assert False in log_validation()

[AndreiBaraian]

Hi! I am trying to run your code and although the training works alright, I stumble on an error in log_validation() function, where inference is done on the validation images. Specifically, the line with image = pipeline(val_prompt, val_labelTrain_onehot, num_inference_steps=20, generator=generator).images[0] triggers the following error:
Traceback (most recent call last):
File "/path/to/DGInStyle/test.py", line 70, in
image = pipeline(
File "/path/to//miniconda3/envs/dginstyle/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/path/to/miniconda3/envs/dginstyle/lib/python3.9/site-packages/diffusers/pipelines/controlnet/pipeline_controlnet.py", line 854, in call
self.check_inputs(
File "/path/to/miniconda3/envs/dginstyle/lib/python3.9/site-packages/diffusers/pipelines/controlnet/pipeline_controlnet.py", line 561, in check_inputs
assert False

I've tried debuggin it, but I cannot see if it's a problem with the input image or because it's failing the isinstanceof(ControlNet). Do you have any idea on what could cause this?