Closed patrickas closed 6 months ago
Same here.
same as well
same here! I tried a stripped down version:
Ah I just read #2 It needs an SDXL model, now it runs for me
i tryed several sdxl models, even the base one. sadly it dident help.
Try updating transformers
Something isent right with my install. When i try to generate a basic sdxl picture i can see how it generates normaly. but when it is done it turns into a oversaturated mess at the last step, no matter how many steps i render. i think i have to try a complete re-install.
reinstalling comfy has fixed this issue. but now it does not apply the input picture, like some people described in the issue "share the workflow".
Updating transformers solved the issue for me
What means updating transformers?
Updating transformers solved the issue for me
hi, I meet the same promblem, what do you mean updating transformers
Using the workflow in the readme, I am getting the following error: Error occurred when executing PhotoMakerEncode:
Cannot handle this data type: (1, 1, 224, 3), |u1
File "C:\Programs\sd\ComfyUI_nightly\ComfyUI\execution.py", line 154, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\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 "C:\Programs\sd\ComfyUI_nightly\ComfyUI\execution.py", line 77, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\ComfyUI\custom_nodes\ComfyUI-PhotoMaker\photomaker.py", line 89, in encode id_pixel_values = clip_vision.id_image_processor(input_id_images, return_tensors="pt").pixel_values.float() ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\transformers\image_processing_utils.py", line 446, in call return self.preprocess(images, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\transformers\models\clip\image_processing_clip.py", line 318, in preprocess images = [self.resize(image=image, size=size, resample=resample) for image in images] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\transformers\models\clip\image_processing_clip.py", line 318, in images = [self.resize(image=image, size=size, resample=resample) for image in images] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\transformers\models\clip\image_processing_clip.py", line 144, in resize return resize(image, size=output_size, resample=resample, data_format=data_format, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\transformers\image_transforms.py", line 275, in resize image = to_pil_image(image) ^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\transformers\image_transforms.py", line 163, in to_pil_image return PIL.Image.fromarray(image) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Programs\sd\ComfyUI_nightly\python_embeded\Lib\site-packages\PIL\Image.py", line 3092, in fromarray raise TypeError(msg) from e