I released this version because using the new model DeepRemaster I experienced the following problems:
Flickering
Inability to apply colors correctly in dark scenes
Inability to apply colors correctly both in bright and dark scenes
I was really surprised by problem #1, because was unexpected, I attached a sample to show it, fortunately are available filters to fix it, while the problems #2 and #3 were expected.
To fix the problem #2 I used the API function: HAVC_merge, while to fix the problem #3 I had to write a new API function called: HAVC_recover_clip_color.
I updated the user guide, with the following chapters:
3.5.2 Using Deep-Exemplar to speed-up the encoding (interesting, worth reading)
4.3.1 Fixing DeepRemaster problems (where are described in more details the solutions on the DeepRemaster problems)
P.S.
An example of movie colored using the fix described is the following: Fort Apache (1948)
22.02.2025, 12:45 (This post was last modified: 22.02.2025, 13:04 by Selur.)
thx for the info
Will update the torch add-on tomorrow, mostly afk. today.
Just realized, I got a bit of time => will update torch add-on (should be up in ~1hr)
----
Dev versions are in the 'experimental'-folder of my GoogleDrive, which is linked on the download page.
I was able to get vs-deoldify working with CUDA 12.8 as explained in post: #11
To get "colormnet" working is necessary to recompile "Pytorch-Correlation-extension".
To get "Pytorch-Correlation-extension" working is necessary to set the following environment variable (where has been added the compute capability of RTX 50 series: 12.0)
TORCH_CUDA_ARCH_LIST=8.0 8.6 9.0 12.0
I attached the updated instruction for compiling Pytorch-Correlation-extension with CUDA 12.8 and the working wheel build.
26.03.2025, 10:55 (This post was last modified: 26.03.2025, 11:43 by Selur.)
Sadly none of those, works.
=> so 5000x users will have to figure this out on their own.
maybe modifying the existing setup and not creating a new one works
no,
python -m pip install --upgrade torch-tensorrt
Requirement already satisfied: torch-tensorrt in f:\hybrid\64bit\vapoursynth\lib\site-packages (2.7.0.dev20250325+cu128)
Requirement already satisfied: torch<2.9.0,>=2.8.0.dev in f:\hybrid\64bit\vapoursynth\lib\site-packages (from torch-tensorrt) (2.8.0.dev20250323+cu128)
Requirement already satisfied: tensorrt<10.10.0,>=10.9.0 in f:\hybrid\64bit\vapoursynth\lib\site-packages (from torch-tensorrt) (10.9.0.34)
Collecting tensorrt-cu12<10.10.0,>=10.9.0 (from torch-tensorrt)
Using cached tensorrt_cu12-10.9.0.34.tar.gz (18 kB)
Preparing metadata (setup.py) ... done
Collecting tensorrt-cu12-bindings<10.10.0,>=10.9.0 (from torch-tensorrt)
Downloading tensorrt_cu12_bindings-10.9.0.34-cp312-none-win_amd64.whl.metadata (606 bytes)
Collecting tensorrt-cu12-libs<10.10.0,>=10.9.0 (from torch-tensorrt)
Using cached tensorrt_cu12_libs-10.9.0.34.tar.gz (704 bytes)
Installing build dependencies ... done
Getting requirements to build wheel ... done
Collecting tensorrt-cu12-libs<10.10.0,>=10.9.0 (from torch-tensorrt)
Using cached tensorrt_cu12_libs-10.9.0.34.tar.gz (704 bytes)
Installing build dependencies ... done
Getting requirements to build wheel ... done
ERROR: Exception:
Traceback (most recent call last):
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\cli\base_command.py", line 106, in _run_wrapper
status = _inner_run()
^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\cli\base_command.py", line 97, in _inner_run
return self.run(options, args)
^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\cli\req_command.py", line 67, in wrapper
return func(self, options, args)
^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\commands\install.py", line 386, in run
requirement_set = resolver.resolve(
^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\resolver.py", line 95, in resolve
result = self._result = resolver.resolve(
^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 546, in resolve
state = resolution.resolve(requirements, max_rounds=max_rounds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 427, in resolve
failure_causes = self._attempt_to_pin_criterion(name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 239, in _attempt_to_pin_criterion
criteria = self._get_updated_criteria(candidate)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 230, in _get_updated_criteria
self._add_to_criteria(criteria, requirement, parent=candidate)
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\resolvelib\resolvers.py", line 173, in _add_to_criteria
if not criterion.candidates:
^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\resolvelib\structs.py", line 156, in __bool__
return bool(self._sequence)
^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\found_candidates.py", line 174, in __bool__
return any(self)
^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\found_candidates.py", line 162, in <genexpr>
return (c for c in iterator if id(c) not in self._incompatible_ids)
^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\found_candidates.py", line 53, in _iter_built
candidate = func()
^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\factory.py", line 187, in _make_candidate_from_link
base: Optional[BaseCandidate] = self._make_base_candidate_from_link(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\factory.py", line 233, in _make_base_candidate_from_link
self._link_candidate_cache[link] = LinkCandidate(
^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 304, in __init__
super().__init__(
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 159, in __init__
self.dist = self._prepare()
^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 236, in _prepare
dist = self._prepare_distribution()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\resolution\resolvelib\candidates.py", line 315, in _prepare_distribution
return preparer.prepare_linked_requirement(self._ireq, parallel_builds=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\operations\prepare.py", line 527, in prepare_linked_requirement
return self._prepare_linked_requirement(req, parallel_builds)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\operations\prepare.py", line 642, in _prepare_linked_requirement
dist = _get_prepared_distribution(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\operations\prepare.py", line 72, in _get_prepared_distribution
abstract_dist.prepare_distribution_metadata(
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\distributions\sdist.py", line 56, in prepare_distribution_metadata
self._install_build_reqs(finder)
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\distributions\sdist.py", line 126, in _install_build_reqs
build_reqs = self._get_build_requires_wheel()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\distributions\sdist.py", line 103, in _get_build_requires_wheel
return backend.get_requires_for_build_wheel()
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_internal\utils\misc.py", line 702, in get_requires_for_build_wheel
return super().get_requires_for_build_wheel(config_settings=cs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\pyproject_hooks\_impl.py", line 196, in get_requires_for_build_wheel
return self._call_hook(
^^^^^^^^^^^^^^^^
File "F:\Hybrid\64bit\Vapoursynth\Lib\site-packages\pip\_vendor\pyproject_hooks\_impl.py", line 402, in _call_hook
raise BackendUnavailable(
pip._vendor.pyproject_hooks._impl.BackendUnavailable: Cannot import 'wheel_stub.buildapi'
In my case the build was successful.
But I think that is necessary to have a proper development environment, like the one necessary to build "Pytorch-Correlation-extension".
