SD3 - data did not match any variant of untagged enum PyPreTokenizerTypeWrapper

[TEGNoV]

Describe the bug

Error while execution of demo code:

Traceback (most recent call last):
File "/Users/fp/Library/CloudStorage/OneDrive-Personal/1. Projekte/Code/Adobe StableDiffusion/mlx/mydiffusers.py", line 34, in
pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16 , use_auth_token="")
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 881, in from_pretrained
loaded_sub_model = load_sub_model(
^^^^^^^^^^^^^^^
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/diffusers/pipelines/pipeline_loading_utils.py", line 703, in load_sub_model
loaded_sub_model = load_method(os.path.join(cached_folder, name), **loading_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1825, in from_pretrained
return cls._from_pretrained(
^^^^^^^^^^^^^^^^^^^^^
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/transformers/tokenization_utils_base.py", line 1988, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/transformers/models/t5/tokenization_t5_fast.py", line 133, in init
super().init(
File "/Users/fp/.pyenv/versions/3.11.9/lib/python3.11/site-packages/transformers/tokenization_utils_fast.py", line 111, in init
fast_tokenizer = TokenizerFast.from_file(fast_tokenizer_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Exception: data did not match any variant of untagged enum PyPreTokenizerTypeWrapper at line 960 column 3

Reproduction

import torch
from diffusers import StableDiffusion3Pipeline

pipe = StableDiffusion3Pipeline.from_pretrained("stabilityai/stable-diffusion-3-medium-diffusers", torch_dtype=torch.float16 , use_auth_token="")
pipe = pipe.to("mps")

image = pipe(
"A cat holding a sign that says hello world",
negative_prompt="",
num_inference_steps=28,
guidance_scale=7.0,
).images[0]
image

Logs

No response

System Info

Latest source pull
Macbook M1 Pro

Who can help?

No response

[yiyixuxu]

hi can you try install /upgrade accelerate?

pip install --upgrade accelerate

[xingy038]

I have same problem.

[wenqsun]

Hello, I also have this problem, have you solved this issue?

[wenqsun]

I solved this problem by updating the transformers. Hope this helps you.
pip install transformers -U

[yiyixuxu]

what was your transformer version?

cc @sayakpaul here - we might need to pin a newer version for transformer

[wenqsun]

what was your transformer version?

cc @sayakpaul here - we might need to pin a newer version for transformer

@yiyixuxu I updated the transformers from 4.37.2 to 4.41.2, it may be related to the tokenizers package.

[sayakpaul]

Thanks for reporting and for the information. Could you try with the latest version of tokenizers?

[sayakpaul]

@yiyixuxu #8522

[TEGNoV]

Fixed by:

pip install --upgrade accelerate
pip install transformers -U
pip install git+https://github.com/huggingface/diffusers