. Frame Generation doesn't look any better or run any better
Correct. Both AMD and Nvidia Frame Gen is partly built into the game which is why only certain games have that feature. AMD has a driver only based version as well but in short, SVP is better.
maorgr wrote:dawkinscm wrote:Chainik wrote:dunno, there're no errors in that log... does it work for 1080p?
maybe it's similar to https://www.svp-team.com/forum/viewtopic.php?id=7033
all we can do is update vsmlrt, may be there's some known and fixed issue with 4090 / latest drivers /etc...
I think the vsmirt-cuda folder needs updating. The Python script is not important but you might as well update it anyway.
Hello,
Thanks for responding.
Drivers are the latest (of course).
how do I update the vsmirt-cude folder though ?
Thanks for your reply in advance.
First I recommend rolling back SVP if you can. If you can't then I would recommend removing SVP completely, rebooting your machine. then re-downloading and installing it again.
But if you really want to do this then try downloading VSTRT-Windows-x64.v14.test.7z from https://github.com/AmusementClub/vs-mlr … g/v14.test then replace the files under the Rife folder. If that doesn't work then then you might need to download the full vsmlrt-windows-x64-cuda.v14.test.7z file. This is the file I downloaded and used it to replace the executables and libraries in the Rife folder. If it is still not clear what you need to do from my instructions then as before I recommend you rollback SVP , re-install or wait for an update.
Chainik wrote:dunno, there're no errors in that log... does it work for 1080p?
maybe it's similar to https://www.svp-team.com/forum/viewtopic.php?id=7033
all we can do is update vsmlrt, may be there's some known and fixed issue with 4090 / latest drivers /etc...
I think the vsmirt-cuda folder needs updating. The Python script is not important but you might as well update it anyway.
chrisssj2 wrote:Whats the real benefit of using this? are there comparison screenshots somewhere?
It depends on what you want. If you want the smoothest motion available with fewest artefacts then Rife is the best. The main downsides to Rife are that the few remaining artefacts can quite often be worse than Automatic. Also you will need at least a medium to high end 30 series Nvidia GPU.
Blackfyre wrote:dawkinscm wrote:It's strange that some of you are having issues because there have not been any reported stability issues with 0.36. I updated my version of SVP and had no issues. So my recommendation would be to completely uninstall SVP, reboot then try again.
Just to clarify, I don't have any issues with 0.36
Just wanted to test the latest versions that were linked above by Chainik
At the time of writing, I built a recent update based on a change in vsync timing. But even that is specific to me and would have little effect for you. Unless you are monitoring the updates and have a specific reason to update then I don't think you will notice any difference. In the end, the latest builds are just 0.36 with some bug fixes and minor updates.
Blackfyre wrote:Does it have to replace the MPV in the SVP folder?
Unless you change the settings to point somewhere else then you have to replace mpv.com and mpv.exe in the mp64 folder. The v3 version works just fine. But it's going to be a similar version to what was downloaded with SVP. It's strange that some of you are having issues because there have not been any reported stability issues with 0.36. I updated my version of SVP and had no issues. So my recommendation would be to completely uninstall SVP, reboot then try again.
Blackfyre wrote:RTX 3090 is no longer capable of pushing 4K at 2X with 4.7 (at least with my configuration, I will try to lower them and see if it's possible, but doubt it).
Not surprising. I think running 4.7 at 1920x2160/60Hz with my config would kill my old 3080, never mind 4k/60hz which uses about 95% on a high end 40 series GPU.
Posts found: 351 to 375 of 442