Flux.1-dev access denied

[Anothergazz]

I'm trying to generate a Lora with OneTrainer installed via Stability Matrix. But every time I start Training. I get the following error

Cannot access gated repo for url https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/0ef5fff789c832c5c7f4e127f94c8b54bbcced44/model_index.json.
Access to model black-forest-labs/FLUX.1-dev is restricted. You must have access to it and be authenticated to access it. Please log in.

Yes I have a HF account and I'm logged in when I run Onetrainer. I even generated a HF token but I have no idea how to use it with OneTrainer. What am I missing?

[Lolzen]

export HF_TOKEN=<YOUR READ TOKEN>

https://huggingface.co/docs/text-generation-inference/basic_tutorials/gated_model_access

[Lolzen]

you may add that to your .bashrc if you want it permanent.

if access is still restricted, go to the HF repo for FLUX and accept the terms & conditions.

[Anothergazz]

Thanks for your help, but I'm afraid you will have to dumb it in down for me. I should have mentioned I'm using windows, (is .bashrd linux only ?) I already have the token but I don't know how get OneTrainer to use it.

[Anothergazz]

Im adding the full print out when I run the training, Hopefully it will help

Clearing cache directory workspace-cache/run! You can disable this if you want to continue using the same cache.
TensorFlow installation not found - running with reduced feature set.
Fetching 16 files: 0%| | 0/16 [00:00<?, ?it/s]
Serving TensorBoard on localhost; to expose to the network, use a proxy or pass --bind_all
TensorBoard 2.17.0 at http://localhost:6006/ (Press CTRL+C to quit)
Traceback (most recent call last):
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 223, in load
self.__load_internal(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 42, in __load_internal
raise Exception("not an internal model")
Exception: not an internal model

Traceback (most recent call last):
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 232, in load
self.__load_diffusers(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 55, in __load_diffusers
tokenizer_1 = CLIPTokenizer.from_pretrained(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\transformers\tokenization_utils_base.py", line 2053, in from_pretrained
raise ValueError(
ValueError: Calling CLIPTokenizer.from_pretrained() with the path to a single file or url is not supported for this tokenizer. Use a model identifier or the path to a directory instead.

Traceback (most recent call last):
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\utils_errors.py", line 304, in hf_raise_for_status
response.raise_for_status()
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\requests\models.py", line 1024, in raise_for_status
raise HTTPError(http_error_msg, response=self)
requests.exceptions.HTTPError: 401 Client Error: Unauthorized for url: https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/0ef5fff789c832c5c7f4e127f94c8b54bbcced44/model_index.json

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 241, in load
self.__load_safetensors(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 153, in __load_safetensors
pipeline = FluxPipeline.from_single_file(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\src\diffusers\src\diffusers\loaders\single_file.py", line 403, in from_single_file
cached_model_config_path = _download_diffusers_model_config_from_hub(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\src\diffusers\src\diffusers\loaders\single_file.py", line 249, in _download_diffusers_model_config_from_hub
cached_model_path = snapshot_download(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub_snapshot_download.py", line 294, in snapshot_download
thread_map(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\tqdm\contrib\concurrent.py", line 69, in thread_map
return _executor_map(ThreadPoolExecutor, fn, *iterables, **tqdm_kwargs)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\tqdm\contrib\concurrent.py", line 51, in _executor_map
return list(tqdm_class(ex.map(fn, *iterables, chunksize=chunksize), **kwargs))
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\tqdm\std.py", line 1181, in iter
for obj in iterable:
File "concurrent\futures_base.py", line 621, in result_iterator
File "concurrent\futures_base.py", line 319, in _result_or_cancel
File "concurrent\futures_base.py", line 458, in result
File "concurrent\futures_base.py", line 403, in __get_result
File "concurrent\futures\thread.py", line 58, in run
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub_snapshot_download.py", line 268, in _inner_hf_hub_download
return hf_hub_download(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 1221, in hf_hub_download
return _hf_hub_download_to_cache_dir(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 1325, in _hf_hub_download_to_cache_dir
_raise_on_head_call_error(head_call_error, force_download, local_files_only)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 1823, in _raise_on_head_call_error
raise head_call_error
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 1722, in _get_metadata_or_catch_error
metadata = get_hf_file_metadata(url=url, proxies=proxies, timeout=etag_timeout, headers=headers)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\utils_validators.py", line 114, in _inner_fn
return fn(*args, **kwargs)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 1645, in get_hf_file_metadata
r = _request_wrapper(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 372, in _request_wrapper
response = _request_wrapper(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\file_download.py", line 396, in _request_wrapper
hf_raise_for_status(response)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\venv\lib\site-packages\huggingface_hub\utils_errors.py", line 321, in hf_raise_for_status
raise GatedRepoError(message, response) from e
huggingface_hub.utils._errors.GatedRepoError: 401 Client Error. (Request ID: Root=1-67038806-54f423326ee97cf32d03bb59;90e1f520-16b2-4770-bcca-5646cacee26d)

Cannot access gated repo for url https://huggingface.co/black-forest-labs/FLUX.1-dev/resolve/0ef5fff789c832c5c7f4e127f94c8b54bbcced44/model_index.json.
Access to model black-forest-labs/FLUX.1-dev is restricted. You must have access to it and be authenticated to access it. Please log in.

Traceback (most recent call last):
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\ui\TrainUI.py", line 552, in __training_thread_function
trainer.start()
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\trainer\GenericTrainer.py", line 122, in start
self.model = self.model_loader.load(
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\FluxLoRAModelLoader.py", line 46, in load
base_model_loader.load(model, model_type, model_names, weight_dtypes)
File "C:\AI\Stability Matrix\Data\Packages\OneTrainer\modules\modelLoader\flux\FluxModelLoader.py", line 261, in load
raise Exception("could not load model: " + model_names.base_model)
Exception: could not load model: C:/AI/Stability Matrix/Data/Models/StableDiffusion/FluxAI/flux1_dev.safetensors

[Calamdor]

activate the venv
run huggingface-cli login
insert your token.

[Anothergazz]

Thanks for the suggestion, unfortunately Stability Matrix is a program that manages and runs OneTrainer, so all the venv etc is out of my control.
I have also posted this in the StabiltyMatrix discussions,

[Calamdor]

Then you have to clone the HF repo manually using the instructions on the HF repo page and use the directory in OneTrainer

[Lolzen]

I'm not familiar with StabilityMatrix unfortunately, but guessing everything it does is local on your machine, you can try this to set your HF token:

https://www.computerhope.com/issues/ch000549.htm

in your case put HF_TOKEN under "Variable" and your actual token string under "value"

[Anothergazz]

Thank you Lolzen. I was a bit sceptical about adding the token to the environment variables, but it seems to have made a difference. No longer getting "unauthorized" complaints about HF. Still not working but that's a problem for another day

[Lolzen]

did you visit https://huggingface.co/black-forest-labs/FLUX.1-dev and accept the term & conditions?