Qwen

/

Qwen-Image

like 2.33k

Follow

Qwen 63.9k

Hi, I'm trying to load the model using official demo. But I encountered the following problem:

Traceback (most recent call last):
  File "/home/zjn_data/Qwen-Image/test_image.py", line 14, in <module>
    pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype)
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
    return fn(*args, **kwargs)
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 1022, in from_pretrained
    loaded_sub_model = load_sub_model(
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/diffusers/pipelines/pipeline_loading_utils.py", line 846, in load_sub_model
    loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/transformers/modeling_utils.py", line 279, in _wrapper
    return func(*args, **kwargs)
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/transformers/modeling_utils.py", line 4342, in from_pretrained
    model = cls(config, *model_args, **model_kwargs)
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/transformers/models/qwen2_5_vl/modeling_qwen2_5_vl.py", line 1481, in __init__
    super().__init__(config)
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/transformers/modeling_utils.py", line 1884, in __init__
    self.generation_config = GenerationConfig.from_model_config(config) if self.can_generate() else None
  File "/home/zjnyly/miniconda3/envs/py310/lib/python3.10/site-packages/transformers/generation/configuration_utils.py", line 1290, in from_model_config
    decoder_config_dict = decoder_config.to_dict()
AttributeError: 'dict' object has no attribute 'to_dict'

The related pakages are:

diffusers                         0.35.0.dev0
torch                             2.5.1
torchaudio                        2.5.1
torchvision                       0.20.1
huggingface-hub                   0.34.3

It this a common problem? Thanks!