Welcome to Doom9's Forum, THE in-place to be for everyone interested in DVD conversion.

Before you start posting please read the forum rules. By posting to this forum you agree to abide by the rules.

 

Go Back   Doom9's Forum > Capturing and Editing Video > VapourSynth

Reply
 
Thread Tools Search this Thread Display Modes
Old 7th January 2023, 12:52   #121  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
Quote:
Cuda plugins very slow now
Not really Cuda, more like most of the ai model based stuff.
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 7th January 2023, 13:03   #122  |  Link
kedautinh12
Registered User
 
Join Date: Jan 2018
Posts: 1,808
You forgot "Cu Selur"
kedautinh12 is offline   Reply With Quote
Old 7th January 2023, 13:45   #123  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
\_(ツ)_/
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 7th January 2023, 21:22   #124  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
A few more examples of vs-femasr:
not bad:
https://imgsli.com/MTQ1ODI3
https://imgsli.com/MTQ1ODI4
https://imgsli.com/MTQ1ODI5
https://imgsli.com/MTQ1ODM1
nice detail recovery, but partially too sharp (too much contrast) for my liking, and if you have noise&co that might get enhanced too.
https://imgsli.com/MTQ1ODM5

Cu
Selur
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 27th January 2023, 10:00   #125  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
High Performance GMFSS with RIFE and GAN for Anime Video Frame Interpolation: https://github.com/HolyWu/vs-gmfss_union
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 27th January 2023, 11:00   #126  |  Link
kedautinh12
Registered User
 
Join Date: Jan 2018
Posts: 1,808
Wow, VS development very fast. When i think Avs+ can reach to VS but after Pytorch, NumPy releases VS development more than Avs+ very much
kedautinh12 is offline   Reply With Quote
Old 27th January 2023, 11:55   #127  |  Link
ChaosKing
Registered User
 
Join Date: Dec 2005
Location: Germany
Posts: 1,751
Some quick performance numbers with RTX 3070 TI & 720x480 clip (noisy source):
tested with vsedit, so number should be slighlty higher bcs of the editors small overhead.

Code:
gmfss_union(clip) # ~14fps
gmfss_union(clip, trt=True) # ~17fps, tensor cache took a long time to build
gmfss_union(clip, num_streams=2) # ~17.5fps
gmfss_union(clip, num_streams=3) # ~18.9fps
gmfss_union(clip, trt=True, num_streams=2) # ~21.5fps
gmfss_union(clip, trt=True, num_streams=3) # ~22.5fps
__________________
AVSRepoGUI // VSRepoGUI - Package Manager for AviSynth // VapourSynth
VapourSynth Portable FATPACK || VapourSynth Database || https://github.com/avisynth-repository
ChaosKing is offline   Reply With Quote
Old 27th January 2023, 14:57   #128  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
What speed do you get with RIFE and the anime model?
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 27th January 2023, 18:25   #129  |  Link
ChaosKing
Registered User
 
Join Date: Dec 2005
Location: Germany
Posts: 1,751
https://github.com/HolyWu/vs-rife runs with 175 fps
clip = RIFE(clip)

https://github.com/HomeOfVapourSynth...FE-ncnn-Vulkan
rife.RIFE(clip, model=3) # ~78fps

Look at this perfect frame
https://i.imgur.com/r2GAnRI.jpeg
__________________
AVSRepoGUI // VSRepoGUI - Package Manager for AviSynth // VapourSynth
VapourSynth Portable FATPACK || VapourSynth Database || https://github.com/avisynth-repository

Last edited by ChaosKing; 27th January 2023 at 18:30.
ChaosKing is offline   Reply With Quote
Old 27th January 2023, 18:41   #130  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
Okay, so it's really slow.
(for RIFE enabling sc and setting sc_threshold to something like 0.1 might help a bit)

...

Played around with it and probably won't add this to Hybrid since I don't see any gain from it over RIFE&co atm.
__________________
Hybrid here in the forum, homepage

Last edited by Selur; 28th January 2023 at 09:39.
Selur is offline   Reply With Quote
Old 8th February 2023, 20:00   #131  |  Link
~ VEGETA ~
The cult of personality
 
~ VEGETA ~'s Avatar
 
Join Date: May 2013
Location: Planet Vegeta
Posts: 155
tried installing vsbasicvsr++ but got this error: https://pastebin.com/6VWwaXRd

how can i solve it?
~ VEGETA ~ is offline   Reply With Quote
Old 8th February 2023, 20:07   #132  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
Probably an issue with the cuda dependencies,
here's what I did last time I setup the environment:
  • I created a new empy Vapoursynth-folder
  • downloaded 'Windows embeddable package (64-bit)' from https://www.python.org/downloads/release/python-3108/ (3.11 isn't supported atm. by Vapoursynth)
  • extracted the Python download into the download into the 'Vapoursynth'-folder
  • downloaded 'VapourSynth64-Portable-R60.7z' from https://github.com/vapoursynth/vapoursynth/releases
  • extracted the Vapoursynth portable download into the 'Vapoursynth'-folder
  • downloaded get-pip.py from https://bootstrap.pypa.io/get-pip.py and save it into the 'Vapoursynth'-folder
  • opened a 'Windows Command Prompt'-window and navigate into the 'Vaporusynth'-folder
  • installed pip by calling :
    Code:
    pyhton get-pip.py
  • opened the python310._pth in a text addition and added the following to lines above anything else in that file and saved the file
    Code:
    Scripts
    Lib\site-packages
  • installed VSGAN
    • python -m pip install vsgan
    • python -m pip install torch===1.13.0+cu117 torchvision==0.14.0 -f https://download.pytorch.org/whl/torch_stable.html
    • installed BASICVSR++
      Code:
      python -m pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu117/torch1.13/index.html
      python -m pip install tqdm
      python -m pip install opencv-python
      python -m pip install --upgrade vsbasicvsrpp
      python -m vsbasicvsrpp
  • installted RIFE
    • downloaded https://github.com/HolyWu/vs-realesr...5.2.2_win64.7z (there's a newer versio now)
    • extractedtensorrt-8.5.2.2-cp310-none-win_amd64.whl into my Vapoursynth folder
    • python -m pip install tensorrt-8.5.2.2-cp310-none-win_amd64.whl
    • deleted tensorrt-8.5.2.2-cp310-none-win_amd64.whl
    • python -m pip install --upgrade vsrife
    • created a folder 'vsrife_dependencies' inside the Vapoursynth folder and copied the other files form the CUDA-11.7_cuDNN-8.6.0_TensorRT-8.5.1.7_win64.7z into it. This folder need to be added to when using vs-rife using:
      Code:
      import site
      # add vs-rife dependencies to the path
      path = site.getsitepackages()[0]+'/torch_dependencies/'
      path = path.replace('\\', '/')
      import os
      os.environ["PATH"] = path + os.pathsep + os.environ["PATH"]
    • downloaded the models using:
      Code:
      set PATH=i:\Hybrid\64bit\Vapoursynth\torch_dependencies\bin;%PATH
      python -m vsrife
    • installed SWINIR
      Code:
      python -m pip install --upgrade vsswinir
      python -m vsswinir
  • installed DPIR and onnxruntime-gpu
    Code:
    python -m pip install --upgrade vsdpir
    python -m pip install --upgrade onnxruntime-gpu
    python -m vsdpir
  • created a onnxruntime_dlls folder inside the Vapoursynth folder.
    I copied from cudnn-11.4-windows-x64-v8.2.4.15.zip and NVIDIA CUDA SDK 11.4.1 runtimes the following files into the folder:
    • cublas64_11.dll
    • cublasLt64_11.dll
    • cudart64_110.dll
    • cudnn_cnn_infer64_8.dll
    • cudnn_ops_infer64_8.dll
    • cudnn64_8.dll
    • cufft64_10.dll
    • cufftw64_10.dll
    • msvcp140.dll
    • nvinfer.dll
    • nvinfer_builder_resource.dll
    • nvinfer_plugin.dll
    • nvonnxparser.dll
    • nvparsers.dll
    • vcruntime140.dll
    • vcruntime140_1.dll
  • When using vsdir or realesrgan in a Vapoursynth script:
    Code:
    # Import libraries for onnxruntime
    import site
    import ctypes
    path = site.getsitepackages()[0]+'/onnxruntime_dlls/'
    ctypes.windll.kernel32.SetDllDirectoryW(path)
    needs to be added to the script to load the dlls.
  • installed REALESRGAN (which also uses onnxruntime)
    Code:
    python -m pip install --upgrade vsrealesrgan
    python -m vsrealesrgan
  • Installed HINet
    Code:
    python -m pip install --upgrade vshinet
    python -m vshinet

Cu Selur

Ps.: also send you a link to my current Hybrid dev and torch addon, going to bed now. You might want to checkout
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 24th March 2023, 19:05   #133  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
Anyone managed to get BasicVSR++ v2.0.0 running in a portable Vapoursynth setup?
I'm stuck https://github.com/HolyWu/vs-basicvsrpp/issues/29 installing mmcv-full.

Cu Selur
__________________
Hybrid here in the forum, homepage

Last edited by Selur; 24th March 2023 at 20:12.
Selur is offline   Reply With Quote
Old 25th March 2023, 09:56   #134  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
HolyWu could help, using:
Code:
python -m pip install torch==1.13.1+cu117 torchvision==0.14.1+cu117 --extra-index-url https://download.pytorch.org/whl/cu117
python -m pip install -U openmim
python -m mim install "mmcv-full>=1.7.1"
python -m pip install -U vsbasicvsrpp
python -m vsbasicvsrpp
worked

Cu Selur
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 31st March 2023, 13:01   #135  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
With the release of Vapoursynth R62, it's either Python 3.11 or Python 3.8. (Python 3.8 is still there to support old Windows versions and Python 3.10 support was dropped not to having to support multiple Python versions.)
So Python 3.11 is probably what most folks want to go for, but since there are no cp311 pytorch versions over at https://download.pytorch.org/whl/torch/ for Windows I was wondering if someone got a way to get all the ai stuff working with Python 3.11 and Vapoursynth R62?

Cu Selur
__________________
Hybrid here in the forum, homepage
Selur is offline   Reply With Quote
Old 1st April 2023, 10:46   #136  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
btw. did anyone test https://github.com/HolyWu/vs-codeformer ?
https://imgsli.com/MTY2MTM5
Suzie: https://imgsli.com/MTY2MTQz
__________________
Hybrid here in the forum, homepage

Last edited by Selur; 1st April 2023 at 11:09.
Selur is offline   Reply With Quote
Old 1st April 2023, 11:24   #137  |  Link
ChaosKing
Registered User
 
Join Date: Dec 2005
Location: Germany
Posts: 1,751
lol they get entirely new faces
__________________
AVSRepoGUI // VSRepoGUI - Package Manager for AviSynth // VapourSynth
VapourSynth Portable FATPACK || VapourSynth Database || https://github.com/avisynth-repository
ChaosKing is offline   Reply With Quote
Old 1st April 2023, 11:27   #138  |  Link
Selur
Registered User
 
Selur's Avatar
 
Join Date: Oct 2001
Location: Germany
Posts: 7,033
Yes, but in combination with realesrgan this might have its uses.
=> I have to check what happens if this is applied to different actors,...
https://imgsli.com/MTY2MTQ0
https://imgsli.com/MTY2MTQ2
https://imgsli.com/MTY2MTQ3
https://imgsli.com/MTY2MTQ5
seems more like a gimmick filter than really usable atm., but its impressive.

Cu Selur
__________________
Hybrid here in the forum, homepage

Last edited by Selur; 1st April 2023 at 11:50.
Selur is offline   Reply With Quote
Old 1st April 2023, 15:04   #139  |  Link
Dogway
Registered User
 
Join Date: Nov 2009
Posts: 2,255
Some people mix it with GFPGAN or other face models, haven't played with NN but it seems there's more work to it than a simple button push.
Usually whenever I use NN upscaling I always follow a downscale, to hide the pristine AI look and blend everything together.
Very excited to get into this AI craze soon.
__________________
i7-4790K@Stock::GTX 1070] AviSynth+ filters and mods on GitHub + Discussion thread

Last edited by Dogway; 1st April 2023 at 15:06.
Dogway is offline   Reply With Quote
Old 1st April 2023, 16:21   #140  |  Link
HolyWu
Registered User
 
Join Date: Aug 2006
Location: Taiwan
Posts: 391
Quote:
Originally Posted by Selur View Post
Yes, but in combination with realesrgan this might have its uses.
=> I have to check what happens if this is applied to different actors,...
https://imgsli.com/MTY2MTQ0
https://imgsli.com/MTY2MTQ2
https://imgsli.com/MTY2MTQ3
https://imgsli.com/MTY2MTQ5
seems more like a gimmick filter than really usable atm., but its impressive.

Cu Selur
You should also try weight=1 if you prefer a higher-fidelity result.
HolyWu is offline   Reply With Quote
Reply

Thread Tools Search this Thread
Search this Thread:

Advanced Search
Display Modes

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT +1. The time now is 05:57.


Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2023, vBulletin Solutions Inc.