Deoldify Vapoursynth filter

[Selur]

I installed the dev version...

I wrote:

Uploaded a new test version (Hybrid_deoldify; not dev version).

[Dan64]

I found the option, was hidden due to the small size of my window GUI, I enlarged it and now is visible.

The option is Ok, but should be enabled (no gray-out) even when the selected method is HAVC only.
Please, could you update the GUI.

Thanks,
Dan



P.S.
I'm writing the user guide, when it will be released it should be useful in understanding all the HAVC options.

[Selur]

I'm writing the user guide, when it will be released it should be useful in understanding all the HAVC options.

Looking forward to it.
Atm. with each change it makes less and less sense to me.
updated the Hybrid_deoldify download

Cu Selur

[Dan64]

I'm writing the user guide, when it will be released it should be useful in understanding all the HAVC options.

Looking forward to it.
Atm. with each change it makes less and less sense to me. 
updated the Hybrid_deoldify download

Cu Selur

It is working now.

Thanks,
Dan

[Selur]

Nice.
I uploaded a new dev with these changes.

Cu Selur

[Selur]

https://github.com/HolyWu/vs-rife/commit...dd67e109e0 <- that will probably cause problems with other projects,...

[Selur]

After running:

python -m pip install -U packaging setuptools wheel
python -m pip install --pre -U torch torchvision --index-url https://download.pytorch.org/whl/nightly/cu126
python -m pip install --no-deps --pre -U torch_tensorrt --index-url https://download.pytorch.org/whl/nightly/cu126
python -m pip install -U tensorrt-cu12 tensorrt-cu12_bindings tensorrt-cu12_libs --extra-index-url https://pypi.nvidia.com
python -m pip install -U vsrife
python -m vsrife

to update to the latest vs-rife (5.5.0: https://github.com/HolyWu/vs-rife)
I'm back to:

Failed to evaluate the script:
Python exception: Failed to initialize ColorMNet[remote] try ColorMNet[local]

Traceback (most recent call last):
File "src\\cython\\vapoursynth.pyx", line 3387, in vapoursynth._vpy_evaluate
File "src\\cython\\vapoursynth.pyx", line 3388, in vapoursynth._vpy_evaluate
File "J:\tmp\tempPreviewVapoursynthFile12_44_37_338.vpy", line 47, in
clip = HAVC_main(clip=clip, EnableDeepEx=True, DeepExMethod=0, DeepExRefMerge=0, DeepExOnlyRefFrames=False, ScFrameDir=None, DeepExModel=0, DeepExEncMode=0, DeepExMaxMemFrames=0)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\__init__.py", line 327, in HAVC_main
clip_colored = HAVC_deepex(clip=clip, clip_ref=clip_ref, method=DeepExMethod, render_speed=DeepExPreset,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\__init__.py", line 626, in HAVC_deepex
clip_colored = vs_colormnet(clip, clip_ref, clip_sc, image_size=-1, enable_resize=enable_resize,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\vsslib\vsmodels.py", line 45, in vs_colormnet
return vs_colormnet_remote(clip, clip_ref, clip_sc, image_size, enable_resize, frame_propagate,
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\colormnet\__init__.py", line 136, in vs_colormnet_remote
HAVC_LogMessage(MessageType.EXCEPTION, "Failed to initialize ColorMNet[remote] try ColorMNet[local]")
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\vsdeoldify\vsslib\vsutils.py", line 48, in HAVC_LogMessage
raise vs.Error(message_text)
vapoursynth.Error: Failed to initialize ColorMNet[remote] try ColorMNet[local]

when using Model is set to "ColorMNet".
Would be nice if you can fix this? (I guess a new spatial_correlation_sampler is required)

Cu Selur

[Dan64]

The problem is that you updated also pytorch. Please remain to torch-2.6.0.dev20241101+cu124. vs-RIFE is requiring PyTorch 2.6.0.dev20241023 or later so torch-2.6.0.dev20241101  is still good. If you upgrade PyTorch not only will broke vs-deoldify but also BasicVSR++ because mmvc 2.0 is not working with a version of PyTorch above 2.6.0.dev20241101.
Please update vs-rife but not PyTorch.

Dan

[Selur]

Please update vs-rife but not PyTorch.

Already tried that.
That does not work, 'python -m pip install -U vsrife' on its own will just reinstall 5.4.1.

Cu Selur

[Dan64]

You can download the wheel from https://pypi.org/project/vsrife/#files

Then you can install vs-rife 5.5.0 with the following command

PS D:\Programs\Hybrid\64bit\Vapoursynth> .\python -m pip install vsrife-5.5.0-py3-none-any.whl
Processing d:\programs\hybrid\64bit\vapoursynth\vsrife-5.5.0-py3-none-any.whl
Requirement already satisfied: numpy in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife==5.5.0) (1.26.4)
Requirement already satisfied: requests in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife==5.5.0) (2.32.3)
Requirement already satisfied: torch>=2.6.0.dev in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife==5.5.0) (2.6.0.dev20241101+cu124)
Requirement already satisfied: tqdm in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife==5.5.0) (4.66.5)
Requirement already satisfied: vapoursynth>=66 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from vsrife==5.5.0) (68)
Requirement already satisfied: filelock in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (3.13.1)
Requirement already satisfied: typing-extensions>=4.10.0 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (4.12.2)
Requirement already satisfied: networkx in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (3.3)
Requirement already satisfied: jinja2 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (3.1.4)
Requirement already satisfied: fsspec in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (2024.6.1)
Requirement already satisfied: setuptools in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (70.0.0)
Requirement already satisfied: sympy==1.13.1 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from torch>=2.6.0.dev->vsrife==5.5.0) (1.13.1)
Requirement already satisfied: mpmath<1.4,>=1.1.0 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from sympy==1.13.1->torch>=2.6.0.dev->vsrife==5.5.0) (1.3.0)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from requests->vsrife==5.5.0) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from requests->vsrife==5.5.0) (3.10)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from requests->vsrife==5.5.0) (2.2.3)
Requirement already satisfied: certifi>=2017.4.17 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from requests->vsrife==5.5.0) (2024.8.30)
Requirement already satisfied: colorama in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from tqdm->vsrife==5.5.0) (0.4.6)
Requirement already satisfied: MarkupSafe>=2.0 in d:\programs\hybrid\64bit\vapoursynth\lib\site-packages (from jinja2->torch>=2.6.0.dev->vsrife==5.5.0) (2.1.5)
Installing collected packages: vsrife
  Attempting uninstall: vsrife
    Found existing installation: vsrife 5.4.1
    Uninstalling vsrife-5.4.1:
      Successfully uninstalled vsrife-5.4.1
Successfully installed vsrife-5.5.0

It worked on my side (no pytorch upgrade).

Dan