ainseven/comfyui-fastblend

fastblend for comfyui, and other nodes that I write for generate video. rebatch image, my openpose

comfyui-fastblend's Issues

CuPy failed to load libnvrtc.so.12

Hello, I use the paperspace.com node Smooth Video and gives such an error:
There is no such error on the local computer, what could be the problem?

Error occurred when executing SmoothVideo:

CuPy failed to load libnvrtc.so.12: OSError: libnvrtc.so.12: cannot open shared object file: No such file or directory

File "/notebooks/ComfyUI/execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/notebooks/ComfyUI/execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/notebooks/ComfyUI/execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/notebooks/ComfyUI/custom_nodes/AInseven/smoothVideo.py", line 110, in execute
frames = smooth_video(
File "/notebooks/ComfyUI/custom_nodes/AInseven/FastBlend/api.py", line 75, in smooth_video
frames=FastModeRunner().run(frames_guide, frames_style, batch_size=batch_size, window_size=window_size,
File "/notebooks/ComfyUI/custom_nodes/AInseven/FastBlend/runners/fast.py", line 125, in run
table_l = table_manager.build_remapping_table(frames_guide, frames_style, patch_match_engine, batch_size, desc="Fast Mode Step 1/4")
File "/notebooks/ComfyUI/custom_nodes/AInseven/FastBlend/runners/fast.py", line 44, in build_remapping_table
_, target_style = patch_match_engine.estimate_nnf(source_guide, target_guide, source_style)
File "/notebooks/ComfyUI/custom_nodes/AInseven/FastBlend/patch_match.py", line 291, in estimate_nnf
nnf = self.initialize_nnf(source_guide.shape[0]) if level==0 else self.update_nnf(nnf, level)
File "/notebooks/ComfyUI/custom_nodes/AInseven/FastBlend/patch_match.py", line 254, in initialize_nnf
cp.repeat(cp.arange(height), width).reshape(height, width),
File "/usr/local/lib/python3.10/dist-packages/cupy/_creation/ranges.py", line 60, in arange
_arange_ufunc(typ(start), typ(step), ret, dtype=dtype)
File "cupy/_core/_kernel.pyx", line 1375, in cupy._core._kernel.ufunc.__call__
File "cupy/_core/_kernel.pyx", line 1402, in cupy._core._kernel.ufunc._get_ufunc_kernel
File "cupy/_core/_kernel.pyx", line 1082, in cupy._core._kernel._get_ufunc_kernel
File "cupy/_core/_kernel.pyx", line 94, in cupy._core._kernel._get_simple_elementwise_kernel
File "cupy/_core/_kernel.pyx", line 82, in cupy._core._kernel._get_simple_elementwise_kernel_from_code
File "cupy/_core/core.pyx", line 2254, in cupy._core.core.compile_with_cache
File "/usr/local/lib/python3.10/dist-packages/cupy/cuda/compiler.py", line 484, in _compile_module_with_cache
return _compile_with_cache_cuda(
File "/usr/local/lib/python3.10/dist-packages/cupy/cuda/compiler.py", line 499, in _compile_with_cache_cuda
arch = _get_arch()
File "cupy/_util.pyx", line 64, in cupy._util.memoize.decorator.ret
File "/usr/local/lib/python3.10/dist-packages/cupy/cuda/compiler.py", line 148, in _get_arch
nvrtc_max_compute_capability = _get_max_compute_capability()
File "cupy/_util.pyx", line 64, in cupy._util.memoize.decorator.ret
File "/usr/local/lib/python3.10/dist-packages/cupy/cuda/compiler.py", line 126, in _get_max_compute_capability
major, minor = _get_nvrtc_version()
File "/usr/local/lib/python3.10/dist-packages/cupy/cuda/compiler.py", line 115, in _get_nvrtc_version
_nvrtc_version = nvrtc.getVersion()
File "cupy_backends/cuda/libs/nvrtc.pyx", line 56, in cupy_backends.cuda.libs.nvrtc.getVersion
File "cupy_backends/cuda/libs/nvrtc.pyx", line 57, in cupy_backends.cuda.libs.nvrtc.getVersion
File "cupy_backends/cuda/libs/_cnvrtc.pxi", line 72, in cupy_backends.cuda.libs.nvrtc.initialize
File "cupy_backends/cuda/libs/_cnvrtc.pxi", line 76, in cupy_backends.cuda.libs.nvrtc._initialize
File "cupy_backends/cuda/libs/_cnvrtc.pxi", line 143, in cupy_backends.cuda.libs.nvrtc._get_softlink
File "cupy_backends/cuda/_softlink.pyx", line 32, in cupy_backends.cuda._softlink.SoftLink.__init__

Vram still full after using the node.

Hello, the data from the node stay in vram after usage which is an issue when using steps after the node.

KSampler will report an error when running smoothvideo.json workflow.

I really like your ComfyUI-fastblend. However, after upgrading the ComfyUI version, KSampler will report an error when running smoothvideo.json workflow.

IndexError: index 87 is out of bounds for axis 0 with size 86

间隔帧的工作流，两个加载视频的模选都一样，第一个视频没错，但是到第二个视频的时候就弹出这个错误。8秒多点的视频，帧读取上线都是0.第二个加载视频报错的时候我改成86也不行。不知道哪里错误了，大佬帮忙看看。

各种视频连线的方法都试了。。。

comfyui里没有必要装gradio,我看你的要求里多了这个

cupy-cuda12x
gradio

加载不到smoothvideo节点了？停止维护了？

Error occurred when executing SmoothVideo: 'list' object has no attribute 'shape

smoothvideo.json KSampler AttributeError: 'NoneType' object has no attribute 'shape'

The only thing I changed was the Empty Latent Image size to 512x512.
Any help would be appreciated. Thanks in advance.

CuPy Error

When running your example workflow I am having this problem.

Do you know what could be causing it?

Log:
Error occurred when executing SmoothVideo:

CuPy failed to load nvrtc64_120_0.dll: FileNotFoundError: Could not find module 'nvrtc64_120_0.dll' (or one of its dependencies). Try using the full path with constructor syntax.

File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\execution.py", line 82, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\custom_nodes\AInseven\smoothVideo.py", line 110, in execute
frames = smooth_video(
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\custom_nodes\AInseven\FastBlend\api.py", line 75, in smooth_video
frames=FastModeRunner().run(frames_guide, frames_style, batch_size=batch_size, window_size=window_size,
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\custom_nodes\AInseven\FastBlend\runners\fast.py", line 125, in run
table_l = table_manager.build_remapping_table(frames_guide, frames_style, patch_match_engine, batch_size, desc="Fast Mode Step 1/4")
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\custom_nodes\AInseven\FastBlend\runners\fast.py", line 44, in build_remapping_table
_, target_style = patch_match_engine.estimate_nnf(source_guide, target_guide, source_style)
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\custom_nodes\AInseven\FastBlend\patch_match.py", line 291, in estimate_nnf
nnf = self.initialize_nnf(source_guide.shape[0]) if level==0 else self.update_nnf(nnf, level)
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\ComfyUI\custom_nodes\AInseven\FastBlend\patch_match.py", line 254, in initialize_nnf
cp.repeat(cp.arange(height), width).reshape(height, width),
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy_creation\ranges.py", line 60, in arange
_arange_ufunc(typ(start), typ(step), ret, dtype=dtype)
File "cupy_core_kernel.pyx", line 1375, in cupy._core._kernel.ufunc.call
File "cupy_core_kernel.pyx", line 1402, in cupy._core._kernel.ufunc._get_ufunc_kernel
File "cupy_core_kernel.pyx", line 1082, in cupy._core._kernel._get_ufunc_kernel
File "cupy_core_kernel.pyx", line 94, in cupy._core._kernel._get_simple_elementwise_kernel
File "cupy_core_kernel.pyx", line 82, in cupy._core._kernel._get_simple_elementwise_kernel_from_code
File "cupy_core\core.pyx", line 2254, in cupy._core.core.compile_with_cache
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy\cuda\compiler.py", line 484, in _compile_module_with_cache
return _compile_with_cache_cuda(
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy\cuda\compiler.py", line 499, in _compile_with_cache_cuda
arch = _get_arch()
File "cupy_util.pyx", line 64, in cupy._util.memoize.decorator.ret
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy\cuda\compiler.py", line 148, in _get_arch
nvrtc_max_compute_capability = _get_max_compute_capability()
File "cupy_util.pyx", line 64, in cupy._util.memoize.decorator.ret
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy\cuda\compiler.py", line 126, in _get_max_compute_capability
major, minor = _get_nvrtc_version()
File "P:\STABLEDIFFUSION\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy\cuda\compiler.py", line 115, in _get_nvrtc_version
_nvrtc_version = nvrtc.getVersion()
File "cupy_backends\cuda\libs\nvrtc.pyx", line 56, in cupy_backends.cuda.libs.nvrtc.getVersion
File "cupy_backends\cuda\libs\nvrtc.pyx", line 57, in cupy_backends.cuda.libs.nvrtc.getVersion
File "cupy_backends\cuda\libs_cnvrtc.pxi", line 72, in cupy_backends.cuda.libs.nvrtc.initialize
File "cupy_backends\cuda\libs_cnvrtc.pxi", line 76, in cupy_backends.cuda.libs.nvrtc._initialize
File "cupy_backends\cuda\libs_cnvrtc.pxi", line 143, in cupy_backends.cuda.libs.nvrtc._get_softlink
File "cupy_backends\cuda_softlink.pyx", line 32, in cupy_backends.cuda._softlink.SoftLink.__ini

No module named 'custom_nodes.AInseven'

How it's works ?

Hi! I really love it; Ainseven did awesome work. I have a question: Can someone explain how exactly it works? Could it be something that can be done with a real-time post-processing shader? Thanks!

TypeError: Cannot handle this data type: (1, 1, 576, 3), |u1

I got this error at the video-combine item

好像通过 smooth viedo 处理后，图像会变得模糊？

有办法解决模糊的问题么？或者调整什么参数可以减弱模糊的情况
感谢关注此问题