Qwen-Image Workflow From Templates: LOADClip Node: Confusing Error Containing "make sure you don't have a local directory with the same name"

[GeorgiaM-honestly]

Hello! Thank you for taking the time to read this.

I am trying to use the Qwen-Image workflow from templates. I downloaded the files as instructed (though i did deviate a bit: opting for fp16 where possible -- Something I have done without issue with other workflows). My setup DOES deviate from probably most, where I am running inside of a virtualenv. I want to keep the models etc on a separate filesystem (software raid1 for speed), so I have symlinks inside of the virtualenv pointing to where the files are. I have been doing this without issue for years and I doubt doing so is causing the issue I will describe.

When it is time to load the CLIP using the LOADClip node (titled "Load CLIP" in the workflow) I get the following error which I find confusing:

CLIPLoader
Can't load tokenizer for '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer'. 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 '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer' is the correct path to a directory containing all relevant files for a Qwen2Tokenizer tokenizer.

Let's go step by step:

/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders is a directory that exists. "qwen25_tokenizer" is not a directory or anything else that exists there, so I don't understand what is going on there.

I did get the models from huggingface.co .

make sure you don't have a local directory with the same name. Otherwise, make sure '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer' is the correct path to a directory containing all relevant files for a Qwen2Tokenizer tokenizer.

The above portion of the error is what confuses me the most. "make sure you don't have a local directory with the same name.". The same name as what? And why is it expecting "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer" as a path?

I mentioned earlier that i was trying the fp16 files wherever possible, including for the CLIP. So, I renamed the fp16 clip to something else, re-downloaded it, and compared the md5sum of the old and new file. They are the same. I then downloaded the fp8 file, pointed the LOADClip node at it, and I get exactly the same error.

I feel like I'm missing something obvious. My initial impression is that the wording of the error is a bit... strange. But it could be me too, or something i'm doing locally to screw it up.

SYSTEM & VERSIONS INFORMATION

• Intel(R) Core(TM) i7-7820X CPU @ 3.60GHz
• 128GB system ram
• NVIDIA GeForce RTX 4090 24GB
• Ubuntu Server Linux 24.04.3 LTS , updated a few days ago
• Nvidia Driver Version: 535.247.01
• CUDA Version: 12.2
• ComfyUI installation: virtualenv. Virtualenv Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
• ComfyUI version: 0.3.56
• ComfyUI frontend version: 1.25.11
• ComfyUI templates / workflows version: comfyui_workflow_templates-0.1.70

FULL COMFYUI STARTUP COMMAND AND OUTPUT AND ERROR

Start command: cd ~/virtualenvs/comfyui/ && . bin/activate && cd ~/virtualenvs/comfyui/ComfyUI && python main.py --use-sage-attention --disable-smart-memory --listen $(ifconfig eth1 | grep "inet " | awk '{print $2}')

Script started on 2025-08-31 02:16:01+00:00 [TERM="screen.xterm-256color" TTY="/dev/pts/1" COLUMNS="122" LINES="33"]
�[?2004h�[01;32mmyusername@ubuntu-server�[00m:�[01;34m~/virtualenvs/comfyui/ComfyUI�[00m$ exit�����[K�[7mcd ~/virtualenvs/comfyui/ && . bin/activate && cd /virtualenvs/comfy�[27m�[7mu�[27m�[7mi/ComfyUI && python main.py --use-sage-attention --disable-smart-memory --listen $(ifconfig eth1 | grep "inet " | awk '{p�[27m�[7mr�[27m�[7mint $2}')�[27m�[A�[A
�[01;32mmyusername@ubuntu-server�[00m:�[01;34m/virtualenvs/comfyui/ComfyUI�[00m$ cd ~/virtualenvs/comfyui/ && . bin/activate && cd ~/virtualenvs/comfyui/ComfyUI && python main.py --use-sage-attention --disable-smart-memory --listen $(ifconfig eth1 | grep "inet " | awk '{print $2}')
�[?2004l
[START] Security scan
�[2mUsing Python 3.12.3 environment at: /home/myusername/virtualenvs/comfyui�[0m
[DONE] Security scan

ComfyUI-Manager: installing dependencies done.

** ComfyUI startup time: 2025-08-31 02:16:11.793
** Platform: Linux
** Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
** Python executable: /home/myusername/virtualenvs/comfyui/bin/python
** ComfyUI Path: /home/myusername/virtualenvs/comfyui/ComfyUI
** ComfyUI Base Folder Path: /home/myusername/virtualenvs/comfyui/ComfyUI
** User directory: /home/myusername/virtualenvs/comfyui/ComfyUI/user
** ComfyUI-Manager config path: /home/myusername/virtualenvs/comfyui/ComfyUI/user/default/ComfyUI-Manager/config.ini
** Log path: /home/myusername/virtualenvs/comfyui/ComfyUI/user/comfyui.log
�[2mUsing Python 3.12.3 environment at: /home/myusername/virtualenvs/comfyui�[0m
�[2mUsing Python 3.12.3 environment at: /home/myusername/virtualenvs/comfyui�[0m

Prestartup times for custom nodes:
0.0 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/rgthree-comfy
0.4 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/comfyui-manager

Checkpoint files will always be loaded safely.
Total VRAM 24215 MB, total RAM 128511 MB
pytorch version: 2.9.0.dev20250719+cu129
Set vram state to: NORMAL_VRAM
Disabling smart memory management
Device: cuda:0 NVIDIA GeForce RTX 4090 : cudaMallocAsync
Using sage attention
Python version: 3.12.3 (main, Aug 14 2025, 17:47:21) [GCC 13.3.0]
ComfyUI version: 0.3.56
ComfyUI frontend version: 1.25.11
[Prompt Server] web root: /home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/comfyui_frontend_package/static

Loading: ComfyUI-Manager (V3.36)

[ComfyUI-Manager] network_mode: public

ComfyUI Revision: 3853 [4449e14] *DETACHED | Released on '2025-08-30'

[Crystools �[0;32mINFO�[0m] Crystools version: 1.27.3
[Crystools �[0;32mINFO�[0m] Platform release: 6.8.0-78-generic
[Crystools �[0;32mINFO�[0m] JETSON: Not detected.
[Crystools �[0;32mINFO�[0m] CPU: Intel(R) Core(TM) i7-7820X CPU @ 3.60GHz - Arch: x86_64 - OS: Linux 6.8.0-78-generic
[Crystools �[0;32mINFO�[0m] pynvml (NVIDIA) initialized.
[Crystools �[0;32mINFO�[0m] GPU/s:
[Crystools �[0;32mINFO�[0m] 0) NVIDIA GeForce RTX 4090
[Crystools �[0;32mINFO�[0m] NVIDIA Driver: 535.247.01
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/model-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/alter-list.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/extension-node-map.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/github-stats.json
[ComfyUI-Manager] default cache updated: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json

�[92m[rgthree-comfy] Loaded 48 fantastic nodes. 🎉�[0m

Import times for custom nodes:
0.0 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/websocket_image_save.py
0.0 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/ComfyUI-Custom-Scripts
0.1 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/ComfyUI-Crystools
0.1 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/comfyui-manager
0.4 seconds: /home/myusername/virtualenvs/comfyui/ComfyUI/custom_nodes/rgthree-comfy

Context impl SQLiteImpl.
Will assume non-transactional DDL.
No target revision found.
Starting server

To see the GUI go to: http://10.1.1.216:8188
FETCH ComfyRegistry Data: 5/96
FETCH ComfyRegistry Data: 10/96
FETCH ComfyRegistry Data: 15/96
FETCH ComfyRegistry Data: 20/96
FETCH ComfyRegistry Data: 25/96
FETCH ComfyRegistry Data: 30/96
FETCH ComfyRegistry Data: 35/96
FETCH ComfyRegistry Data: 40/96
FETCH ComfyRegistry Data: 45/96
FETCH ComfyRegistry Data: 50/96
FETCH ComfyRegistry Data: 55/96
FETCH ComfyRegistry Data: 60/96
FETCH ComfyRegistry Data: 65/96
FETCH ComfyRegistry Data: 70/96
FETCH ComfyRegistry Data: 75/96
FETCH ComfyRegistry Data: 80/96
FETCH ComfyRegistry Data: 85/96
FETCH ComfyRegistry Data: 90/96
FETCH ComfyRegistry Data: 95/96
FETCH ComfyRegistry Data [DONE]
[ComfyUI-Manager] default cache updated: https://api.comfy.org/nodes
FETCH DATA from: https://raw.githubusercontent.com/ltdrdata/ComfyUI-Manager/main/custom-node-list.json [DONE]
[ComfyUI-Manager] All startup tasks have been completed.
got prompt
Using pytorch attention in VAE
Using pytorch attention in VAE
VAE load device: cuda:0, offload device: cpu, dtype: torch.bfloat16
!!! Exception during processing !!! Can't load tokenizer for '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer'. 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 '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer' is the correct path to a directory containing all relevant files for a Qwen2Tokenizer tokenizer.
Traceback (most recent call last):
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/transformers/utils/hub.py", line 470, in cached_files
hf_hub_download(
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer'. Use repo_type argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1912, in from_pretrained
resolved_config_file = cached_file(
^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/transformers/utils/hub.py", line 312, in cached_file
file = cached_files(path_or_repo_id=path_or_repo_id, filenames=[filename], **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/transformers/utils/hub.py", line 523, in cached_files
_get_cache_file_to_return(path_or_repo_id, filename, cache_dir, revision) for filename in full_filenames
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/transformers/utils/hub.py", line 140, in _get_cache_file_to_return
resolved_file = try_to_load_from_cache(path_or_repo_id, full_filename, cache_dir=cache_dir, revision=revision)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 106, in _inner_fn
validate_repo_id(arg_value)
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py", line 154, in validate_repo_id
raise HFValidationError(
huggingface_hub.errors.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer'. Use repo_type argument if needed.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "/home/myusername/virtualenvs/comfyui/ComfyUI/execution.py", line 496, in execute
output_data, output_ui, has_subgraph, has_pending_tasks = await get_output_data(prompt_id, unique_id, obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/execution.py", line 315, in get_output_data
return_values = await _async_map_node_over_list(prompt_id, unique_id, obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb, hidden_inputs=hidden_inputs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/execution.py", line 289, in _async_map_node_over_list
await process_inputs(input_dict, i)
File "/home/myusername/virtualenvs/comfyui/ComfyUI/execution.py", line 277, in process_inputs
result = f(**inputs)
^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/nodes.py", line 948, in load_clip
clip = comfy.sd.load_clip(ckpt_paths=[clip_path], embedding_directory=folder_paths.get_folder_paths("embeddings"), clip_type=clip_type, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/sd.py", line 782, in load_clip
return load_text_encoder_state_dicts(clip_data, embedding_directory=embedding_directory, clip_type=clip_type, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/sd.py", line 988, in load_text_encoder_state_dicts
clip = CLIP(clip_target, embedding_directory=embedding_directory, parameters=parameters, tokenizer_data=tokenizer_data, model_options=model_options)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/sd.py", line 119, in init
self.tokenizer = tokenizer(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen_image.py", line 16, in init
super().init(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data, name="qwen25_7b", tokenizer=Qwen25_7BVLITokenizer)
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/sd1_clip.py", line 645, in init
setattr(self, self.clip, tokenizer(embedding_directory=embedding_directory, tokenizer_data=tokenizer_data))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen_image.py", line 11, in init
super().init(tokenizer_path, pad_with_end=False, embedding_size=3584, embedding_key='qwen25_7b', tokenizer_class=Qwen2Tokenizer, has_start_token=False, has_end_token=False, pad_to_max_length=False, max_length=99999999, min_length=1, pad_token=151643, tokenizer_data=tokenizer_data)
File "/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/sd1_clip.py", line 466, in init
self.tokenizer = tokenizer_class.from_pretrained(tokenizer_path, **tokenizer_args)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/myusername/virtualenvs/comfyui/lib/python3.12/site-packages/transformers/tokenization_utils_base.py", line 1932, in from_pretrained
raise OSError(
OSError: Can't load tokenizer for '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer'. 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 '/home/myusername/virtualenvs/comfyui/ComfyUI/comfy/text_encoders/qwen25_tokenizer' is the correct path to a directory containing all relevant files for a Qwen2Tokenizer tokenizer.

Prompt executed in 0.21 seconds
^C
Stopped server
�[?2004h(comfyui) �[01;32mmyusername@ubuntu-server�[00m:�[01;34m~/virtualenvs/comfyui/ComfyUI�[00m$ exit
�[?2004l