Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

2 Major issues for Windows - Too many errors spent hours already to fix all - Pip freeze attached #18

Closed
FurkanGozukara opened this issue Sep 17, 2023 · 35 comments
Closed

2 Major issues for Windows - Too many errors spent hours already to fix all - Pip freeze attached #18

FurkanGozukara opened this issue Sep 17, 2023 · 35 comments

Comments

@FurkanGozukara
Copy link

Current gradio version is not working. So I had to update it to the latest now works

ebsynth compile not working. Please upload ebsynth compiled binary file directly into the repo or hugging face and make it auto download

I tried with cuda v11.4 and visual studio 2019 and all errors

And finally without ebsynth i did run an example video with default settings. I got keys frames but rest is all errors

Here below video process error

Global seed set to 2008357443
Data shape for DDIM sampling is (1, 4, 64, 72), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|██████████| 20/20 [00:05<00:00,  3.92it/s]
python video_blend.py result\brad --beg 1 --end 311 --itv 10 --key keys  --output result\brad\blend.mp4 --fps 23.976023976023978 --n_proc 4 -ps
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_81\0082.jpg'): can't open/read file: check file path/integrity
Process Process-2:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_241\0242.jpg'): can't open/read file: check file path/integrity
Process Process-4:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_161\0162.jpg'): can't open/read file: check file path/integrity
Process Process-3:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0002.jpg'): can't open/read file: check file path/integrity
Process Process-1:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
ebsynth: 6.116290330886841
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0010.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0011.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_11\0010.jpg'): can't open/read file: check file path/integrity
Traceback (most recent call last):
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 318, in <module>
    main(args)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 267, in main
    process_seq(video_sequence, i, blend_histogram, blend_gradient)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 198, in process_seq
    dist1s.append(load_error(bin_a, img_shape))
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 159, in load_error
    with open(bin_path, 'rb') as fp:
FileNotFoundError: [Errno 2] No such file or directory: 'result\\brad\\out_1\\0002.bin'
Traceback (most recent call last):
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\queueing.py", line 388, in call_prediction
    output = await route_utils.call_process_api(
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\route_utils.py", line 219, in call_process_api
    output = await app.get_blocks().process_api(
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\blocks.py", line 1440, in process_api
    data = self.postprocess_data(fn_index, result["prediction"], state)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\blocks.py", line 1341, in postprocess_data
    prediction_value = block.postprocess(prediction_value)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\video.py", line 281, in postprocess
    processed_files = (self._format_video(y), None)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\video.py", line 355, in _format_video
    video = self.make_temp_copy_if_needed(video)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\base.py", line 226, in make_temp_copy_if_needed
    temp_dir = self.hash_file(file_path)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\base.py", line 190, in hash_file
    with open(file_path, "rb") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'result\\brad\\blend.mp4'
python video_blend.py result\brad --beg 1 --end 311 --itv 10 --key keys  --output result\brad\blend.mp4 --fps 23.976023976023978 --n_proc 4 -ps
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
C:\Python3108\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_81\0082.jpg'): can't open/read file: check file path/integrity
Process Process-2:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_241\0242.jpg'): can't open/read file: check file path/integrity
Process Process-4:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_161\0162.jpg'): can't open/read file: check file path/integrity
Process Process-3:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\0002.jpg'): can't open/read file: check file path/integrity
Process Process-1:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
ebsynth: 4.1365814208984375
[ WARN:[email protected]] global loadsave.cpp:244 cv::findDecoder imread_('result\brad\out_1\

here below ebsynth build error

(venv) G:\Rerender_A_Video auto install\Rerender_A_Video>python install2.py
Build Ebsynth Windows 64 bit. If you want to build for 32 bit, please modify install.py.
.\build-win64-cpu+cuda.bat
"C:\Program Files\Microsoft Visual Studio\2022\Community\VC\Auxiliary\Build\vcvarsall.bat"
nvcc warning : The 'compute_35', 'compute_37', 'compute_50', 'sm_35', 'sm_37' and 'sm_50' architectures are deprecated, and may be removed in a future release (Use -Wno-deprecated-gpu-targets to suppress warning).
ebsynth.cpp
The contents of <filesystem> are available only with C++17 or later.
ebsynth_cpu.cpp
ebsynth_cuda.cu
C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime.h(197): error: invalid redeclaration of type name "size_t"

C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new.h(48): error: first parameter of allocation function must be of type "size_t"

C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new.h(53): error: first parameter of allocation function must be of type "size_t"

C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new.h(59): error: first parameter of allocation function must be of type "size_t"

C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new.h(64): error: first parameter of allocation function must be of type "size_t"

C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\VC\Tools\MSVC\14.29.30133\include\vcruntime_new.h(166): error: first parameter of allocation function must be of type "size_t"
@FurkanGozukara
Copy link
Author

here my venv pip freeze

Microsoft Windows [Version 10.0.19045.3324]
(c) Microsoft Corporation. All rights reserved.

G:\Rerender_A_Video auto install\Rerender_A_Video\venv\Scripts>activate

(venv) G:\Rerender_A_Video auto install\Rerender_A_Video\venv\Scripts>pip freeze
absl-py==1.4.0
addict==2.4.0
aenum==3.1.15
aiofiles==23.2.1
aiohttp==3.8.5
aiosignal==1.3.1
albumentations==1.3.0
altair==5.1.1
annotated-types==0.5.0
antlr4-python3-runtime==4.8
anyio==3.7.1
async-timeout==4.0.3
attrs==23.1.0
basicsr==1.4.2
blendmodes==2023
blinker==1.6.2
braceexpand==0.1.7
cachetools==5.3.1
certifi==2023.7.22
charset-normalizer==3.2.0
click==8.1.7
colorama==0.4.6
coloredlogs==15.0.1
contourpy==1.1.1
cycler==0.11.0
deprecation==2.1.0
einops==0.3.0
exceptiongroup==1.1.3
fastapi==0.103.1
ffmpy==0.3.1
filelock==3.12.4
flatbuffers==23.5.26
fonttools==4.42.1
frozenlist==1.4.0
fsspec==2023.9.1
ftfy==6.1.1
future==0.18.3
gitdb==4.0.10
GitPython==3.1.36
google-auth==2.23.0
google-auth-oauthlib==1.0.0
gradio==3.44.3
gradio_client==0.5.0
grpcio==1.58.0
h11==0.14.0
httpcore==0.18.0
httpx==0.25.0
huggingface-hub==0.17.1
humanfriendly==10.0
idna==3.4
imageio==2.9.0
imageio-ffmpeg==0.4.2
importlib-metadata==6.8.0
importlib-resources==6.0.1
invisible-watermark==0.1.5
Jinja2==3.1.2
joblib==1.3.2
jsonschema==4.19.0
jsonschema-specifications==2023.7.1
kiwisolver==1.4.5
kornia==0.6.0
lazy_loader==0.3
linkify-it-py==2.0.2
llvmlite==0.40.1
lmdb==1.4.1
Markdown==3.4.4
markdown-it-py==2.2.0
MarkupSafe==2.1.3
matplotlib==3.8.0
mdit-py-plugins==0.3.3
mdurl==0.1.2
mpmath==1.3.0
multidict==6.0.4
networkx==3.1
numba==0.57.0
numpy==1.24.4
oauthlib==3.2.2
omegaconf==2.1.1
onnx==1.14.1
onnxruntime==1.15.1
open-clip-torch==2.0.2
opencv-python==4.8.0.76
opencv-python-headless==4.8.0.76
orjson==3.9.7
packaging==23.1
pandas==2.1.0
Pillow==10.0.1
prettytable==3.6.0
protobuf==3.20.3
pyarrow==13.0.0
pyasn1==0.5.0
pyasn1-modules==0.3.0
pydantic==2.3.0
pydantic_core==2.6.3
pydeck==0.8.1b0
pyDeprecate==0.3.1
pydub==0.25.1
Pygments==2.16.1
Pympler==1.0.1
pyparsing==3.1.1
pyreadline3==3.4.1
python-dateutil==2.8.2
python-multipart==0.0.6
pytorch-lightning==1.5.0
pytz==2023.3.post1
PyWavelets==1.4.1
PyYAML==6.0.1
qudida==0.0.4
referencing==0.30.2
regex==2023.8.8
requests==2.31.0
requests-oauthlib==1.3.1
rich==13.5.3
rpds-py==0.10.3
rsa==4.9
safetensors==0.2.7
scikit-image==0.20.0
scikit-learn==1.3.0
scipy==1.11.2
semantic-version==2.10.0
semver==3.0.1
six==1.16.0
smmap==5.0.1
sniffio==1.3.0
starlette==0.27.0
streamlit==1.12.1
streamlit-drawable-canvas==0.8.0
sympy==1.12
tb-nightly==2.15.0a20230915
tensorboard==2.14.0
tensorboard-data-server==0.7.1
test-tube==0.7.5
threadpoolctl==3.2.0
tifffile==2023.8.30
timm==0.6.12
tokenizers==0.12.1
toml==0.10.2
toolz==0.12.0
torch==2.0.1+cu118
torchaudio==2.0.2+cu118
torchmetrics==0.6.0
torchvision==0.15.2+cu118
tornado==6.3.3
tqdm==4.66.1
transformers==4.19.2
typing_extensions==4.7.1
tzdata==2023.3
tzlocal==5.0.1
uc-micro-py==1.0.2
urllib3==1.26.16
uvicorn==0.23.2
validators==0.22.0
watchdog==3.0.0
wcwidth==0.2.6
webdataset==0.2.5
websockets==11.0.3
Werkzeug==2.3.7
xformers==0.0.21
yapf==0.32.0
yarl==1.9.2
zipp==3.16.2

(venv) G:\Rerender_A_Video auto install\Rerender_A_Video\venv\Scripts>

@FurkanGozukara FurkanGozukara changed the title 2 Major issues for Windows 2 Major issues for Windows - Too many errors spent hours already to fix all - Pip freeze attached Sep 17, 2023
@FurkanGozukara
Copy link
Author

only keyframe extraction are working here proof

python 3.10.11 - windows 10

image

@FurkanGozukara
Copy link
Author

I managed to compile ebsynth

ebsynth.cpp
ebsynth_cpu.cpp
ebsynth_cuda.cu
Creating library dummy.lib and object dummy.exp
ebsynth.cpp
ebsynth_cpu.cpp
ebsynth_cuda.cu
Creating library lib\ebsynth.lib and object lib\ebsynth.exp
Ebsynth installed successfully.

Now the problem is like below

tested 2 second video

out folders also have 1 jpg image

image

image

Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:08<00:00,  2.39it/s]
python video_blend.py result\test1 --beg 1 --end 41 --itv 10 --key keys  --output result\test1\blend.mp4 --fps 25.0 --n_proc 4 -ps
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
[ [W AWARN:[email protected]:[email protected]]9 g18] gllobobal loal loadsavead.csave.cppp:p:248 cv::findDecoder imread_('result\test1\out_31\00248 cv::32.jpg'): can't open/read file: check file path/integrity
findDecoder imread_('result\test1\out_1\0002.jpg'): can't open/read file: check file path/integrity
Process Process-4:
Process Process-1:
Traceback (most recent call last):
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0012.jpg'): can't open/read file: check file path/integrity
Process Process-2:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_21\0022.jpg'): can't open/read file: check file path/integrity
Process Process-3:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
ebsynth: 7.543177843093872
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0010.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0010.jpg'): can't open/read file: check file path/integrity
Traceback (most recent call last):
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 318, in <module>
    main(args)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 267, in main
    process_seq(video_sequence, i, blend_histogram, blend_gradient)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 198, in process_seq
    dist1s.append(load_error(bin_a, img_shape))
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 159, in load_error
    with open(bin_path, 'rb') as fp:
FileNotFoundError: [Errno 2] No such file or directory: 'result\\test1\\out_1\\0002.bin'
Traceback (most recent call last):
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\queueing.py", line 388, in call_prediction
    output = await route_utils.call_process_api(
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\route_utils.py", line 219, in call_process_api
    output = await app.get_blocks().process_api(
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\blocks.py", line 1440, in process_api
    data = self.postprocess_data(fn_index, result["prediction"], state)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\blocks.py", line 1341, in postprocess_data
    prediction_value = block.postprocess(prediction_value)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\video.py", line 281, in postprocess
    processed_files = (self._format_video(y), None)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\video.py", line 355, in _format_video
    video = self.make_temp_copy_if_needed(video)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\base.py", line 226, in make_temp_copy_if_needed
    temp_dir = self.hash_file(file_path)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\gradio\components\base.py", line 190, in hash_file
    with open(file_path, "rb") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'result\\test1\\blend.mp4'

@williamyang1991
Copy link
Owner

Thank you for your detailed feedbacks!

Ebsynth is for full video translation. It is not used in key frame translation. So you got errors after getting key frames if Ebsynth is not correctly built.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works?
If it works, I will add downloading instructions in the README.md.

@FurkanGozukara
Copy link
Author

Thank you for your detailed feedbacks!

Ebsynth is for full video translation. It is not used in key frame translation. So you got errors after getting key frames if Ebsynth is not correctly built.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works? If it works, I will add downloading instructions in the README.md.

I complied it after that message with Cuda 10 and visual studio 2017

The errors above after that
I see ebsyth message printed during processing so it is working I guess

Example : ebsynth: 7.543177843093872

I asked gpt 4 code interpreter but not luck it can't solve it

@williamyang1991
Copy link
Owner

If ebsynth works correctly, it will produce the intermediate images like 'result\test1\out_1\0002.bin' and 'result\test1\out_1\0002.jpg'.
TI think that means it is not working correctly in your case.

Maybe you can use my complied file, and directly run the code to test it:

python video_blend.py result\test1 --beg 1 --end 41 --itv 10 --key keys  --output result\test1\blend.mp4 --fps 25.0 --n_proc 4 -ps

@FurkanGozukara
Copy link
Author

If ebsynth works correctly, it will produce the intermediate images like 'result\test1\out_1\0002.bin' and 'result\test1\out_1\0002.jpg'. TI think that means it is not working correctly in your case.

Maybe you can use my complied file, and directly run the code to test it:

python video_blend.py result\test1 --beg 1 --end 41 --itv 10 --key keys  --output result\test1\blend.mp4 --fps 25.0 --n_proc 4 -ps

Ok i will try

What visual studio and Cuda version did you use to compile?

@williamyang1991
Copy link
Owner

What visual studio and Cuda version did you use to compile?

I test our code on VS 2022 and CUDA 12.0

@FurkanGozukara
Copy link
Author

What visual studio and Cuda version did you use to compile?

I test our code on VS 2022 and CUDA 12.0

just tested with your uploaded ebsynth.exe and still errors same. i think it is about your pathing with windows . i also tested with my self compiled cuda 12 visual studio 2022 ebsynth.exe

all default settings, cuda and xformers installed

here below the entire CMD window, RTX 3090 TI

keys frames are made

logging improved.
Running on local URL:  http://0.0.0.0:7860

To create a public link, set `share=True` in `launch()`.
ControlLDM: Running in eps-prediction mode
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla-xformers' with 512 in_channels
building MemoryEfficientAttnBlock with 512 in_channels...
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla-xformers' with 512 in_channels
building MemoryEfficientAttnBlock with 512 in_channels...
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Loaded model config from [./deps/ControlNet/models/cldm_v15.yaml]
Loaded state_dict from [./models/control_sd15_hed.pth]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\safetensors\torch.py:98: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
  with safe_open(filename, framework="pt", device=device) as f:
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.66it/s]
1
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.69it/s]
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.69it/s]
11
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.70it/s]
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.68it/s]
21
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.67it/s]
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.67it/s]
31
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.64it/s]
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.64it/s]
41
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.66it/s]
Global seed set to 1398427114
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.67it/s]
python video_blend.py result\test1 --beg 1 --end 41 --itv 10 --key keys  --output result\test1\blend.mp4 --fps 25.0 --n_proc 4 -ps
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_31\0032.jpg'): can't open/read file: check file path/integrity
[Process Process-4:
 WARTraceback (most recent call last):
N:[email protected]] global load  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
save.cpp:248 cv::findDecoder imread_('result\  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
test1\out_1\0002.jpg'): can't open/rea  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
d file: check file path/i  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
ntegrity
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
Process Process-1:
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0012.jpg'): can't open/read file: check file path/integrity
Process Process-2:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_21\0022.jpg'): can't open/read file: check file path/integrity
Process Process-3:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
ebsynth: 4.434685230255127
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0010.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0010.jpg'): can't open/read file: check file path/integrity
Traceback (most recent call last):
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 318, in <module>
    main(args)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 267, in main
    process_seq(video_sequence, i, blend_histogram, blend_gradient)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 198, in process_seq
    dist1s.append(load_error(bin_a, img_shape))
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 159, in load_error
    with open(bin_path, 'rb') as fp:
FileNotFoundError: [Errno 2] No such file or directory: 'result\\test1\\out_1\\0002.bin'

@SoftologyPro
Copy link

SoftologyPro commented Sep 18, 2023 •
edited
Loading

I get this same error on Windows.
First frame image renders fine. Key frame key.mp4 finishes fine. When I click the propagate button, same error about missing file (which is a valid error as the file it is looking for does not exist on the drive).
Ebsynth compiled fine. I even tried copying ebsynth.exe and ebsynth.dll to the same directory as webui.py. No change.

Any ideas what else we can try here? I have been trying different Python package versions for hours now to try and fluke a working setup. For example the gradio you specify is too old and causes errors. invisible-watermark is not needed. Neither are the streamlit packages. Also test-tube and webdataset are not needed. An updated requirements.txt with the latest possible versions would really help too.

@FurkanGozukara
Copy link
Author

FurkanGozukara commented Sep 18, 2023 •
edited
Loading

I get this same error on Windows. First frame image renders fine. Key frame key.mp4 finishes fine. When I click the propagate button, same error about missing file (which does not exist on the drive). Ebsynth compiled fine. I even tried copying ebsynth.exe and ebsynth.dll to the same directory as webui.py. No change.

Any ideas what else we can try here? I have been trying different Python package versions for hours now to try and fluke a working setup.

i have been struggling since yesterday

definitely not an error of Ebsynth

because Ebsynth message is printed

moreover i tested with the developer uploaded Ebsynth as well

@williamyang1991
Copy link
Owner

I get this same error on Windows. First frame image renders fine. Key frame key.mp4 finishes fine. When I click the propagate button, same error about missing file (which does not exist on the drive). Ebsynth compiled fine. I even tried copying ebsynth.exe and ebsynth.dll to the same directory as webui.py. No change.

Any ideas what else we can try here? I have been trying different Python package versions for hours now to try and fluke a working setup.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works?

@FurkanGozukara
Copy link
Author

FurkanGozukara commented Sep 18, 2023 •
edited
Loading

I get this same error on Windows. First frame image renders fine. Key frame key.mp4 finishes fine. When I click the propagate button, same error about missing file (which does not exist on the drive). Ebsynth compiled fine. I even tried copying ebsynth.exe and ebsynth.dll to the same directory as webui.py. No change.
Any ideas what else we can try here? I have been trying different Python package versions for hours now to try and fluke a working setup.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works?

not related to it

i think related to your windows pathing

also if i turn every frame into key frames still there are some errors but you can get this output

https://twitter.com/GozukaraFurkan/status/1703554976969019457

are you reading CMD outputs? or my replies? i tested your uploaded ensynth too same error

@williamyang1991
Copy link
Owner

I get this same error on Windows. First frame image renders fine. Key frame key.mp4 finishes fine. When I click the propagate button, same error about missing file (which does not exist on the drive). Ebsynth compiled fine. I even tried copying ebsynth.exe and ebsynth.dll to the same directory as webui.py. No change.
Any ideas what else we can try here? I have been trying different Python package versions for hours now to try and fluke a working setup.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works?

not related to it

i think related to your windows pathing

also if i turn every frame into key frames still there are some errors but you can get this output

https://twitter.com/GozukaraFurkan/status/1703554976969019457

are you reading CMD outputs? or my replies? i tested your uploaded ensynth too same error

Ah. We will look into it. Maybe this is due to the path difference between windows and linux?
@SingleZombie Any ideas?

@FurkanGozukara FurkanGozukara mentioned this issue Sep 18, 2023
Closed
@SingleZombie
Copy link
Collaborator

Seems Ebsynth runs failed. Could you open Ebsynth log in the following line and show the logs again?

Rerender_A_Video/video_blend.py

Line 22 in 7f8072f

OPEN_EBSYNTH_LOG = False

@michaelgold michaelgold mentioned this issue Sep 18, 2023
Open
@SoftologyPro
Copy link

SoftologyPro commented Sep 18, 2023 •
edited
Loading

I get this same error on Windows. First frame image renders fine. Key frame key.mp4 finishes fine. When I click the propagate button, same error about missing file (which does not exist on the drive). Ebsynth compiled fine. I even tried copying ebsynth.exe and ebsynth.dll to the same directory as webui.py. No change.
Any ideas what else we can try here? I have been trying different Python package versions for hours now to try and fluke a working setup.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works?

Ebsynth compiled fine. It is either the path and/or versions of the Python packages. If we could get an updated and working requirements.txt that would also really help on Windows.

@FurkanGozukara
Copy link
Author

FurkanGozukara commented Sep 18, 2023 •
edited
Loading

OPEN_EBSYNTH_LOG

here logs open run

yep looks like path. testing with changing path of folder name

.\deps\ebsynth\bin\ebsynth.exe -style G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\keys\0001.png -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0001.png G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0002.png -weight 6 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\edge_0001.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\edge_0002.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\temporal_0001.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\temporal_0002.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\pos_0001.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\pos_0002.jpg -weight 2 -output G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\out_1\0002.jpg -searchvoteiters 12 -patchmatchiters 6

error: unrecognized option 'auto'

logging improved.
Running on local URL:  http://0.0.0.0:7860

To create a public link, set `share=True` in `launch()`.
ControlLDM: Running in eps-prediction mode
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla-xformers' with 512 in_channels
building MemoryEfficientAttnBlock with 512 in_channels...
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla-xformers' with 512 in_channels
building MemoryEfficientAttnBlock with 512 in_channels...
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 320, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 640, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is None and using 8 heads.
Setting up MemoryEfficientCrossAttention. Query dim is 1280, context_dim is 768 and using 8 heads.
Loaded model config from [./deps/ControlNet/models/cldm_v15.yaml]
Loaded state_dict from [./models/control_sd15_hed.pth]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\safetensors\torch.py:98: UserWarning: TypedStorage is deprecated. It will be removed in the future and UntypedStorage will be the only storage class. This should only matter to you if you are using storages directly.  To access UntypedStorage directly, use tensor.untyped_storage() instead of tensor.storage()
  with safe_open(filename, framework="pt", device=device) as f:
A matching Triton is not available, some optimizations will not be enabled.
Error caught was: No module named 'triton'
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.71it/s]
1
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.71it/s]
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.71it/s]
11
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.71it/s]
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.70it/s]
21
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.69it/s]
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.68it/s]
31
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.69it/s]
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.63it/s]
41
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.62it/s]
Global seed set to 608253894
Data shape for DDIM sampling is (1, 4, 112, 64), eta 0.0
Running DDIM Sampling with 20 timesteps
DDIM Sampler: 100%|████████████████████████████████████████████████████████████████████████████████████████████████| 20/20 [00:07<00:00,  2.62it/s]
python video_blend.py result\test1 --beg 1 --end 41 --itv 10 --key keys  --output result\test1\blend.mp4 --fps 25.0 --n_proc 4 -ps
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
G:\Rerender_A_Video auto install\Rerender_A_Video\venv\lib\site-packages\torch\functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ..\aten\src\ATen\native\TensorShape.cpp:3484.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
.\deps\ebsynth\bin\ebsynth.exe -style G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\keys\0001.png -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0001.png G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0002.png -weight 6 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\edge_0001.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\edge_0002.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\temporal_0001.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\temporal_0002.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\pos_0001.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_1\pos_0002.jpg -weight 2 -output G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\out_1\0002.jpg -searchvoteiters 12 -patchmatchiters 6
error: unrecognized option 'auto'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0002.jpg'): can't open/read file: check file path/integrity
Process Process-1:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
.\deps\ebsynth\bin\ebsynth.exe -style G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\keys\0031.png -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0031.png G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0032.png -weight 6 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_31\edge_0031.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_31\edge_0032.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_31\temporal_0031.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_31\temporal_0032.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_31\pos_0031.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_31\pos_0032.jpg -weight 2 -output G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\out_31\0032.jpg -searchvoteiters 12 -patchmatchiters 6
error: unrecognized option 'auto'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_31\0032.jpg'): can't open/read file: check file path/integrity
Process Process-4:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
.\deps\ebsynth\bin\ebsynth.exe -style G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\keys\0011.png -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0011.png G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0012.png -weight 6 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_11\edge_0011.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_11\edge_0012.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_11\temporal_0011.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_11\temporal_0012.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_11\pos_0011.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_11\pos_0012.jpg -weight 2 -output G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\out_11\0012.jpg -searchvoteiters 12 -patchmatchiters 6
error: unrecognized option 'auto'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0012.jpg'): can't open/read file: check file path/integrity
Process Process-2:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
.\deps\ebsynth\bin\ebsynth.exe -style G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\keys\0021.png -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0021.png G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\video\0022.png -weight 6 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_21\edge_0021.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_21\edge_0022.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_21\temporal_0021.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_21\temporal_0022.jpg -weight 0.5 -guide G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_21\pos_0021.jpg G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\tmp\out_21\pos_0022.jpg -weight 2 -output G:\Rerender_A_Video auto install\Rerender_A_Video\result\test1\out_21\0022.jpg -searchvoteiters 12 -patchmatchiters 6
error: unrecognized option 'auto'
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_21\0022.jpg'): can't open/read file: check file path/integrity
Process Process-3:
Traceback (most recent call last):
  File "C:\Python3108\lib\multiprocessing\process.py", line 314, in _bootstrap
    self.run()
  File "C:\Python3108\lib\multiprocessing\process.py", line 108, in run
    self._target(*self._args, **self._kwargs)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 109, in process_sequences
    process_one_sequence(i, video_sequence)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 96, in process_one_sequence
    cmd += ' ' + g.get_cmd(j, w)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\blender\guide.py", line 100, in get_cmd
    warped_img = flow_calc.warp(prev_img, self.flows[i - 1],
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\flow\flow_utils.py", line 188, in warp
    if len(img.shape) == 2:
AttributeError: 'NoneType' object has no attribute 'shape'
ebsynth: 4.452345848083496
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_1\0010.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0002.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0003.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0004.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0005.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0006.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0007.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0008.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0009.jpg'): can't open/read file: check file path/integrity
[ WARN:[email protected]] global loadsave.cpp:248 cv::findDecoder imread_('result\test1\out_11\0010.jpg'): can't open/read file: check file path/integrity
Traceback (most recent call last):
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 318, in <module>
    main(args)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 267, in main
    process_seq(video_sequence, i, blend_histogram, blend_gradient)
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 198, in process_seq
    dist1s.append(load_error(bin_a, img_shape))
  File "G:\Rerender_A_Video auto install\Rerender_A_Video\video_blend.py", line 159, in load_error
    with open(bin_path, 'rb') as fp:
FileNotFoundError: [Errno 2] No such file or directory: 'result\\test1\\out_1\\0002.bin'

@FurkanGozukara
Copy link
Author

FurkanGozukara commented Sep 18, 2023 •
edited
Loading

yep it was path error fixed it :)

i can't believe in 2023 folder paths are still an issue :)

blend.mp4

@williamyang1991
Copy link
Owner

Wow, how do you fix it? Could you share it with us?

@SoftologyPro
Copy link

yep it was path error fixed it :)

How did you fix it?

@FurkanGozukara
Copy link
Author

FurkanGozukara commented Sep 18, 2023 •
edited
Loading

Wow, how do you fix it? Could you share it with us?

i made the main folder name like this Rerender_A_Video_auto_install

no spaces - no non english characters

@SoftologyPro

that enable debug gave me the hint

@SoftologyPro
Copy link

SoftologyPro commented Sep 18, 2023 •
edited
Loading

Wow, how do you fix it? Could you share it with us?

i made the main folder name like this Rerender_A_Video_auto_install

no spaces - no non english characters

@SoftologyPro

No spaces would mean an unquoted path inside the code somewhere.

At least using paths without spaces will get it working in the meantime. Thank you for the fix.

@FurkanGozukara
Copy link
Author

Wow, how do you fix it? Could you share it with us?

i made the main folder name like this Rerender_A_Video_auto_install
no spaces - no non english characters
@SoftologyPro

No spaces would mean an unquoted path inside the code somewhere.

At least using paths without spaces may get it working in the meantime.

yep it means that

@SingleZombie
Copy link
Collaborator

Thanks for the feedback. The bug is caused by Python API subprocess. We will add notes to documents.

@SoftologyPro
Copy link

SoftologyPro commented Sep 18, 2023 •
edited
Loading

Thanks for the feedback. The bug is caused by Python API subprocess. We will add notes to documents.

So will the scripts be fixed to support spaces or will the fix be "make sure you do not have spaces in the path to webui.py"?

@JPW0080
Copy link

JPW0080 commented Sep 18, 2023 •
edited
Loading

Having - within folder/file name also does not work.

@williamyang1991 williamyang1991 mentioned this issue Sep 19, 2023
Closed
@lmpeng12
Copy link

Hello, I have encountered the same problem and cannot find the relevant bin file. My Ebsynth is running normally. I can find the output images in out_1 folder, and there are also npy files in tmp. How can I modify it??
python video_blend.py result/pexels-koolshooters-7322716 --beg 1 --end 101 --itv 10 --key keys --output result/pexels-koolshooters-7322716/blend.mp4 --fps 25.0 --n_proc 4 -ps
/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)
return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined]
ebsynth: 113.05732083320618
Traceback (most recent call last):
File "/home/ai-tets/wangzijian/image_generator/Rerender_A_Video-main/video_blend.py", line 330, in
main(args)
File "/home/ai-tets/wangzijian/image_generator/Rerender_A_Video-main/video_blend.py", line 268, in main
process_seq(video_sequence, i, blend_histogram, blend_gradient)
File "/home/ai-tets/wangzijian/image_generator/Rerender_A_Video-main/video_blend.py", line 199, in process_seq
dist1s.append(load_error(bin_a, img_shape))
File "/home/ai-tets/wangzijian/image_generator/Rerender_A_Video-main/video_blend.py", line 159, in load_error
with open(bin_path, 'rb') as fp:
FileNotFoundError: [Errno 2] No such file or directory: 'result/pexels-koolshooters-7322716/out_1/0002.bin'
Traceback (most recent call last):
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/routes.py", line 437, in run_predict
output = await app.get_blocks().process_api(
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/blocks.py", line 1355, in process_api
data = self.postprocess_data(fn_index, result["prediction"], state)
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/blocks.py", line 1289, in postprocess_data
prediction_value = block.postprocess(prediction_value)
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/components/video.py", line 249, in postprocess
processed_files = (self._format_video(y), None)
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/components/video.py", line 313, in _format_video
video = self.make_temp_copy_if_needed(video)
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/components/base.py", line 223, in make_temp_copy_if_needed
temp_dir = self.hash_file(file_path)
File "/home/ai-tets/miniconda3/envs/lmp_1/lib/python3.10/site-packages/gradio/components/base.py", line 187, in hash_file
with open(file_path, "rb") as f:
FileNotFoundError: [Errno 2] No such file or directory: 'result/pexels-koolshooters-7322716/blend.mp4'

@williamyang1991
Copy link
Owner

Having - within folder/file name also does not work.

@lmpeng12 Your path /home/ai-tets/ contains -

@williamyang1991 williamyang1991 mentioned this issue Sep 20, 2023
Open
@17freeman
Copy link

I used my own data for testing and then reported this error

(liddle) root@lnyang-0001:~/AIGC/Rerender_A_Video# python video_blend.py /root/AIGC/Rerender_A_Video/videos/try/first --beg 1 --end 659 --itv 4 --key keys --output /root/AIGC/Rerender_A_Video/videos/try/first/blend.mp4 --fps 30.0 --n_proc 1 -ps
Process Process-1:
Traceback (most recent call last):
File "/root/anaconda3/envs/liddle/lib/python3.8/multiprocessing/process.py", line 315, in _bootstrap
self.run()
File "/root/anaconda3/envs/liddle/lib/python3.8/multiprocessing/process.py", line 108, in run
self._target(*self._args, **self._kwargs)
File "/root/AIGC/Rerender_A_Video/video_blend.py", line 109, in process_sequences
process_one_sequence(i, video_sequence)
File "/root/AIGC/Rerender_A_Video/video_blend.py", line 76, in process_one_sequence
flow_calc.get_flow(i1, i2, flow_seq[j])
File "/root/anaconda3/envs/liddle/lib/python3.8/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/root/AIGC/Rerender_A_Video/flow/flow_utils.py", line 172, in get_flow
results_dict = self.model(image1,
File "/root/anaconda3/envs/liddle/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "/root/AIGC/Rerender_A_Video/deps/gmflow/gmflow/gmflow.py", line 133, in forward
feature0, feature1 = feature_add_position(feature0, feature1, attn_splits, self.feature_channels)
File "/root/AIGC/Rerender_A_Video/deps/gmflow/gmflow/utils.py", line 70, in feature_add_position
feature0_splits = split_feature(feature0, num_splits=attn_splits)
File "/root/AIGC/Rerender_A_Video/deps/gmflow/gmflow/utils.py", line 21, in split_feature
assert h % num_splits == 0 and w % num_splits == 0
AssertionError
ebsynth: 4.577818870544434
Traceback (most recent call last):
File "video_blend.py", line 318, in
main(args)
File "video_blend.py", line 267, in main
process_seq(video_sequence, i, blend_histogram, blend_gradient)
File "video_blend.py", line 198, in process_seq
dist1s.append(load_error(bin_a, img_shape))
File "video_blend.py", line 159, in load_error
with open(bin_path, 'rb') as fp:
FileNotFoundError: [Errno 2] No such file or directory: '/root/AIGC/Rerender_A_Video/videos/try/first/out_1/0002.bin'

@williamyang1991
Copy link
Owner 

assert h % num_splits == 0 and w % num_splits == 0
AssertionError

You can resize the video so that the length and width of the input video must be at least a multiple of 16.

#32 (comment)

@17freeman
Copy link

Thanks for your reply, I can indeed run it successfully after lowering the resolution of my own keyframe images. What I want to ask you is, can you run the video_blend program without reducing the resolution of the image?

@williamyang1991
Copy link
Owner

Yes, there is no resolution limitation except that the length and width of the input video must be at least a multiple of 16.
Instead of crop the video (lower the resolution), you can also pad the video to increase the resolution to meet the aforementioned requirement.

@17freeman
Copy link

Hello, thank you for your answer. I would like to ask you again about the problem of too slow generation speed. For the same picture, it took me about half an hour to use your program to generate the video, and it took about three minutes for me to use the ebsynth-beta software to generate the video from the ebs file. My program execution instructions are as follows: python video_blend.py videos/10_8 --beg 1 --end 449 --itv 10 --key img2img_key --output videos/10_8/blend.mp4 --fps 30.0 --n_proc 4 -ps . Is this normal? Is there any way to speed up the generation.

@williamyang1991
Copy link
Owner

We are not the soft engineering of the ebsynth-beta software. We just reimplement ebsynth based on the open source, which is definitely different from the code used in ebsynth-beta software.
There may be some optimization to speed up the process in the software that we don't know.

@8600862
Copy link

8600862 commented Oct 9, 2023

Thank you for your detailed feedbacks!

Ebsynth is for full video translation. It is not used in key frame translation. So you got errors after getting key frames if Ebsynth is not correctly built.

I uploaded my complied ensynth in windows and linux (https://drive.google.com/drive/folders/1oSB3imKwZGz69q2unBUfcgmQpzwccoyD?usp=sharing). Could you kindly try to see if it works? If it works, I will add downloading instructions in the README.md.

it not works for me
I try to build ensynth very hard. I use gcc 9.4 (7.4 will get filesystem: No such file or directory, >=8 maybe ok), export cuda bin& lib64 to PATH&LD_LIBRARY_PATH, fix compute_xx as my gpu in shell, then it works after a few minutes

@williamyang1991 williamyang1991 mentioned this issue Jun 30, 2024
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
8 participants
@williamyang1991 @FurkanGozukara @8600862 @lmpeng12 @17freeman @SingleZombie @SoftologyPro @JPW0080