[Bug]: OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'openai/clip-vit-large-patch14' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer.

[ku-count]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

I can't deploy the environment or(can not install SD successful )

Steps to reproduce the problem

press webui-user.bat it's the first time to click this button.

What should have happened?

The deployment was successful and a URL like 127.0.0.1:7860 from the web tutorial popped up!!

Version or Commit where the problem happens

V1-5-pruned-emaonly.ckpt

What Python version are you running on ?

Python 3.10.x

What platforms do you use to access the UI ?

Windows

What device are you running WebUI on?

Nvidia GPUs (GTX 16 below)

Cross attention optimization

None

What browsers do you use to access the UI ?

Microsoft Edge

Command Line Arguments

git pull
@echo off

set PYTHON=
set GIT=
set VENV_DIR=
set COMMANDLINE_ARGS=--medvram

call webui.bat

List of extensions

i dont know what

Console logs

win11 22621.1928  22H2  / python 3.10.6 / git 2.41.0 64bit

:::::::::::error code::::::
--------------------------------------------------------------------------------------------------------------------------------------
venv "D:\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 98947d173e3f1667eba29c904f681047dea9de90
Installing requirements for Web UI
Launching Web UI with arguments: --medvram
Checkpoint model (7460a6fa).ckpt [7460a6fa] not found; loading fallback model.ckpt [7460a6fa]
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Traceback (most recent call last):
  File "D:\stable-diffusion-webui\launch.py", line 256, in <module>
    start()
  File "D:\stable-diffusion-webui\launch.py", line 251, in start
    webui.webui()
  File "D:\stable-diffusion-webui\webui.py", line 146, in webui
    initialize()
  File "D:\stable-diffusion-webui\webui.py", line 82, in initialize
    modules.sd_models.load_model()
  File "D:\stable-diffusion-webui\modules\sd_models.py", line 253, in load_model
    sd_model = instantiate_from_config(sd_config.model)
  File "D:\stable-diffusion-webui\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "D:\stable-diffusion-webui\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 461, in __init__
    self.instantiate_cond_stage(cond_stage_config)
  File "D:\stable-diffusion-webui\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 519, in instantiate_cond_stage
    model = instantiate_from_config(config)
  File "D:\stable-diffusion-webui\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
    return get_obj_from_str(config["target"])(**config.get("params", dict()))
  File "D:\stable-diffusion-webui\repositories\stable-diffusion\ldm\modules\encoders\modules.py", line 141, in __init__
    self.tokenizer = CLIPTokenizer.from_pretrained(version)
  File "D:\stable-diffusion-webui\venv\lib\site-packages\transformers\tokenization_utils_base.py", line 1768, in from_pretrained
    raise EnvironmentError(
OSError: Can't load tokenizer for 'openai/clip-vit-large-patch14'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure 'openai/clip-vit-large-patch14' is the correct path to a directory containing all relevant files for a CLIPTokenizer tokenizer.

---------------------------------------------Dividing Line ------------------------------------------
Cloning Stable Diffusion into D:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai...
Traceback (most recent call last):
  File "D:\stable-diffusion-webui\launch.py", line 38, in <module>
    main()
  File "D:\stable-diffusion-webui\launch.py", line 29, in main
    prepare_environment()
  File "D:\stable-diffusion-webui\modules\launch_utils.py", line 299, in prepare_environment
    git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash)
  File "D:\stable-diffusion-webui\modules\launch_utils.py", line 153, in git_clone
    run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}")
  File "D:\stable-diffusion-webui\modules\launch_utils.py", line 107, in run
    raise RuntimeError("\n".join(error_bits))
RuntimeError: Couldn't clone Stable Diffusion.
Command: "git" clone "https://github.com/Stability-AI/stablediffusion.git" "D:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai"
Error code: 128
stderr: Cloning into 'D:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai'...
error: 2485 bytes of body are still expected
fetch-pack: unexpected disconnect while reading sideband packet
fatal: early EOF
fatal: fetch-pack: invalid index-pack output
-------------------------------------------------------------------------------------------------------
the second time I run webui-user.bat and add the code: git pull  Error message for the second run

Additional information

No response

[ku-count]

the third time I run it by delete the code:git pull, only @echo off

set PYTHON= set GIT= set VENV_DIR= set COMMANDLINE_ARGS=--medvram

call webui.bat ---------------------------------------------------------------------diving line------------------------------------------------------------ venv "D:\stable-diffusion-webui\venv\Scripts\Python.exe" Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: v1.4.0 Commit hash: 394ffa7b0a7fff3ec484bcd084e673a8b301ccc8 Cloning Stable Diffusion into D:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai... Traceback (most recent call last): File "D:\stable-diffusion-webui\launch.py", line 38, in main() File "D:\stable-diffusion-webui\launch.py", line 29, in main prepare_environment() File "D:\stable-diffusion-webui\modules\launch_utils.py", line 299, in prepare_environment git_clone(stable_diffusion_repo, repo_dir('stable-diffusion-stability-ai'), "Stable Diffusion", stable_diffusion_commit_hash) File "D:\stable-diffusion-webui\modules\launch_utils.py", line 153, in git_clone run(f'"{git}" clone "{url}" "{dir}"', f"Cloning {name} into {dir}...", f"Couldn't clone {name}") File "D:\stable-diffusion-webui\modules\launch_utils.py", line 107, in run raise RuntimeError("\n".join(error_bits)) RuntimeError: Couldn't clone Stable Diffusion. Command: "git" clone "https://github.com/Stability-AI/stablediffusion.git" "D:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai" Error code: 128 stderr: Cloning into 'D:\stable-diffusion-webui\repositories\stable-diffusion-stability-ai'... error: 3323 bytes of body are still expected fetch-pack: unexpected disconnect while reading sideband packet fatal: early EOF fatal: fetch-pack: invalid index-pack output

[LeonZhao28]

download files from https://huggingface.co/openai/clip-vit-large-patch14/tree/main and put them into the directory stable-diffusion-webui/openai (create it if doesn't exist)

[ku-count]

download files from https://huggingface.co/openai/clip-vit-large-patch14/tree/main and put them into the directory stable-diffusion-webui/openai (create it if doesn't exist)

3Q i ll try

[starqiu]

download files from https://huggingface.co/openai/clip-vit-large-patch14/tree/main and put them into the directory stable-diffusion-webui/openai (create it if doesn't exist)

it works for me,3Q. don't put them on model directory~

[ku-count]

3QQQQQQQQQQQQQQQQQQQQ , IT WORKS ,OMG O(∩_∩)O

Lionel @.***> 于2023年6月29日周四 17:39写道：

download files from https://huggingface.co/openai/clip-vit-large-patch14/tree/main and put them into the directory stable-diffusion-webui/openai.

— Reply to this email directly, view it on GitHub https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/11507#issuecomment-1612718791, or unsubscribe https://github.com/notifications/unsubscribe-auth/BA5SC5PNLPKOVZLPIJBEBZLXNVEOLANCNFSM6AAAAAAZYDRF7Q . You are receiving this because you authored the thread.Message ID: @.***>

[JinghuaOriental]

download files from https://huggingface.co/openai/clip-vit-large-patch14/tree/main and put them into the directory stable-diffusion-webui/openai (create it if doesn't exist)

Thank you very much !!

[shihaiyang-world]

download all files from https://huggingface.co/openai/clip-vit-large-patch14/tree/main, all files! and mkdir -p stable-diffusion-webui/openai/clip-vit-large-patch14 and move its to stable-diffusion-webui/openai/clip-vit-large-patch14/ like it:

[serg06]

I solved it like this:

cd stable-diffusion-webui
mkdir openai
cd openai
git clone https://huggingface.co/openai/clip-vit-large-patch14

P.S. can we update the repo with this permanent fix?

[JinghuaOriental]

Thank you, I just saw that it means the file is lack and I need to download it, then put it to the specific path. Maybe we still need to update the file manually if the repository updated.

---Original--- From: @.> Date: Fri, Jan 19, 2024 13:27 PM To: @.>; Cc: "Yingjie @.@.>; Subject: Re: [AUTOMATIC1111/stable-diffusion-webui] [Bug]: OSError: Can't loadtokenizer for 'openai/clip-vit-large-patch14'. If you were trying to load itfrom 'https://huggingface.co/models', make sure you don't have a localdirectory with the same name. Otherwise, make sure'openai/clip-vit-large-patch14' is the correct path to a directory containingall relevant files for a CLIPTokenizer tokenizer. (Issue #11507)

I solved it like this: cd stable-diffusion-webui mkdir openai git clone https://huggingface.co/openai/clip-vit-large-patch14

P.S. can we update the repo with this permanent fix?

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you commented.Message ID: @.***>

[becausecurious]

if you started getting this error 1-2h ago when trying to run webui, it looks like https://huggingface.co/ is in maintenance, so that's why the download fails.

I don't see any estimate when it will be over, there is https://status.huggingface.co/ for the current status.

There is https://www.kaggle.com/datasets/ferruccioliu/openai-clip-vit-large-patch14 as an alternative for now.

[becausecurious]

huggingface is back, but the latency is huge - I suspect there is a large backlog of downloads.

[Jiatoka]

遇到这个问题都是中国人，直接用中文就好了。单纯就是被墙了，连不上huggingface，在windows上部署还好，起码能翻墙，linux才叫麻烦。

[jistan]

不能翻墙的可以从百度网盘下载，链接: https://pan.baidu.com/s/1EBptJ2v9inq9A5LEYFfBMg 提取码: dh2b

[Xi-Meng]

笑吐了，这个帖子

[Acommonlittlea]

所以到底放哪？有没有人能把完整路径放出来

[JinghuaOriental]

你运行webui.sh之后会生成一个stable-diffusion-webui文件夹，把openai这个文件夹放到stable-diffusion-webui文件夹下面就好了

所以到底放哪？有没有人能把完整路径放出来

[Acommonlittlea]

Windows怎么跑.sh？下WSL？

[JinghuaOriental]

Windows怎么跑.sh？下WSL？

windows下是跑bat文件吧，要用windows的安装方法，源文件也说了