kijai / ComfyUI-KwaiKolorsWrapper

Diffusers wrapper to run Kwai-Kolors model
Apache License 2.0
518 stars 26 forks source link

[Bug] :bug: After adding this plugin, Yoloworld_ESAM_Zho began to generate errors : failed in the TorchScript interpreter.RuntimeError: invalid vector subscript #18

Closed Erwin11 closed 1 month ago

Erwin11 commented 1 month ago

:bug: :bug: :bug: 屏幕截图 2024-07-09 084741 Yoloworld-sam_bug with-kcolors-.json

_Yoloworld_ESAM_Zho worked before. Are these two plugins incompatible with each other?_

1 My Test Initially, I suspected that my PyTorch version might be incompatible, leading to the issue. Therefore, I downgraded my PyTorch installation to version 2.0.1+cu118, but unfortunately, this did not resolve the problem. Consequently, I decided to revert to the previous version, 2.1.2+cu118.

My next hypothesis was that one of the numerous plugins I had installed could be causing the conflict. To test this theory, I methodically removed all plugins from my system. Subsequently, Yoloworld_ESAM_Zho began functioning correctly again.

I then systematically reintroduced each removed plugin into the ComfyUI interface, one at a time. Through this process, I discovered that the KwaiKolorsWrapper plugin was responsible for the malfunctioning of Yoloworld_ESAM_Zho.

2 Error

Error occurred when executing Yoloworld_ESAM_Zho:

The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
RuntimeError: invalid vector subscript

File "E:\AI\ComfyUI\ComfyUI-webui\ComfyUI_windows_portable\ComfyUI\execution.py", line 151, in recursive_execute
output_data, output_ui = get_output_data(obj, input_data_all)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\ComfyUI\ComfyUI-webui\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 "E:\AI\ComfyUI\ComfyUI-webui\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 "E:\AI\ComfyUI\ComfyUI-webui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\YOLO_WORLD_EfficientSAM.py", line 149, in yoloworld_esam_image
detections.mask = inference_with_boxes(
^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\ComfyUI\ComfyUI-webui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\utils\efficient_sam.py", line 59, in inference_with_boxes
mask = inference_with_box(image, box, model, device)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\ComfyUI\ComfyUI-webui\ComfyUI_windows_portable\ComfyUI\custom_nodes\ComfyUI-YoloWorld-EfficientSAM\utils\efficient_sam.py", line 28, in inference_with_box
predicted_logits, predicted_iou = model(
^^^^^^
File "E:\AI\ComfyUI\ComfyUI-webui\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1518, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "E:\AI\ComfyUI\ComfyUI-webui\ComfyUI_windows_portable\python_embeded\Lib\site-packages\torch\nn\modules\module.py", line 1527, in _call_impl
return forward_call(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^

Close
Peter0755 commented 1 month ago

我也是存在这个问题

l2x commented 1 month ago

+1

zhangfeifei0907 commented 1 month ago

I has the same problem.

nghiavu2011 commented 1 month ago

thanks for your tut, already fix it

Garfield-00 commented 1 month ago

thanks,that's the quesion

liangmou825 commented 2 weeks ago

thanks for your tut, already fix it