Open kubilaykilinc opened 5 months ago
I am seeing the seeing the same error. As far as I can tell this is because insightface is not detecting a face in the image.
OK, I think I figured it out. This occurs when a face is not detected in the image. There are a few things that factor into this.
det_size
is 640px by 640pximg_resize
is max 1280 pixelsIf your face is taking up the majority of the pixels, i.e.> 640px, then it will fail to detect a face and show this error. Therefore, you will need to make sure your image is > 640 pixels and that the face is < 640 pixels of the entire image.
Thank you very much for the information you provided. I thought about your idea and solved this problem by adding the "Prepare imafe for insightface" node between the source face image and the "prepare image for clipvision" node. Problem solved.
@ZHO-ZHO-ZHO I think raising an error when face is not detected would be a good strategy here. Otherwise the end-user is left to interpret an arguably ambiguous error.
My PC configuration: NVDIA RTX 3050 - 12 GB Vram 32 GB Ram - Win 11 Last version ComfyUI and successfully installed CofyUI InstantID node
I am using example workflow & Using JuggernutXL 8 - base model. but i am getting this error.
Error occurred when executing PreviewImage:
'str' object has no attribute 'shape'
File "ComfyUI_windows_portable\ComfyUI\execution.py", line 155, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "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 "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 "ComfyUI_windows_portable\ComfyUI\nodes.py", line 1415, in save_images full_output_folder, filename, counter, subfolder, filename_prefix = folder_paths.get_save_image_path(filename_prefix, self.output_dir, images[0].shape[1], images[0].shape[0]) ^^^^^^^^^^^^^^^