The image class I input is <class 'PIL.PngImagePlugin.PngImageFile'>, which is a subclass of the supported <class 'PIL.Image.Image'>. Why is there this problem?
The detailed error information is as follows:
Traceback (most recent call last):
File "/home/u1120210216/zzq/ACE_plus/infer_lora.py", line 237, in
run()
File "/home/u1120210216/zzq/ACE_plus/infer_lora.py", line 233, in run
local_path, seed = run_one_case(pipe, **params)
File "/home/u1120210216/zzq/ACE_plus/infer_lora.py", line 64, in run_one_case
image, seed = pipe(
File "/home/u1120210216/miniconda3/envs/py39/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/u1120210216/zzq/ACE_plus/inference/ace_plus_diffusers.py", line 105, in call
image = self.pipe(
File "/home/u1120210216/miniconda3/envs/py39/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
File "/home/u1120210216/miniconda3/envs/py39/lib/python3.9/site-packages/diffusers/pipelines/flux/pipeline_flux_fill.py", line 868, in call
init_image = self.image_processor.preprocess(image, height=height, width=width)
File "/home/u1120210216/miniconda3/envs/py39/lib/python3.9/site-packages/diffusers/image_processor.py", line 678, in preprocess
raise ValueError(
ValueError: Input is in incorrect format. Currently, we only support <class 'PIL.Image.Image'>, <class 'numpy.ndarray'>, <class 'torch.Tensor'>