You are not logged in. Please login or register.
SmoothVideo Project → Using SVP → New RIFE filter - 3x faster AI interpolation possible in SVP!!!
This new stuff does seem extremely over complicated and Rife is flawlessly smooth with minimal artefacts. It just needs to be less resource hungry and reduce artefacts even further. But maybe Rife also seemed extremely complicated before members worked through it and got it to where it is now. So I think the Video Deblurring and Video Frame Interpolation championed by @UHD should be in its own thread.
Thank you @UHD for all that detailed analysis and what can be done for the future.
Loved reading it.
Rife is flawlessly smooth with minimal artefacts.
It has different artifacts, although minimal the vast majority of the time (compared to prior methods). However, when they are noticeable, like in the beginning of the movie AIR that came out recently (scenes with a lot of noise especially), they are very heavy and noticable. Or the HBO (static) background at the start of GoT/HoTD/etc
So I think the Video Deblurring and Video Frame Interpolation championed by @UHD should be in its own thread.
Once there is a working model, there should definitely be a new thread for it. But I feel as though that is a while away.
Wishing @UHD luck with his proposal.
Thank you @UHD for all that detailed analysis and what can be done for the future.
Loved reading it.
dawkinscm wrote:Rife is flawlessly smooth with minimal artefacts.
It has different artifacts, although minimal the vast majority of the time (compared to prior methods). However, when they are noticeable, like in the beginning of the movie AIR that came out recently (scenes with a lot of noise especially), they are very heavy and noticable. Or the HBO (static) background at the start of GoT/HoTD/etc
Yes that is true. The opening scenes in Blade Runner 2049 and the star fields in Gravity have a horrible artefacts but they don't last long. Also I don't think either film has the kind of slow pan that causes problems for Automatic mode so I could use that instead and the issues go away.
So I think the Video Deblurring and Video Frame Interpolation championed by @UHD should be in its own thread.
Once there is a working model, there should definitely be a new thread for it. But I feel as though that is a while away.
Wishing @UHD luck with his proposal.
Yes but this isn't the easiest thread to navigate already and the last page is effectively a large dump of info not related to the topic. Maybe a single post intro should be placed here which then links to the new thread.
Hi,
Sorry if this question has been asked before: is there a way to use the standard timing/masking settings that normal SVP has with RIFE? I've found that I get the proper level of smoothing I like (no SOE) by being able to limit the number of interpolated vs original frames and setting masking to "Strong" or a higher custom setting.
In short, I'd like to be able to play at 24fps x 3 with two normal frames and one interpolated frame (or 24fps x 5 with 1 interpolated frame; would want to test). I'd like to be able to tinker with masking. Is this possible? Just RIFE at 48fps is too smooth, but the lack of artifacts is incredible. I'd like to be able to blend/blur these results a little further to get it to feel closer to 24fps but with less blur.
Hello, paid user here, one thing to ask:
How to re-generate the rife model engine in AppData in once a certain resolution is mistakenly generated(not that I want),
for example, I rotate the player last time and it remembers the settings, but this time when I open a new resolution video whose rife model has never been generated,
the SVP will sure thinks it's a new resolution and the CLI will certainly generates this new wrong "portrait" type of resolution, which is sure not that I want.
From the last time I tried, I can tell SVP will regardlessly wrongly generates the new model without any "portrait identifications or references",
and if you delete the wrong output model from AppData directly, the SVP will just play the video without rife next time and not to re-generate the exact resolution model(once failed, failure forever?),
which is not quite "smart" and you can only re-install the whole program and re-generate the whole many resolution models to get it work again.
This is quite in-convenientcon from what I can see, so I has this question for the developers, is there any solution or updates for this?
> How to re-generate the rife model engine in AppData in once a certain resolution is mistakenly generated(not that I want),
delete corresponding files?
Chainik I have a question, are the engine cache models system dependent? Or can they be transferable?
For example, once I have completed the majority of resolutions, or all the ones I use. Can I basically compress them into one file, back them up, place them back after I format? Or even use them in another system completely?
I think it's specific to the GPU model and TensortRT version in use.
I think it's specific to the GPU model and TensortRT version in use.
On a related question. I notice if I delete the Rife cache then even if new entries are created the cache folder stays empty and the rife folders also stay empty yet everything still works. What am I missing?
For questions below my message:
Chainik wrote:> How to re-generate the rife model engine in AppData in once a certain resolution is mistakenly generated(not that I want),
delete corresponding files?
nope, like I said, it will just play the video without rife re-generated like the default, only reinstall the whole program will somehow re-activate that procedure, seems like there's some registry info missing?
That's exactly what I found like I said above.
We haven't updated for some time, I saw that there are new versions of TensorRT OSS v8.6.1/v14. Latest TensorRT library, I don't know if you plan to upgrade or if it makes any sense/benefit to do so. Sometimes the updates mean big changes, other times, for example, drivers, big problems.Big fan of Rife option and looking forward to see it improve. Thanks for the work you already done.
No need to update. I've made some tweaks using the latest scripts but Rife is still Rife, and v2 still FF/REW instantly. I wouldn't bother.
We haven't updated for some time, I saw that there are new versions of TensorRT OSS v8.6.1/v14. Latest TensorRT library, I don't know if you plan to upgrade or if it makes any sense/benefit to do so. Sometimes the updates mean big changes, other times, for example, drivers, big problems.Big fan of Rife option and looking forward to see it improve. Thanks for the work you already done.
> How to re-generate the rife model engine in AppData in once a certain resolution is mistakenly generated(not that I want),
delete corresponding files?
nope, like I said, it will just play the video without rife re-generated like the default, only reinstall the whole program will somehow re-activate that procedure, seems like there's some registry info missing?
not sure what you guys mean...
if there's a file for given resolution in the cache folder - it reads it
if the file isn't there, it generates it, end of story 
simple as a AK-47 
Could not read timing cache from: C:\Users\chain\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.1920x1088_fp16_no-tf32_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-2060_3dcbe72f.engine.cache. A new timing cache will be generated and written.
That's weird, catshit. I just tested to confirm and mine works as one would expect, and Chainik described. Deleting the files in "AppData\Roaming\SVP4\cache\Program Files (x86)\SVP 4\rife\models\rife" causes them to regenerate next time I open a video of that resolution.
not sure what you guys mean...
if there's a file for given resolution in the cache folder - it reads it
if the file isn't there, it generates it, end of storyCould not read timing cache from: C:\Users\chain\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.1920x1088_fp16_no-tf32_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-2060_3dcbe72f.engine.cache. A new timing cache will be generated and written.
Not for me. I can literally delete the models/rife folder and it does one of two things. It either keeps on working as if the cache is still there and nothing changes. Or it does generate a new timing cache but the rife folder does not reappear and if the empty cache folder is there then it stays empty. The only thing I can think of is that I am using a later version of the Python wrapper script (3.15.23) and rife v2.
Chainik wrote:not sure what you guys mean...
if there's a file for given resolution in the cache folder - it reads it
if the file isn't there, it generates it, end of storyCould not read timing cache from: C:\Users\chain\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.1920x1088_fp16_no-tf32_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-2060_3dcbe72f.engine.cache. A new timing cache will be generated and written.
Not for me. I can literally delete the models/rife folder and it does one of two things. It either keeps on working as if the cache is still there and nothing changes. Or it does generate a new timing cache but the rife folder does not reappear and if the empty cache folder is there then it stays empty. The only thing I can think of is that I am using a later version of the Python wrapper script (3.15.23) and rife v2.
When your terminal pops up during the model generation does it say it's looking in that path? To me that sounds like your RIFE install is just referencing a different folder. I'm on RIFE V1, maybe V2 has a different path?
the path is different in the original "Python wrapper script"
the path is different in the original "Python wrapper script"
I see. The path code is different. Thanks I'll look into this further.
OK I see modified code for SVP. It works as expected now. I just have to remember to add this for future revisions. I don't have a temp directory set up so I guess it was using the current working directory. Can't find it though. I've never coded in Python so this is a fun way to learn bits and pieces of Python coding. Anyway thanks @Chainik.
A few months ago the direct show players weren't even close to the same quality as MPV. But as an experiment I've set up mpc-be with Nvidia super-resolution running Rife v2 upscaling to 4K. I'm only upscaling on the Y axis because the resolution of my files is 1920x2160p. I compared it to using MPV it is "almost" identical except for the areas where you have little control like colour, banding and aliasing. Also rife now works just as it does on MPV which again is another great improvement. I also tried Madvr for much which enables control over aliasing, banding and colour management and they were much better (but still not quite as good as MPV). Madvr can't be used with Nvidia super-resolution but it was the best option for picture quality in my use case.
Maybe it's always been this way and my issues were local, but Rife v2 is now very useable, even with Madvr upscaling to 4k. MPV still has the advantage, but the gap between the two isn't a great as it was before. Nice to have the choice 
Blackfyre
To summarise:The best current model is:
rife_v4.6_ensemble.onnx from the v2 package: https://github.com/AmusementClub/vs-mlr … e_v2_v1.7zIf someone is not able to use the full capacity of their screen with this model, for example to interpolate 4K files, it is worth using a faster model, with a small loss of quality:
rife_v4.6.onnx from the v2 package: https://github.com/AmusementClub/vs-mlr … e_v2_v1.7zIf anyone is interested in much, much better quality than RIFE interpolation I will write about it soon, here on this forum. Please give me another week, maybe two weeks, until I update my repository on GitHub.
I would love to use Ensemble for my 1920x2160 files, but no matter what I try, my 3080 is basically stuck at 100% and the picture is very jerky.
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.
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
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.
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.
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.
It's a very minor change which you can see if you search for ensemble in the wrapper code. If this doesn't make sense then unless you have a 3090ti or above just leave it for now.
[
It's a very minor change which you can see if you search for ensemble in the wrapper code. If this doesn't make sense then unless you have a 3090ti or above just leave it for now.
Is it difficult to explain how to do it? I would like to try it out and see the difference good or bad for myself and learn something new in the process. Is there any documentation on the forum how to do it? I find users saying they have used it, one asking to implement an on/off mode in svp, but no guide on how to do it.
Hence my initial question.
SmoothVideo Project → Using SVP → New RIFE filter - 3x faster AI interpolation possible in SVP!!!
Powered by PunBB, supported by Informer Technologies, Inc.