Open netdzynr opened 1 month ago
Am encountering an error on the muse_pose_align node (all nodes appear to load correctly).
Error occurred when executing museposealign: name 'adapt_mmdet_pipeline' is not defined File "/Users/me/comfyui/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/Users/me/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 "/Users/me/comfyui/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/nodes.py", line 554, in posealign_func return run_align_video_with_filterPose_translate_smooth(args) File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/nodes.py", line 276, in run_align_video_with_filterPose_translate_smooth detector = DWposeDetector( File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/pose/script/dwpose.py", line 74, in __init__ self.pose_estimation = Wholebody(det_config, det_ckpt, pose_config, pose_ckpt, device) File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/pose/script/wholebody.py", line 52, in __init__ self.detector.cfg = adapt_mmdet_pipeline(self.detector.cfg)
All models downloaded and placed as prescribed.
Is there any limitation on the size/proportion of source media?
Source video: 1410 x 2560 2.9mb Source image: 512 x 929 400kb muse_pose_align: detect_resolution: 512 muse_pose_align: image_resolution: 768
System: M1, MacOS Ventura
Are the labels on the muse_pose_align node misnamed? Should they read "horizontal_resolution" and "vertical_resolution"?
Has mmpose been successfully installed?
Reinstalled, this seemed to work: the openpose(?) frame sequence was generated. Thank you.
But new torch-related error, which I assume is a MacOS problem.
Error occurred when executing musepose:
Torch not compiled with CUDA enabled
File "/Users/me/comfyui/execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
File "/Users/me/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 "/Users/me/comfyui/execution.py", line 74, in map_node_over_list
results.append(getattr(obj, func)(**slice_dict(input_data_all, i)))
File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/nodes.py", line 782, in musepose_func
return musepose(args, image_path, video)
File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/nodes.py", line 601, in musepose
vae = AutoencoderKL.from_pretrained(pretrained_vae_path,
File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1173, in to
return self._apply(convert)
File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply
module._apply(fn)
File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply
module._apply(fn)
File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 804, in _apply
param_applied = fn(param)
File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1159, in convert
return t.to(
File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/cuda/__init__.py", line 284, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
Not sure if you can offer a suggestion for this?
Reinstalled, this seemed to work: the openpose(?) frame sequence was generated. Thank you.
But new torch-related error, which I assume is a MacOS problem.
Error occurred when executing musepose: Torch not compiled with CUDA enabled File "/Users/me/comfyui/execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "/Users/me/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 "/Users/me/comfyui/execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(**slice_dict(input_data_all, i))) File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/nodes.py", line 782, in musepose_func return musepose(args, image_path, video) File "/Users/me/comfyui/custom_nodes/Comfyui-MusePose/nodes.py", line 601, in musepose vae = AutoencoderKL.from_pretrained(pretrained_vae_path, File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1173, in to return self._apply(convert) File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 779, in _apply module._apply(fn) File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 804, in _apply param_applied = fn(param) File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1159, in convert return t.to( File "/Users/me/comfyui/venv/lib/python3.10/site-packages/torch/cuda/__init__.py", line 284, in _lazy_init raise AssertionError("Torch not compiled with CUDA enabled")
Not sure if you can offer a suggestion for this?
i updated the requirements.txt file, you can try if it helps
Hi!
I have same problem in windows. I re installed the mmpose 1.3.1 manually but the issue continue:
Error occurred when executing museposealign:
name 'init_detector' is not defined
File "G:\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\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 "G:\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 "G:\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-MusePose\nodes.py", line 554, in posealign_func return run_align_video_with_filterPose_translate_smooth(args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-MusePose\nodes.py", line 276, in run_align_video_with_filterPose_translate_smooth detector = DWposeDetector( ^^^^^^^^^^^^^^^ File "G:\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-MusePose\pose\script\dwpose.py", line 74, in init self.pose_estimation = Wholebody(det_config, det_ckpt, pose_config, pose_ckpt, device) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "G:\ComfyUI_windows_portable\ComfyUI\custom_nodes\Comfyui-MusePose\pose\script\wholebody.py", line 51, in init self.detector = init_detector(det_config, det_ckpt, device=device) ^^^^^^^^^^^^^
Am encountering an error on the muse_pose_align node (all nodes appear to load correctly).
All models downloaded and placed as prescribed.
Is there any limitation on the size/proportion of source media?
Source video: 1410 x 2560 2.9mb Source image: 512 x 929 400kb muse_pose_align: detect_resolution: 512 muse_pose_align: image_resolution: 768
System: M1, MacOS Ventura
Are the labels on the muse_pose_align node misnamed? Should they read "horizontal_resolution" and "vertical_resolution"?