hunyuanvideo-community/HunyuanVideo · add sample_size to transformer/config.json which is required by recent versions of diffusers

Traceback (most recent call last):
  File "/workspace/hyvideo_sqs_worker.py", line 59, in <module>
    pipe = xFuserHunyuanDiTPipeline.from_pretrained(
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/xfuser/model_executor/pipelines/pipeline_hunyuandit.py", line 50, in from_pretrained
    pipeline = HunyuanDiTPipeline.from_pretrained(
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 1031, in from_pretrained
    model = pipeline_class(**init_kwargs)
            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/opt/conda/lib/python3.11/site-packages/diffusers/pipelines/hunyuandit/pipeline_hunyuandit.py", line 247, in __init__
    self.transformer.config.sample_size
AttributeError: 'FrozenDict' object has no attribute 'sample_size'