fannovel16 / comfyui-frame-interpolation Goto Github PK
View Code? Open in Web Editor NEWA custom node set for Video Frame Interpolation in ComfyUI.
License: MIT License
A custom node set for Video Frame Interpolation in ComfyUI.
License: MIT License
i put this in node but it didn‘t work
The image output from the interpolation nodes (FILM, Fortuna, etc) seem to be in half format, when they should be full float? If I don't use the interpolation nodes, the images can be saved with combo node, or viewed in preview image. I'm not sure what's going on.
ComfyUI commit: 74b7233f57301bb08c2b29fb420eeacf8757d41c
I installed ComfyUI from the repo on a venv, I didn't use the portable.
Upscaling with Image Upscale (with model) node:
ERROR:root:Traceback (most recent call last):
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "K:\ComfyUI_Main\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 "K:\ComfyUI_Main\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in upscale
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy\utils.py", line 418, in tiled_scale
ps = function(s_in).to(output_device)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in <lambda>
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\chainner_models\architecture\RRDB.py", line 296, in forward
return self.model(x)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
input = module(input)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (struct c10::Half) and bias type (float) should be the same
Preview/Save Image
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "K:\ComfyUI_Main\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "K:\ComfyUI_Main\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 "K:\ComfyUI_Main\ComfyUI\execution.py", line 75, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in upscale
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy\utils.py", line 418, in tiled_scale
ps = function(s_in).to(output_device)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\nodes_upscale_model.py", line 52, in <lambda>
s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\comfy_extras\chainner_models\architecture\RRDB.py", line 296, in forward
return self.model(x)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\container.py", line 217, in forward
input = module(input)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 460, in forward
return self._conv_forward(input, self.weight, self.bias)
File "K:\ComfyUI_Main\ComfyUI\lib\site-packages\torch\nn\modules\conv.py", line 456, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Input type (struct c10::Half) and bias type (float) should be the same
The M2M_arch.py
file attempts to import softsplat_func
with the following line:
from ..ops.softsplat import softsplat_func'
However, the function is actually defined as softsplat
in taichi_wrapper.py
:
def softsplat(
tenIn: torch.Tensor, tenFlow: torch.Tensor, tenMetric: torch.Tensor, strMode: str
):
This discrepancy leads to the following error:
ImportError: cannot import name 'softsplat_func' from 'models.ops.softsplat'
Hi guys,
when i tried to run the RIFE VFI nodes, some error occrured:
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\rife_init_.py", line 105, in vfi
generic_frame_loop(frames, clear_cache_after_n_frames, multiplier, return_middle_frame, *args,
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_utils.py", line 188, in generic_frame_loop
out = torch.cat(output_frames, dim=0)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:0 and cpu! (when checking argument for argument tensors in method wrapper_CUDA_cat)
I've read some articles and still couldn't fix by myself :(
Getting some cupy wheel build errors
Using pytorch cross attention
Traceback (most recent call last):
File "C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\__init__.py", line 17, in <module>
from cupy import _core # NOQA
^^^^^^^^^^^^^^^^^^^^^^
File "C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\_core\__init__.py", line 3, in <module>
from cupy._core import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "cupy\_core\core.pyx", line 1, in init cupy._core.core
File "C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda\__init__.py", line 8, in <module>
from cupy.cuda import compiler # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda\compiler.py", line 13, in <module>
from cupy.cuda import device
File "cupy\cuda\device.pyx", line 1, in init cupy.cuda.device
ImportError: DLL load failed while importing runtime: The specified module could not be found.
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\nodes.py", line 1734, in load_custom_node
module_spec.loader.exec_module(module)
File "<frozen importlib._bootstrap_external>", line 940, in exec_module
File "<frozen importlib._bootstrap>", line 241, in _call_with_frames_removed
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\__init__.py", line 9, in <module>
from models.gmfss_fortuna import GMFSS_Fortuna_VFI
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\gmfss_fortuna\__init__.py", line 7, in <module>
from .GMFSS_Fortuna_arch import Model as GMFSS
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\gmfss_fortuna\GMFSS_Fortuna_arch.py", line 29, in <module>
from models.ops import softsplat
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\ops\__init__.py", line 21, in <module>
from .cupy_ops import softsplat, ModuleSoftsplat, FunctionSoftsplat, softsplat_func, costvol_func, sepconv_func, init, batch_edt, FunctionAdaCoF, ModuleCorrelation, FunctionCorrelation, _FunctionCorrelation
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\ops\cupy_ops\__init__.py", line 1, in <module>
from .costvol import *
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\ops\cupy_ops\costvol.py", line 1, in <module>
from .utils import cuda_kernel, cuda_launch, cuda_int32
File "C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\ops\cupy_ops\utils.py", line 1, in <module>
import cupy
File "C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\__init__.py", line 19, in <module>
raise ImportError(f'''
ImportError:
================================================================
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1
DLL dependencies:
KERNEL32.dll -> C:\WINDOWS\System32\KERNEL32.DLL
MSVCP140.dll -> C:\WINDOWS\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\WINDOWS\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\python311.dll
Original error:
ImportError: DLL load failed while importing runtime: The specified module could not be found.
================================================================
Cannot import C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation module for custom nodes:
================================================================
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1
DLL dependencies:
KERNEL32.dll -> C:\WINDOWS\System32\KERNEL32.DLL
MSVCP140.dll -> C:\WINDOWS\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\WINDOWS\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> C:\sdComfyUI\ComfyUI_windows_portable\python_embeded\python311.dll
Original error:
ImportError: DLL load failed while importing runtime: The specified module could not be found.
================================================================
### Loading: ComfyUI-Impact-Pack (V4.20.3)
### Loading: ComfyUI-Impact-Pack (Subpack: V0.2.4)
### Loading: ComfyUI-Inspire-Pack (V0.28.3)
### Loading: ComfyUI-Manager (V0.34)
### ComfyUI Revision: 1575 [2231edec] | Released on '2023-10-14'
0.1 seconds (IMPORT FAILED): C:\sdComfyUI\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
Installed via comfy manager
tried to install.bat, get this error below have nodes red in the workflow tried install missing nodes all points to custom node pack.
Installing ComfyUI Frame Interpolation..
Installing with ComfyUI Portable
Installing torch...
Requirement already satisfied: torch in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (2.0.1+cu118)
Requirement already satisfied: filelock in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (3.10.0)
Requirement already satisfied: typing-extensions in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (4.5.0)
Requirement already satisfied: sympy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (1.11.1)
Requirement already satisfied: networkx in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (3.0)
Requirement already satisfied: jinja2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (3.1.2)
Requirement already satisfied: MarkupSafe>=2.0 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch) (2.1.2)
Requirement already satisfied: mpmath>=0.19 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch) (1.3.0)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing numpy...
Requirement already satisfied: numpy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (1.23.5)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing einops...
Requirement already satisfied: einops in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (0.6.1)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing opencv-contrib-python...
Requirement already satisfied: opencv-contrib-python in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (4.7.0.72)
Requirement already satisfied: numpy>=1.21.2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from opencv-contrib-python) (1.23.5)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing kornia...
Requirement already satisfied: kornia in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (0.7.0)
Requirement already satisfied: packaging in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from kornia) (23.0)
Requirement already satisfied: torch>=1.9.1 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from kornia) (2.0.1+cu118)
Requirement already satisfied: filelock in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (3.10.0)
Requirement already satisfied: typing-extensions in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (4.5.0)
Requirement already satisfied: sympy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (1.11.1)
Requirement already satisfied: networkx in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (3.0)
Requirement already satisfied: jinja2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (3.1.2)
Requirement already satisfied: MarkupSafe>=2.0 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch>=1.9.1->kornia) (2.1.2)
Requirement already satisfied: mpmath>=0.19 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch>=1.9.1->kornia) (1.3.0)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing scipy...
Requirement already satisfied: scipy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (1.10.1)
Requirement already satisfied: numpy<1.27.0,>=1.19.5 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from scipy) (1.23.5)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing Pillow...
Requirement already satisfied: Pillow in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (9.4.0)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing torchvision...
Requirement already satisfied: torchvision in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (0.15.2+cu118)
Requirement already satisfied: numpy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (1.23.5)
Requirement already satisfied: requests in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (2.31.0)
Requirement already satisfied: torch==2.0.1 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (2.0.1+cu118)
Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (9.4.0)
Requirement already satisfied: filelock in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.0.1->torchvision) (3.10.0)
Requirement already satisfied: typing-extensions in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.0.1->torchvision) (4.5.0)
Requirement already satisfied: sympy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.0.1->torchvision) (1.11.1)
Requirement already satisfied: networkx in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.0.1->torchvision) (3.0)
Requirement already satisfied: jinja2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.0.1->torchvision) (3.1.2)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (2.0.5)
Requirement already satisfied: certifi>=2017.4.17 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (2022.12.7)
Requirement already satisfied: MarkupSafe>=2.0 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch==2.0.1->torchvision) (2.1.2)
Requirement already satisfied: mpmath>=0.19 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch==2.0.1->torchvision) (1.3.0)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing tqdm...
Requirement already satisfied: tqdm in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (4.65.0)
Requirement already satisfied: colorama in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from tqdm) (0.4.6)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Installing timm==0.6.13...
Requirement already satisfied: timm==0.6.13 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (0.6.13)
Requirement already satisfied: torch>=1.7 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (2.0.1+cu118)
Requirement already satisfied: torchvision in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (0.15.2+cu118)
Requirement already satisfied: pyyaml in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (6.0)
Requirement already satisfied: huggingface-hub in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (0.17.3)
Requirement already satisfied: filelock in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (3.10.0)
Requirement already satisfied: typing-extensions in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (4.5.0)
Requirement already satisfied: sympy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (1.11.1)
Requirement already satisfied: networkx in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (3.0)
Requirement already satisfied: jinja2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (3.1.2)
Requirement already satisfied: fsspec in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (2023.3.0)
Requirement already satisfied: requests in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (2.31.0)
Requirement already satisfied: tqdm>=4.42.1 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (4.65.0)
Requirement already satisfied: packaging>=20.9 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (23.0)
Requirement already satisfied: numpy in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision->timm==0.6.13) (1.23.5)
Requirement already satisfied: pillow!=8.3.*,>=5.3.0 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision->timm==0.6.13) (9.4.0)
Requirement already satisfied: colorama in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from tqdm>=4.42.1->huggingface-hub->timm==0.6.13) (0.4.6)
Requirement already satisfied: MarkupSafe>=2.0 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch>=1.7->timm==0.6.13) (2.1.2)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (3.1.0)
Requirement already satisfied: idna<4,>=2.5 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (2.0.5)
Requirement already satisfied: certifi>=2017.4.17 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (2022.12.7)
Requirement already satisfied: mpmath>=0.19 in d:\comfyui_windows_portable_nvidia_cu118_or_cpu\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch>=1.7->timm==0.6.13) (1.3.0)
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Checking cupy...
Uninstall cupy if existed...
WARNING: Skipping cupy-wheel as it is not installed.
WARNING: Skipping cupy-cuda102 as it is not installed.
WARNING: Skipping cupy-cuda110 as it is not installed.
WARNING: Skipping cupy-cuda111 as it is not installed.
WARNING: Skipping cupy-cuda11x as it is not installed.
WARNING: Skipping cupy-cuda12x as it is not installed.
Installing cupy...
Collecting cupy-wheel
Using cached cupy-wheel-12.2.0.tar.gz (2.9 kB)
Preparing metadata (setup.py) ... error
error: subprocess-exited-with-error
× python setup.py egg_info did not run successfully.
│ exit code: 1
╰─> [28 lines of output]
[cupy-wheel] CUDA_PATH is not set.cupy-wheel may not be able to discover NVRTC to probe version
[cupy-wheel] Trying to detect CUDA version from libraries: ['nvrtc64_120_0.dll', 'nvrtc64_112_0.dll', 'nvrtc64_111_0.dll', 'nvrtc64_110_0.dll', 'nvrtc64_102_0.dll']
[cupy-wheel] Looking for library: nvrtc64_120_0.dll
[cupy-wheel] Failed to open nvrtc64_120_0.dll: Could not find module 'nvrtc64_120_0.dll' (or one of its dependencies). Try using the full path with constructor syntax.
[cupy-wheel] Looking for library: nvrtc64_112_0.dll
[cupy-wheel] Failed to open nvrtc64_112_0.dll: Could not find module 'nvrtc64_112_0.dll' (or one of its dependencies). Try using the full path with constructor syntax.
[cupy-wheel] Looking for library: nvrtc64_111_0.dll
[cupy-wheel] Failed to open nvrtc64_111_0.dll: Could not find module 'nvrtc64_111_0.dll' (or one of its dependencies). Try using the full path with constructor syntax.
[cupy-wheel] Looking for library: nvrtc64_110_0.dll
[cupy-wheel] Failed to open nvrtc64_110_0.dll: Could not find module 'nvrtc64_110_0.dll' (or one of its dependencies). Try using the full path with constructor syntax.
[cupy-wheel] Looking for library: nvrtc64_102_0.dll
[cupy-wheel] Failed to open nvrtc64_102_0.dll: Could not find module 'nvrtc64_102_0.dll' (or one of its dependencies). Try using the full path with constructor syntax.
[cupy-wheel] No more candidate library to find
[cupy-wheel] ROCm detection unsupported on platform: win32
Traceback (most recent call last):
File "", line 2, in
File "", line 34, in
File "C:\Users\USER\AppData\Local\Temp\pip-install-_x17ekon\cupy-wheel_59c969eaba2840e7a3f1283ab365374e\setup.py", line 285, in
main()
File "C:\Users\USER\AppData\Local\Temp\pip-install-_x17ekon\cupy-wheel_59c969eaba2840e7a3f1283ab365374e\setup.py", line 269, in main
package = infer_best_package()
File "C:\Users\USER\AppData\Local\Temp\pip-install-_x17ekon\cupy-wheel_59c969eaba2840e7a3f1283ab365374e\setup.py", line 259, in infer_best_package
raise AutoDetectionFailed(
main.AutoDetectionFailed:
============================================================
Unable to detect NVIDIA CUDA or AMD ROCm installation.
============================================================
[end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
error: metadata-generation-failed
× Encountered error while generating package metadata.
╰─> See above for output.
note: This is an issue with the package mentioned above, not pip.
hint: See above for details.
[notice] A new release of pip is available: 23.1.2 -> 23.2.1
[notice] To update, run: D:\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python.exe -m pip install --upgrade pip
Press any key to continue . . .
I am having trouble with Cupy.
Installed ComfyUI-Frame-Interpolation through ComfyUI's manager
Hit update all to make sure everything is the latest version
Tried the example below
https://github.com/Fannovel16/ComfyUI-Frame-Interpolation/raw/main/example.png
Got an error
Terminal says
got prompt
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_init_.py", line 17, in
from cupy import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^
File "D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_core_init.py", line 3, in
from cupy._core import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "cupy_core\core.pyx", line 1, in init cupy.core.core
File "D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda_init.py", line 8, in
from cupy.cuda import compiler # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda\compiler.py", line 13, in
from cupy.cuda import device
File "cupy\cuda\device.pyx", line 1, in init cupy.cuda.device
ImportError: DLL load failed while importing runtime: The specified module could not be found.
The above exception was the direct cause of the following exception:
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: None
DLL dependencies:
KERNEL32.dll -> C:\Windows\System32\KERNEL32.DLL
MSVCP140.dll -> C:\Windows\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> D:\SD\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> D:\SD\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\Windows\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> D:\SD\ComfyUI_windows_portable\python_embeded\python311.dll
Prompt executed in 0.04 seconds`
I then ran install.bat in the ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation directory
Here is the result in the terminal:
Installing ComfyUI Frame Interpolation..
Installing with ComfyUI Portable
Installing torch...
Requirement already satisfied: torch in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (2.1.1+cu121)
Requirement already satisfied: filelock in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (3.13.1)
Requirement already satisfied: typing-extensions in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (4.8.0)
Requirement already satisfied: sympy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (1.12)
Requirement already satisfied: networkx in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (3.2.1)
Requirement already satisfied: jinja2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (3.1.2)
Requirement already satisfied: fsspec in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch) (2023.10.0)
Requirement already satisfied: MarkupSafe>=2.0 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch) (2.1.3)
Requirement already satisfied: mpmath>=0.19 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch) (1.3.0)
Installing numpy...
Requirement already satisfied: numpy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (1.26.2)
Installing einops...
Requirement already satisfied: einops in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (0.7.0)
Installing opencv-contrib-python...
Requirement already satisfied: opencv-contrib-python in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (4.8.1.78)
Requirement already satisfied: numpy>=1.21.2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from opencv-contrib-python) (1.26.2)
Installing kornia...
Requirement already satisfied: kornia in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (0.7.0)
Requirement already satisfied: packaging in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from kornia) (23.2)
Requirement already satisfied: torch>=1.9.1 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from kornia) (2.1.1+cu121)
Requirement already satisfied: filelock in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (3.13.1)
Requirement already satisfied: typing-extensions in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (4.8.0)
Requirement already satisfied: sympy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (1.12)
Requirement already satisfied: networkx in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (3.2.1)
Requirement already satisfied: jinja2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (3.1.2)
Requirement already satisfied: fsspec in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.9.1->kornia) (2023.10.0)
Requirement already satisfied: MarkupSafe>=2.0 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch>=1.9.1->kornia) (2.1.3)
Requirement already satisfied: mpmath>=0.19 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch>=1.9.1->kornia) (1.3.0)
Installing scipy...
Requirement already satisfied: scipy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (1.11.4)
Requirement already satisfied: numpy<1.28.0,>=1.21.6 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from scipy) (1.26.2)
Installing Pillow...
Requirement already satisfied: Pillow in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (9.5.0)
Installing torchvision...
Requirement already satisfied: torchvision in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (0.16.1+cu121)
Requirement already satisfied: numpy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (1.26.2)
Requirement already satisfied: requests in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (2.31.0)
Requirement already satisfied: torch==2.1.1+cu121 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (2.1.1+cu121)
Requirement already satisfied: pillow!=8.3.,>=5.3.0 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision) (9.5.0)
Requirement already satisfied: filelock in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.1.1+cu121->torchvision) (3.13.1)
Requirement already satisfied: typing-extensions in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.1.1+cu121->torchvision) (4.8.0)
Requirement already satisfied: sympy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.1.1+cu121->torchvision) (1.12)
Requirement already satisfied: networkx in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.1.1+cu121->torchvision) (3.2.1)
Requirement already satisfied: jinja2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.1.1+cu121->torchvision) (3.1.2)
Requirement already satisfied: fsspec in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch==2.1.1+cu121->torchvision) (2023.10.0)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->torchvision) (2023.11.17)
Requirement already satisfied: MarkupSafe>=2.0 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch==2.1.1+cu121->torchvision) (2.1.3)
Requirement already satisfied: mpmath>=0.19 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch==2.1.1+cu121->torchvision) (1.3.0)
Installing tqdm...
Requirement already satisfied: tqdm in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (4.66.1)
Requirement already satisfied: colorama in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from tqdm) (0.4.6)
Installing timm==0.6.13...
Requirement already satisfied: timm==0.6.13 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (0.6.13)
Requirement already satisfied: torch>=1.7 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (2.1.1+cu121)
Requirement already satisfied: torchvision in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (0.16.1+cu121)
Requirement already satisfied: pyyaml in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (6.0.1)
Requirement already satisfied: huggingface-hub in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from timm==0.6.13) (0.19.4)
Requirement already satisfied: filelock in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (3.13.1)
Requirement already satisfied: typing-extensions in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (4.8.0)
Requirement already satisfied: sympy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (1.12)
Requirement already satisfied: networkx in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (3.2.1)
Requirement already satisfied: jinja2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (3.1.2)
Requirement already satisfied: fsspec in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torch>=1.7->timm==0.6.13) (2023.10.0)
Requirement already satisfied: requests in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (2.31.0)
Requirement already satisfied: tqdm>=4.42.1 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (4.66.1)
Requirement already satisfied: packaging>=20.9 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from huggingface-hub->timm==0.6.13) (23.2)
Requirement already satisfied: numpy in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision->timm==0.6.13) (1.26.2)
Requirement already satisfied: pillow!=8.3.,>=5.3.0 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from torchvision->timm==0.6.13) (9.5.0)
Requirement already satisfied: colorama in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from tqdm>=4.42.1->huggingface-hub->timm==0.6.13) (0.4.6)
Requirement already satisfied: MarkupSafe>=2.0 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from jinja2->torch>=1.7->timm==0.6.13) (2.1.3)
Requirement already satisfied: charset-normalizer<4,>=2 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from requests->huggingface-hub->timm==0.6.13) (2023.11.17)
Requirement already satisfied: mpmath>=0.19 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from sympy->torch>=1.7->timm==0.6.13) (1.3.0)
Checking cupy...
Uninstall cupy if existed...
WARNING: Skipping cupy-wheel as it is not installed.
WARNING: Skipping cupy-cuda102 as it is not installed.
WARNING: Skipping cupy-cuda110 as it is not installed.
WARNING: Skipping cupy-cuda111 as it is not installed.
Found existing installation: cupy-cuda11x 12.3.0
Uninstalling cupy-cuda11x-12.3.0:
Successfully uninstalled cupy-cuda11x-12.3.0
WARNING: Skipping cupy-cuda12x as it is not installed.
Installing cupy...
Collecting cupy-cuda11x
Using cached cupy_cuda11x-12.3.0-cp311-cp311-win_amd64.whl.metadata (2.7 kB)
Requirement already satisfied: numpy<1.29,>=1.20 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from cupy-cuda11x) (1.26.2)
Requirement already satisfied: fastrlock>=0.5 in d:\sd\comfyui_windows_portable\python_embeded\lib\site-packages (from cupy-cuda11x) (0.8.2)
Using cached cupy_cuda11x-12.3.0-cp311-cp311-win_amd64.whl (70.0 MB)
Installing collected packages: cupy-cuda11x
Successfully installed cupy-cuda11x-12.3.0
Traceback (most recent call last):
File "/home/ComfyUI/nodes.py", line 1735, in load_custom_node
module_spec.loader.exec_module(module)
File "", line 883, in exec_module
File "", line 241, in _call_with_frames_removed
File "/home/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation/init.py", line 9, in
from models.gmfss_fortuna import GMFSS_Fortuna_VFI
ModuleNotFoundError: No module named 'models.gmfss_fortuna'
Cannot import /home/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation module for custom nodes: No module named 'models.gmfss_fortuna'
Import times for custom nodes:
0.1 seconds (IMPORT FAILED): /home/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation
Installed today and getting an import error. Installed repo through Comfy Manager. Any ideas what might be wrong? @Fannovel16
I using this in a steerable motion workflow in ComfyUI. Every time it runs through the batch interpolation node, I get this error
TypeError: BatchCreativeInterpolationNode.combined_function() got an unexpected keyword argument 'cn_start_at'
the value of cn_start_at is 0.00 which is the default. I tried changing it but I keep getting this error.
Anyone have any ideas??
techniques like animatediff let us create looping sequences of frames. when these frames are passed through VFI, a "jerk" results at the loop point because the node doesn't know to interpolate between the last and first frames. demonstration: https://twitter.com/DigThatData/status/1712292557441671223
suggested fix: add a "video_is_loop" toggle (or something like that) that allows the user to indicate to the VFI node that it should concatenate the first frame to the end before interpolating and pop it off before returning the output.
When loading the graph, the following node types were not found:
RIFE VFI
None of the nodes appear in active available custom nodes list, but the folder with all the assets are in the proper custom nodes folder. Uninstalling and reinstalling the custom node does not work.
I appreciate these fantastic nodes.
I have a simple question: I recently updated my comfyui and all node suites via the manager. After restarting comfyui, all requirements are installed again as usual. However, I noticed that your repository installs timm==0.6.13
, but later in the process, comfyui_segment_anything
removes it and installs timm-0.9.12
.
Would it be feasible to update your nodes to the newer version of timm, or would that potentially lead to errors?
I believe segment-anything
simply uses the latest version. Here is the requirements.txt
of segment-anything
:
segment_anything
timm
addict
yapf
Thank you very much.
A web gui with GMFSS mp4 support would be good.
I run workflow, and show this info:
Downloading: "https://github.com/styler00dollar/VSGAN-tensorrt-docker/releases/download/models/GMFSS_fortuna_union_fusionnet.pkl" to /home/llm/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation/ckpts/gmfss_fortuna/GMFSS_fortuna_union_fusionnet.pkl
100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 30.0M/30.0M [01:48<00:00, 291kB/s]
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "/home/llm/ComfyUI/execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/home/llm/ComfyUI/execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "/home/llm/ComfyUI/execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/home/llm/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation/models/gmfss_fortuna/init.py", line 128, in vfi
interpolation_model = CommonModelInference(model_type=ckpt_name)
File "/home/llm/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation/models/gmfss_fortuna/init.py", line 36, in init
self.model.load_model({
File "/home/llm/ComfyUI/custom_nodes/ComfyUI-Frame-Interpolation/models/gmfss_fortuna/GMFSS_Fortuna_union_arch.py", line 1716, in load_model
self.ifnet.load_state_dict(torch.load(path_dict["ifnet"]))
File "/home/llm/ComfyUI/myenv/lib/python3.10/site-packages/torch/serialization.py", line 797, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "/home/llm/ComfyUI/myenv/lib/python3.10/site-packages/torch/serialization.py", line 283, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory
Hello. When I try to use the KSampler, I keep getting this error:
Error occurred when executing KSampler Gradually Adding More Denoise (efficient):
name 'postprocess_frames' is not defined
File "F:\ComfyUI-Update-9-1-2023\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "F:\ComfyUI-Update-9-1-2023\ComfyUI_windows_portable\ComfyUI\execution.py", line 81, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "F:\ComfyUI-Update-9-1-2023\ComfyUI_windows_portable\ComfyUI\execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "F:\ComfyUI-Update-9-1-2023\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\other_nodes.py", line 78, in sample
gradually_denoising_samples = [
File "F:\ComfyUI-Update-9-1-2023\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\other_nodes.py", line 79, in
common_ksampler(
File "F:\ComfyUI-Update-9-1-2023\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\other_nodes.py", line 37, in common_ksampler
return (postprocess_frames(out_frames), )
I've tried deleting and reinstall but nothing seems to get rid of this error.
Thanks!
Hello again,
Im getting the same issue, where Film VFI does not want to install.
I have a fresh copy of Comfy and that node does not want to work when I load a workflow that uses it.
You had fixed it with a new commit but on a new comfy install Im getting the same error as before.
Anyway to help me with it again? below is my code.
G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable>.\python_embeded\python.exe -s ComfyUI\main.py --windows-standalone-build
** ComfyUI start up time: 2023-10-14 20:31:51.547468
Prestartup times for custom nodes:
0.0 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
Total VRAM 16375 MB, total RAM 131015 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 : cudaMallocAsync
VAE dtype: torch.bfloat16
Using pytorch cross attention
Adding extra search path checkpoints G:\WORKSPACE AI\00_SD_MODELS\CHECKPOINTS
Adding extra search path configs G:\WORKSPACE AI\00_SD_MODELS\models/Stable-diffusion
Adding extra search path vae G:\WORKSPACE AI\00_SD_MODELS\VAE
Adding extra search path loras G:\WORKSPACE AI\00_SD_MODELS\LORAS
Adding extra search path loras G:\WORKSPACE AI\00_SD_MODELS\models/LyCORIS
Adding extra search path upscale_models G:\WORKSPACE AI\00_SD_MODELS\ERSGAN
Adding extra search path upscale_models G:\WORKSPACE AI\00_SD_MODELS\models/RealESRGAN
Adding extra search path upscale_models G:\WORKSPACE AI\00_SD_MODELS\models/SwinIR
Adding extra search path embeddings G:\WORKSPACE AI\00_SD_MODELS\EMBEDDINGS
Adding extra search path hypernetworks G:\WORKSPACE AI\00_SD_MODELS\models/hypernetworks
Adding extra search path controlnet G:\WORKSPACE AI\00_SD_MODELS\CONTROLNET
Using pytorch cross attention
G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_environment.py:216: UserWarning: CUDA path could not be detected. Set CUDA_PATH environment variable if CuPy fails to load.
warnings.warn(
Traceback (most recent call last):
File "G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_init_.py", line 17, in
from cupy import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^
File "G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_core_init.py", line 3, in
from cupy._core import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "cupy_core\core.pyx", line 1, in init cupy.core.core
File "G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda_init.py", line 8, in
from cupy.cuda import compiler # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda\compiler.py", line 13, in
from cupy.cuda import device
File "cupy\cuda\device.pyx", line 1, in init cupy.cuda.device
ImportError: DLL load failed while importing runtime: The specified module could not be found.
The above exception was the direct cause of the following exception:
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: None
DLL dependencies:
KERNEL32.dll -> C:\Windows\System32\KERNEL32.DLL
MSVCP140.dll -> C:\Windows\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\Windows\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\python311.dll
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: None
DLL dependencies:
KERNEL32.dll -> C:\Windows\System32\KERNEL32.DLL
MSVCP140.dll -> C:\Windows\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\Windows\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\python311.dll
Registered sys.path: ['G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\init.py', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\custom_pycocotools', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\custom_oneformer', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\custom_mmpkg', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\custom_midas_repo', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\custom_detectron2', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src\controlnet_aux', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\src', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\git\ext\gitdb', WindowsPath('G:/WORKSPACE AI/02_COMFY/ComfyUI_windows_portable/ComfyUI'), 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\comfy', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\python311.zip', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\win32', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\win32\lib', 'G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\python_embeded\Lib\site-packages\Pythonwin', '../..']
G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux\node_wrappers\dwpose.py:26: UserWarning: Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device (super slow)
warnings.warn("Onnxruntime not found or doesn't come with acceleration providers, switch to OpenCV with CPU device (super slow)")
WAS Node Suite: OpenCV Python FFMPEG support is enabled
WAS Node Suite Warning: ffmpeg_bin_path
is not set in G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui\was_suite_config.json
config file. Will attempt to use system ffmpeg binaries if available.
WAS Node Suite: Finished. Loaded 196 nodes successfully.
"Success is not just about making money. It's about making a difference." - Unknown
Total VRAM 16375 MB, total RAM 131015 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce RTX 4080 : cudaMallocAsync
VAE dtype: torch.bfloat16
Import times for custom nodes:
0.0 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Advanced-ControlNet
0.0 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-AnimateDiff-Evolved
0.0 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ymc-node-suite-comfyui
0.0 seconds (IMPORT FAILED): G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
0.0 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
0.3 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
0.4 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\comfyui_controlnet_aux
1.3 seconds: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\was-node-suite-comfyui
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: G:\WORKSPACE AI\02_COMFY\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json
I have some problem with the node STMFNet VFI.
I get error - can't Import name 'get_ckpt_container_path' from 'utils'
utils 3.8 is instal
I use window 10, I am on portable version of comfyUi (uptodate with the manager )
workflow i use https://twitter.com/peteromallet/status/1716044441985728606
any feedback will be great if you have some advise.
I am new with all those python library, probably the error is on my side but can't figure it out .
Error occurred when executing RIFE VFI:
PytorchStreamReader failed reading zip archive: failed finding central directory
File "n:\AI_tools\ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "n:\AI_tools\ComfyUI_windows_portable\ComfyUI\execution.py", line 85, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "n:\AI_tools\ComfyUI_windows_portable\ComfyUI\execution.py", line 78, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "N:\AI_tools\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\rife_init_.py", line 94, in vfi
interpolation_model.load_state_dict(torch.load(model_path))
^^^^^^^^^^^^^^^^^^^^^^
File "n:\AI_tools\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 993, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "n:\AI_tools\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\serialization.py", line 447, in init
super().init(torch._C.PyTorchFileReader(name_or_buffer))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
This seems to quit about %20 of the time (FiLM VFI)
Without an error message, I'm assuming it's being killed due to running our of ram (even though I have 24GB GPU and 64GB system)
Loading 1 new model
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Final clearing cache...
Comfy-VFI: Done cache clearing
Killed
Sucks because It looses the whole queue.
Are there any other logs specifically for this custom node?
Using RIFE, I continuously get this error:
Error occurred when executing RIFE VFI:
Allocation on device 0 would exceed allowed memory. (out of memory)
Even on 24GB with 16 frames.
But when I run python inference_video.py --fps=24 --video=${tempVideoPath} --output=${outputVideoPath}
from ECCV2022-RIFE, with any number of frames, it runs without any issues.
I was wondering if it could be possible to make the interpolation avoid breaking a perfect loop. I guess by not creating frames after the final frame? Don't know how it works internally but it seems to break the perfect loops I create with AnimateDiff.
Log:
Prestartup times for custom nodes:
0.0 seconds: C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
Total VRAM 6144 MB, total RAM 8159 MB
Set vram state to: NORMAL_VRAM
Device: cuda:0 NVIDIA GeForce GTX 1060 6GB : cudaMallocAsync
VAE dtype: torch.float32
Using pytorch cross attention
Import times for custom nodes:
0.0 seconds: C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation
0.1 seconds: C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite
0.6 seconds: C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager
Starting server
To see the GUI go to: http://127.0.0.1:8188
FETCH DATA from: C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Manager\extension-node-map.json
got prompt
C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_environment.py:216: UserWarning: CUDA path could not be detected. Set CUDA_PATH environment variable if CuPy fails to load.
warnings.warn(
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_init_.py", line 17, in
from cupy import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy_core_init.py", line 3, in
from cupy._core import core # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "cupy_core\core.pyx", line 1, in init cupy.core.core
File "C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda_init.py", line 8, in
from cupy.cuda import compiler # NOQA
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\cupy\cuda\compiler.py", line 13, in
from cupy.cuda import device
File "cupy\cuda\device.pyx", line 1, in init cupy.cuda.device
ImportError: DLL load failed while importing runtime: The specified module could not be found.
The above exception was the direct cause of the following exception:
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: None
DLL dependencies:
KERNEL32.dll -> C:\Windows\System32\KERNEL32.DLL
MSVCP140.dll -> C:\Windows\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\Windows\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> C:\Users\user\Downloads\new_ComfyUI_windows_portable_nvidia_cu121_or_cpu\ComfyUI_windows_portable\python_embeded\python311.dll
Prompt executed in 1.60 seconds
Nodes other than gmfss seem to be working fine. This is with CUDA toolkit uninstalled,before I installed 12.1 and 12.2, both didn't seem to fix it and I got a bunch of missing dll files-could be that some dll files required are missing from earlier versions of CUDA,but I doubt it. Going to see if installing it with conda will fix anything.
Error occurred when executing M2M VFI:
module 'tensorflow' has no attribute 'Tensor'
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\ComfyUI-master\execution.py", line 153, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\ComfyUI-master\execution.py", line 83, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\ComfyUI-master\execution.py", line 76, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\ComfyUI-master\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\m2m_init_.py", line 48, in vfi
frames = preprocess_frames(frames)
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\ComfyUI-master\custom_nodes\ComfyUI-Frame-Interpolation\vfi_utils.py", line 115, in preprocess_frames
return einops.rearrange(frames, "n h w c -> n c h w")
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\lib\site-packages\einops\einops.py", line 591, in rearrange
return reduce(tensor, pattern, reduction="rearrange", **axes_lengths)
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\lib\site-packages\einops\einops.py", line 518, in reduce
backend = get_backend(tensor)
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\lib\site-packages\einops_backends.py", line 33, in get_backend
if backend.is_appropriate_type(tensor):
File "C:\Users\nei_b\AppData\Local\Programs\Python\Python310\lib\site-packages\einops_backends.py", line 408, in is_appropriate_type
return isinstance(tensor, (self.tf.Tensor, self.tf.Variable))
After installing tensorflow, M2M worked fine.
Please, update requirements or implementation.
Test the simple workflow of following
get error of cupy
> File "E:\DEV\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops\costvol.py", line 1, in <module>
> from .utils import cuda_kernel, cuda_launch, cuda_int32
> File "E:\DEV\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops\utils.py", line 1, in <module>
> import cupy
> ModuleNotFoundError: No module named 'cupy'
..\..\..\python_embeded\python.exe -m pip install cupy
got error
raise CompileError(None, pyx_file) Cython.Compiler.Errors.CompileError: cupy\_core\_kernel.pyx [end of output]
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for cupy
Running setup.py clean for cupy
Failed to build cupy
ERROR: Could not build wheels for cupy, which is required to install pyproject.toml-based projects
any workround for that? I try to downgrade Cython, but failed.
I have tried everything I could think of to make CAIN video frame interpolation work with the CAIN VFI node, but no matter what I do I get a Tensors must have same number of dimensions: got 4 and 3
error message.
The following log shows what happens when I try to pass a 23 frames long sequence to it.
It seems to be able to create the images, hence the Comfy-VFI done! 46 frames generated at resolution: torch.Size([1, 3, 512, 512])
message, but after that step the frames are not sent to the next node where they would get converted to video.
Comfy-VFI: Clearing cache... Done cache clearing
Comfy-VFI: Clearing cache... Done cache clearing
Comfy-VFI done! 46 frames generated at resolution: torch.Size([1, 3, 512, 512])
ERROR:root:!!! Exception during processing !!!
ERROR:root:Traceback (most recent call last):
File "D:\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\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 "D:\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 "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\cain\__init__.py", line 62, in vfi
generic_frame_loop(frames, clear_cache_after_n_frames, multiplier, return_middle_frame, *args,
File "D:\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_utils.py", line 194, in generic_frame_loop
out = torch.cat(output_frames, dim=0)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: Tensors must have same number of dimensions: got 4 and 3
Prompt executed in 4.23 seconds
Hi there. I found a bug.
FILM interpolation makes 2 or 3 duplicate frames between each inference.
This patch should solve the bug.
--- models/film/__init__.py
+++ models/film/__init__.py
@@ -81,12 +81,12 @@ class FILM_VFI:
output_frames = []
for frame_itr in range(len(frames) - 1): # Skip the final frame since there are no frames after it
frame_0 = frames[frame_itr]
- output_frames.append(frame_0) # Start with first frame
if interpolation_states is not None and interpolation_states.is_frame_skipped(frame_itr):
continue
- output_frames.extend(inference(model, frame_0, frames[frame_itr + 1], multiplier - 1))
+ relust = inference(model, frame_0, frames[frame_itr + 1], multiplier - 1)
+ output_frames.extend(relust[:-1])
# Try to avoid a memory overflow by clearing cuda cache regularly
if number_of_frames_processed_since_last_cleared_cuda_cache >= clear_cache_after_n_frames:
After general updating today, I got this error:
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: None
DLL dependencies:
KERNEL32.dll -> C:\WINDOWS\System32\KERNEL32.DLL
MSVCP140.dll -> C:\WINDOWS\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-string-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
api-ms-win-crt-time-l1-1-0.dll -> C:\WINDOWS\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\cublas64_11.dll
cudnn64_8.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\cufft64_10.dll
curand64_10.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\cusparse64_11.dll
nvrtc64_112_0.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\lib\nvrtc64_112_0.dll
python310.dll -> C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\python310.dll
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\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 "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\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 "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\gmfss_fortuna_init_.py", line 129, in vfi
interpolation_model = CommonModelInference(model_type=ckpt_name)
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\gmfss_fortuna_init_.py", line 30, in init
from .GMFSS_Fortuna_arch import Model as GMFSS
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\gmfss_fortuna\GMFSS_Fortuna_arch.py", line 29, in
from vfi_models.ops import softsplat
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops_init_.py", line 21, in
from .cupy_ops import softsplat, ModuleSoftsplat, FunctionSoftsplat, softsplat_func, costvol_func, sepconv_func, init, batch_edt, FunctionAdaCoF, ModuleCorrelation, FunctionCorrelation, FunctionCorrelation
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops_init.py", line 1, in
from .costvol import *
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops\costvol.py", line 1, in
from .utils import cuda_kernel, cuda_launch, cuda_int32
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops\utils.py", line 1, in
import cupy
File "C:\Users\garci\OneDrive\Documentos\ComfyUI_windows_portable_nvidia_cu118_or_cpu\ComfyUI_windows_portable\python_embeded\lib\site-packages\cupy_init_.py", line 19, in
raise ImportError(f'''
It is quite interesting that someone decided to put my stuff into comfy. I had a faulty 4.7 implementation for a while since I couldn't verify my code because I was training a model and was busy too, so it was faulty for some time. Tried to fix that yesterday here. Should work now unless I overlooked something.
TITLE EDIT : Can't go above 51 frames PER SECOND. Dumb me got it wrong -_-'.
This custom node miraculously started working for me. And it is incredible for animation! In fact, this will quickly become a must-have for AI videos.
But for now there is a huge limitation, and I'm not sure why that is: the video gets more fluid up to a framerate of 51 in Video Combine. But if you try 52 or more, the result is very slow.
It could be because of Video Helper Suite, so I will post a question there too.
Currently this node pack hard fails on DirectML (and anything else) because of several unchecked converts to CUDA types and the nodes that use CUPY without wrapping it in availability checks. Since ComfyUI itself is compatible with other compute devices it should probably gracefully disable the nodes that you don't feel like converting (one has a bunch of inlined CUDA so I can see not dealing with that mess), make the ones that are already wrapped use Comfy's specified device so they don't fall back to CPU when not needed, and fix the few instances where there's an unchecked conversion to a cuda type to use a checked wrapper similar to the rest. There shouldn't be a ton of changes needed but Python isn't a language I'll write in.
This node was working fine until yesterday, all of a sudden started getting this runtime error:
Tried reducing the clear cache to 5 frames, but didn't help. Here's my workflow:
This is the error from the terminal window:
!!! Exception during processing !!!
Traceback (most recent call last):
File "C:\Apps\ComfyUI_windows_portable\ComfyUI\execution.py", line 152, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "C:\Apps\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 "C:\Apps\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 "C:\Apps\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\film\__init__.py", line 86, in vfi
relust = inference(model, frames[frame_itr], frames[frame_itr + 1], multiplier - 1)
File "C:\Apps\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\models\film\__init__.py", line 35, in inference
prediction = model(x0, x1, dt)
File "C:\Apps\ComfyUI_windows_portable\python_embeded\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript, serialized code (most recent call last):
File "code/__torch__/interpolator.py", line 15, in forward
x1: Tensor,
batch_dt: Tensor) -> Tensor:
_0 = (self).debug_forward(x0, x1, batch_dt, )
~~~~~~~~~~~~~~~~~~~ <--- HERE
return (_0["image"])[0]
def debug_forward(self: __torch__.interpolator.Interpolator,
File "code/__torch__/interpolator.py", line 64, in debug_forward
aligned_pyramid1 = __torch__.util.concatenate_pyramids(aligned_pyramid0, forward_flow, )
fuse = self.fuse
_18 = [(fuse).forward(aligned_pyramid1, )]
~~~~~~~~~~~~~ <--- HERE
_19 = {"image": _18, "forward_residual_flow_pyramid": forward_residual_flow_pyramid, "backward_residual_flow_pyramid": backward_residual_flow_pyramid, "forward_flow_pyramid": forward_flow_pyramid, "backward_flow_pyramid": backward_flow_pyramid}
return _19
File "code/__torch__/fusion.py", line 56, in forward
_04 = getattr(_3, "0")
net16 = (_04).forward(net15, )
net17 = torch.cat([pyramid[i2], net16], 1)
~~~~~~~~~ <--- HERE
_13 = getattr(_3, "1")
net18 = (_13).forward(net17, )
Traceback of TorchScript, original code (most recent call last):
File "C:\Users\Danylo\PycharmProjects\frame-interpolation-pytorch\interpolator.py", line 160, in forward
@torch.jit.export
def forward(self, x0, x1, batch_dt) -> torch.Tensor:
return self.debug_forward(x0, x1, batch_dt)['image'][0]
~~~~~~~~~~~~~~~~~~ <--- HERE
File "C:\Users\Danylo\PycharmProjects\frame-interpolation-pytorch\interpolator.py", line 151, in debug_forward
return {
'image': [self.fuse(aligned_pyramid)],
~~~~~~~~~ <--- HERE
'forward_residual_flow_pyramid': forward_residual_flow_pyramid,
'backward_residual_flow_pyramid': backward_residual_flow_pyramid,
File "C:\Users\Danylo\PycharmProjects\frame-interpolation-pytorch\fusion.py", line 116, in forward
net = F.interpolate(net, size=level_size, mode='nearest')
net = layers[0](net)
net = torch.cat([pyramid[i], net], dim=1)
~~~~~~~~~ <--- HERE
net = layers[1](net)
net = layers[2](net)
RuntimeError: Allocation on device 0 would exceed allowed memory. (out of memory)
Currently allocated : 5.77 GiB
Requested : 568.12 MiB
Device limit : 12.00 GiB
Free (according to CUDA): 0 bytes
PyTorch limit (set by user-supplied memory fraction)
: 17179869184.00 GiB
I've been really curious to try and completely failing at getting a node from ComfyUI-Frame-Interpolation to load called STMFNet VFI.
Here is what I've done to try to fix it myself so far.
*Removed ComfyUI-Frame-Interpolation and git cloned it
*Ran the install.bat file
*Uninstalled and Reinstalled CUDA 12.1
*Restarted my computer
*Made sure path was correct (I think it is?) in my environment variables in Windows. (The error says something about that, maybe this is what I'm doing wrong).
*Installed a completely new instance of ComfyUI
*Git Cloned from the repo
*Ran the install.bat
I'm running on Windows 11 Pro with an RTX 4090, Cuda 12.1 and Python 3.10.11
I also just updated to Python 3.11 and ran a new install of everything again to see if that would help resolve this.
Here's the error message I receive:
Error occurred when executing STMFNet VFI:
================================================================
Failed to import CuPy.
If you installed CuPy via wheels (cupy-cudaXXX or cupy-rocm-X-X), make sure that the package matches with the version of CUDA or ROCm installed.
On Linux, you may need to set LD_LIBRARY_PATH environment variable depending on how you installed CUDA/ROCm.
On Windows, try setting CUDA_PATH environment variable.
Check the Installation Guide for details:
https://docs.cupy.dev/en/latest/install.html
CUDA Path: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v12.1
DLL dependencies:
KERNEL32.dll -> C:\Windows\System32\KERNEL32.DLL
MSVCP140.dll -> C:\Windows\SYSTEM32\msvcp140.dll
VCRUNTIME140.dll -> E:\000ComfyUI_portable_Cuda121\python_embeded\VCRUNTIME140.dll
api-ms-win-crt-convert-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-environment-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-filesystem-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-heap-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-runtime-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
api-ms-win-crt-stdio-l1-1-0.dll -> C:\Windows\System32\ucrtbase.dll
cuTENSOR.dll -> not found
cublas64_11.dll -> not found
cudart64_110.dll -> not found
cudnn64_8.dll -> E:\000ComfyUI_portable_Cuda121\python_embeded\Lib\site-packages\torch\lib\cudnn64_8.dll
cufft64_10.dll -> not found
curand64_10.dll -> E:\000ComfyUI_portable_Cuda121\python_embeded\Lib\site-packages\torch\lib\curand64_10.dll
cusolver64_11.dll -> E:\000ComfyUI_portable_Cuda121\python_embeded\Lib\site-packages\torch\lib\cusolver64_11.dll
cusparse64_11.dll -> not found
nvcuda.dll -> C:\Windows\SYSTEM32\nvcuda.dll
nvrtc64_112_0.dll -> not found
python311.dll -> E:\000ComfyUI_portable_Cuda121\python_embeded\python311.dll
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\execution.py", line 154, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\execution.py", line 84, in get_output_data
return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\execution.py", line 77, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\stmfnet_init_.py", line 45, in vfi
from .stmfnet_arch import STMFNet_Model
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\stmfnet\stmfnet_arch.py", line 28, in
from vfi_models.ops import FunctionCorrelation, FunctionAdaCoF, ModuleSoftsplat
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops_init_.py", line 21, in
from .cupy_ops import softsplat, ModuleSoftsplat, FunctionSoftsplat, softsplat_func, costvol_func, sepconv_func, init, batch_edt, FunctionAdaCoF, ModuleCorrelation, FunctionCorrelation, FunctionCorrelation
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops_init.py", line 1, in
from .costvol import *
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops\costvol.py", line 1, in
from .utils import cuda_kernel, cuda_launch, cuda_int32
File "E:\000ComfyUI_portable_Cuda121\ComfyUI\custom_nodes\ComfyUI-Frame-Interpolation\vfi_models\ops\cupy_ops\utils.py", line 1, in
import cupy
File "E:\000ComfyUI_portable_Cuda121\python_embeded\Lib\site-packages\cupy_init_.py", line 19, in
raise ImportError(f'''
Film VFI node not found within ComfyUI, im unsure why the installation is failing, cuda supported, problems with cupy, tried install.bat
RuntimeError: MPS: Unsupported Border padding mode
I have tried the config to taichi,but error the same above
Hello! I see the repo is unlicensed. Have you considered adding a license and if so which?
Hi there,
When I start up Comfy your Node never loads, because apparently I'm missing cupy. I did pip install it though.
When I try to re-install it using your .py, I get this:
...Frame-Interpolation> python install-cupy.py
Requirement already satisfied: cupy-cuda11x in c:\python311\lib\site-packages (12.2.0)
Requirement already satisfied: numpy<1.27,>=1.20 in c:\python311\lib\site-packages (from cupy-cuda11x) (1.26.0)
Requirement already satisfied: fastrlock>=0.5 in c:\python311\lib\site-packages (from cupy-cuda11x) (0.8.2)
Can you publish the workflow file of the complex one(All_in_one_v1_3.png),thank you very much!
It used to work fine, but suddenly RIFE is crashing silently after a while.
Using the latest commit with latest ComfyUI, with rife49.pth checkpoint (I tried 46, 47 as well) running on a T4 in google colab
Input has only 120 frames.
Output is:
got prompt
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
Comfy-VFI: Clearing cache...
Comfy-VFI: Done cache clearing
^C
Is there anywhere some workflow example to know how to use those nodes?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.