miaoshouai
commented
3 months ago seems to me you have unspported image format, could you take a look what types of image extension you have for your image dataset?
Open VJleoliu2023 opened 3 months ago
miaoshouai
commented
3 months ago seems to me you have unspported image format, could you take a look what types of image extension you have for your image dataset?
VJleoliu2023
commented
3 months ago 100% png
miaoshouai
commented
3 months ago just pushed some new code in. update the comfyui node see if that resovles the problem.
Error occurred when executing Miaoshouai_Tagger:
Unable to infer channel dimension format
File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\execution.py", line 151, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\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:\ComfyUI_Windows\ComfyUI-aki-v1.3\execution.py", line 74, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Miaoshouai-Tagger\nodes.py", line 166, in start_tag tags = self.tag_image(image, caption_method, model, processor, device, dtype, max_new_tokens, num_beams) File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\custom_nodes\ComfyUI-Miaoshouai-Tagger\nodes.py", line 77, in tag_image inputs = processor(text=prompt, images=image, return_tensors="pt", do_rescale=False).to(dtype).to(device) File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3.cache\huggingface\modules\transformers_modules\microsoft\Florence-2-base-ft\ace966bc263601c622220596bd7abdc2e4e42267\processing_florence2.py", line 250, in call pixel_values = self.image_processor( File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\python\lib\site-packages\transformers\image_processing_utils.py", line 41, in call return self.preprocess(images, kwargs) File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\python\lib\site-packages\transformers\models\clip\image_processing_clip.py", line 320, in preprocess input_data_format = infer_channel_dimension_format(images[0]) File "E:\ComfyUI_Windows\ComfyUI-aki-v1.3\python\lib\site-packages\transformers\image_utils.py", line 255, in infer_channel_dimension_format raise ValueError("Unable to infer channel dimension format")