magic-research / magic-animate

[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
https://showlab.github.io/magicanimate/
BSD 3-Clause "New" or "Revised" License
10.15k stars 1.03k forks source link

After launching, failed to run demo #98

Open vvip2u opened 7 months ago

vvip2u commented 7 months ago

image

logs

  File "E:\apps\magic-animate\demo\animate.py", line 157, in __call__
    sample = self.pipeline(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "E:\apps\magic-animate\magicanimate\pipelines\pipeline_animation.py", line 592, in __call__
    text_embeddings = self._encode_prompt(
  File "E:\apps\magic-animate\magicanimate\pipelines\pipeline_animation.py", line 187, in _encode_prompt
    text_inputs = self.tokenizer(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils_base.py", line 2602, in __call__
    encodings = self._call_one(text=text, text_pair=text_pair, **all_kwargs)
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils_base.py", line 2688, in _call_one
    return self.batch_encode_plus(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils_base.py", line 2879, in batch_encode_plus
    return self._batch_encode_plus(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils.py", line 744, in _batch_encode_plus
    batch_outputs = self._batch_prepare_for_model(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils.py", line 816, in _batch_prepare_for_model
    batch_outputs = self.pad(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils_base.py", line 3086, in pad
    outputs = self._pad(
  File "D:\ProgramData\anaconda3\envs\magic-animate-py\lib\site-packages\transformers\tokenization_utils_base.py", line 3450, in _pad
    encoded_inputs["attention_mask"] = encoded_inputs["attention_mask"] + [0] * difference
OverflowError: cannot fit 'int' into an index-sized integer
zsszyx commented 6 months ago

same question

Hubert2102 commented 6 months ago

+1

leoullas commented 6 months ago

Same issue

leoullas commented 6 months ago

image

barraland commented 3 months ago

I have exact same error with OMG repo. Any solution? I have latest version of transformers

johndpope commented 3 months ago

what's python version?