22.05.2024, 18:14
Hello Selur
As promised, I included in vs-deoldify the model: Deep-Exemplar based Video Colorization.
This model is the father of BiSTNet and provides similar results.
I rewrote the rendering code and I was able to speed up the rendering from 2fps up to 17fps (depending on the source and settings).
So this version is fast enough to be used in practice.
I will write a separate post to describe how to use this model, but now let's starting the practical issues.
INSTALLATION
to be able to use this model is necessary to install the following packages.
as usual, is necessary to update the vsdeoldify installation using the attached archive: vsdeoldify-4.0.0_RC1.zip
To be able to use the new model is necessary to download the file colorization_checkpoint.zip available in the release 1.0: https://github.com/zhangmozhe/Deep-Exemp...s/tag/v1.0
the archive have to be unziped in: Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\deepex
Finally is necessary to update DDColor with the attached wheel: vsddcolor-1.0.1-py3-none-any.whl.zip
In this version I added an additional parameter: "scenechange" if this parameter is set will be colored only the frames tagged as scene change frame.
To test if the installation works it is possible to use the following script:
I decided to prefix all the filter functions with the word "HAVC" (Hybrid Automatic Video Colorizer)
When I started to develop this filter was included only DeOldify, but now there is a lot of additional material: 2 coloring models and pre/post filters.
To me this name is more appropriate because is including different models, so it can be considered an hybrid model.
Moreover this filter is built on the shoulders of "Hybrid", without your application it would be very difficult to use this filter.
Please let me know if it is working on your side.
Thanks,
Dan
As promised, I included in vs-deoldify the model: Deep-Exemplar based Video Colorization.
This model is the father of BiSTNet and provides similar results.
I rewrote the rendering code and I was able to speed up the rendering from 2fps up to 17fps (depending on the source and settings).
So this version is fast enough to be used in practice.
I will write a separate post to describe how to use this model, but now let's starting the practical issues.
INSTALLATION
to be able to use this model is necessary to install the following packages.
.\python -m pip install scikit-image==0.22.0
.\python -m pip install numba==0.59.1
.\python -m pip install opencv-contrib-python==4.9.0.80
as usual, is necessary to update the vsdeoldify installation using the attached archive: vsdeoldify-4.0.0_RC1.zip
To be able to use the new model is necessary to download the file colorization_checkpoint.zip available in the release 1.0: https://github.com/zhangmozhe/Deep-Exemp...s/tag/v1.0
the archive have to be unziped in: Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\deepex
Finally is necessary to update DDColor with the attached wheel: vsddcolor-1.0.1-py3-none-any.whl.zip
In this version I added an additional parameter: "scenechange" if this parameter is set will be colored only the frames tagged as scene change frame.
To test if the installation works it is possible to use the following script:
# changing range from limited to full range for vsDeOldify
clip = core.resize.Bicubic(clip, range_in_s="limited", range_s="full")
# setting color range to PC (full) range.
clip = core.std.SetFrameProps(clip=clip, _ColorRange=0)
# adjusting color space from YUV420P16 to RGB24
clip = core.resize.Bicubic(clip=clip, format=vs.RGB24, matrix_in_s="709", range_s="full")
# adding colors using HybridAVC
from vsdeoldify import HAVC_main
clip = HAVC_main(clip=clip, EnableDeepEx=True, ScThreshold=0.1)
# changing range from full to limited range for vsDeOldify
clip = core.resize.Bicubic(clip, range_in_s="full", range_s="limited")
I decided to prefix all the filter functions with the word "HAVC" (Hybrid Automatic Video Colorizer)
When I started to develop this filter was included only DeOldify, but now there is a lot of additional material: 2 coloring models and pre/post filters.
To me this name is more appropriate because is including different models, so it can be considered an hybrid model.
Moreover this filter is built on the shoulders of "Hybrid", without your application it would be very difficult to use this filter.
Please let me know if it is working on your side.
Thanks,
Dan