HFValidationError( '.ggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'CompVis/stable-diffusion-v1-4

[Renaldas111]

Tried to install Dreambooth according to Nerdy Rodent video (https://www.youtube.com/watch?v=w6PTviOCYQY)

I am absolutely new to Linux, and failed on last step running the training.
As I understood, something wrong with:
export MODEL_NAME="CompVis/stable-diffusion-v1-4" and --pretrained_model_name_or_path=$MODEL_NAME

Traceback (most recent call last):
File "/home/renaldas/github/diffusers/examples/dreambooth/train_dreambooth.py", line 657, in
main()
File "/home/renaldas/github/diffusers/examples/dreambooth/train_dreambooth.py", line 420, in main
tokenizer = CLIPTokenizer.from_pretrained(
File "/home/renaldas/anaconda3/envs/sd/lib/python3.9/site-packages/transformers/tokenization_utils_base.py", line 1734, in from_pretrained
resolved_vocab_files[file_id] = cached_file(
File "/home/renaldas/anaconda3/envs/sd/lib/python3.9/site-packages/transformers/utils/hub.py", line 408, in cached_file
resolved_file = hf_hub_download(
File "/home/renaldas/anaconda3/envs/sd/lib/python3.9/site-packages/huggingface_hub/file_download.py", line 1022, in hf_hub_download
cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type)
File "/home/renaldas/anaconda3/envs/sd/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 92, in _inner_fn
validate_repo_id(arg_value)
File "/home/renaldas/anaconda3/envs/sd/lib/python3.9/site-packages/huggingface_hub/utils/_validators.py", line 142, in validate_repo_id
raise HFValidationError(
'.ggingface_hub.utils.validators.HFValidationError: Repo id must use alphanumeric chars or '-', '', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'CompVis/stable-diffusion-v1-4

[patrickvonplaten]

Hey @Renaldas111,

Could you maybe add a reproducible code snippet here?
At the moment, I can only guess what code you have run 😅

Thank you :-)

[IT8055]

I dont belive its a code issue. I was facing the same issue and was due to the notepadd++ being configured for windows end of line conversion and not unix so was adding hidden characters to the .sh file. Once changed Notepadd to Unix (Edit - EOL - Unix) and saved the file it worked.

[2feet6inches]

I had the same problem.

%env MODEL_NAME="CompVis/stable-diffusion-v1-4"
%env INSTANCE_DIR="./input"
%env OUTPUT_DIR="./output"

!accelerate launch train_dreambooth.py \
  --pretrained_model_name_or_path=$MODEL_NAME  \
  --instance_data_dir=$INSTANCE_DIR \
  --output_dir=$OUTPUT_DIR \
  --instance_prompt="a photo of sks kitchen" \
  --resolution=512 \
  --train_batch_size=1 \
  --gradient_accumulation_steps=1 \
  --learning_rate=5e-6 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --max_train_steps=400

env: MODEL_NAME="CompVis/stable-diffusion-v1-4"
env: INSTANCE_DIR="./input"
env: OUTPUT_DIR="./output"
The following values were not passed to `accelerate launch` and had defaults used instead:
	`--num_cpu_threads_per_process` was set to `6` to improve out-of-box performance
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Traceback (most recent call last):
  File "train_dreambooth.py", line 592, in <module>
    main()
  File "train_dreambooth.py", line 381, in main
    tokenizer = CLIPTokenizer.from_pretrained(args.pretrained_model_name_or_path, subfolder="tokenizer")
  File "/usr/local/lib/python3.7/dist-packages/transformers/tokenization_utils_base.py", line 1748, in from_pretrained
    _commit_hash=commit_hash,
  File "/usr/local/lib/python3.7/dist-packages/transformers/utils/hub.py", line 420, in cached_file
    local_files_only=local_files_only,
  File "/usr/local/lib/python3.7/dist-packages/huggingface_hub/file_download.py", line 1022, in hf_hub_download
    cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type)
  File "/usr/local/lib/python3.7/dist-packages/huggingface_hub/utils/_validators.py", line 92, in _inner_fn
    validate_repo_id(arg_value)
  File "/usr/local/lib/python3.7/dist-packages/huggingface_hub/utils/_validators.py", line 143, in validate_repo_id
    "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"
huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: '"CompVis/stable-diffusion-v1-4"'.
Traceback (most recent call last):
  File "/usr/local/bin/accelerate", line 8, in <module>
    sys.exit(main())
  File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/accelerate_cli.py", line 43, in main
    args.func(args)
  File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/launch.py", line 910, in launch_command
    simple_launcher(args)
  File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/launch.py", line 400, in simple_launcher
    raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/usr/bin/python3', 'train_dreambooth.py', '--pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4"', '--instance_data_dir="./input"', '--output_dir="./output"', '--instance_prompt=a photo of sks kitchen', '--resolution=512', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--learning_rate=5e-6', '--lr_scheduler=constant', '--lr_warmup_steps=0', '--max_train_steps=400']' returned non-zero exit status 1.

[2feet6inches]

There is no problem if you specify it directly.

%env INSTANCE_DIR="./input"
%env OUTPUT_DIR="./output"

!accelerate launch train_dreambooth.py \
  --pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4"  \
  --instance_data_dir=$INSTANCE_DIR \
  --output_dir=$OUTPUT_DIR \
  --instance_prompt="a photo of sks kitchen" \
  --resolution=512 \
  --train_batch_size=1 \
  --gradient_accumulation_steps=1 \
  --learning_rate=5e-6 \
  --lr_scheduler="constant" \
  --lr_warmup_steps=0 \
  --max_train_steps=400

[patrickvonplaten]

cc @patil-suraj here as well

[patil-suraj]

I couldn't reproduce this, providing model name as env variable works fine for me.

[Klaudioz]

I just got that issue .. few hours ago I didn't have any issues running this command:

sudo docker run -it --gpus=all --ipc=host -v $(pwd):/root -e HUGGING_FACE_HUB_TOKEN=$TOKEN smy20011/dreambooth:latest accelerate launch /train_dreambooth.py   --pretrained_model_name_or_path=$MODEL_NAME   --instance_data_dir=$INSTANCE_DIR  --class_data_dir=$CLASS_DIR   --output_dir=$OUTPUT_DIR   --with_prior_preservation --prior_loss_weight=1.0   --instance_prompt="a portrait of sks woman"   --class_prompt="a portrait of woman"   --resolution=512   --center_crop   --train_batch_size=1   --mixed_precision="fp16"   --use_8bit_adam   --gradient_accumulation_steps=1 --gradient_checkpointing   --learning_rate=5e-6   --lr_scheduler="constant"   --lr_warmup_steps=0   --num_class_images=100   --sample_batch_size=4   --max_train_steps=800
The following values were not passed to `accelerate launch` and had defaults used instead:
        `--num_processes` was set to a value of `1`
        `--num_machines` was set to a value of `1`
        `--mixed_precision` was set to a value of `'no'`
        `--num_cpu_threads_per_process` was set to `3` to improve out-of-box performance
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
Traceback (most recent call last):
  File "/opt/conda/lib/python3.7/site-packages/diffusers/configuration_utils.py", line 234, in get_config_dict
    revision=revision,
  File "/opt/conda/lib/python3.7/site-packages/huggingface_hub/file_download.py", line 1022, in hf_hub_download
    cache_dir, repo_folder_name(repo_id=repo_id, repo_type=repo_type)
  File "/opt/conda/lib/python3.7/site-packages/huggingface_hub/utils/_validators.py", line 92, in _inner_fn
    validate_repo_id(arg_value)
  File "/opt/conda/lib/python3.7/site-packages/huggingface_hub/utils/_validators.py", line 143, in validate_repo_id
    "Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are"
huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: ''.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/train_dreambooth.py", line 695, in <module>
    main()
  File "/train_dreambooth.py", line 376, in main
    args.pretrained_model_name_or_path, torch_dtype=torch_dtype, use_auth_token=True
  File "/opt/conda/lib/python3.7/site-packages/diffusers/pipeline_utils.py", line 372, in from_pretrained
    revision=revision,
  File "/opt/conda/lib/python3.7/site-packages/diffusers/configuration_utils.py", line 261, in get_config_dict
    f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load this model, couldn't find it"
OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like  is not the path to a directory containing a model_index.json file.
Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.
Traceback (most recent call last):
  File "/opt/conda/bin/accelerate", line 8, in <module>
    sys.exit(main())
  File "/opt/conda/lib/python3.7/site-packages/accelerate/commands/accelerate_cli.py", line 43, in main
    args.func(args)
  File "/opt/conda/lib/python3.7/site-packages/accelerate/commands/launch.py", line 837, in launch_command
    simple_launcher(args)
  File "/opt/conda/lib/python3.7/site-packages/accelerate/commands/launch.py", line 354, in simple_launcher
    raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd)
subprocess.CalledProcessError: Command '['/opt/conda/bin/python', '/train_dreambooth.py', '--pretrained_model_name_or_path=', '--instance_data_dir=', '--class_data_dir=', '--output_dir=', '--with_prior_preservation', '--prior_loss_weight=1.0', '--instance_prompt=a portrait of sks woman', '--class_prompt=a portrait of woman', '--resolution=512', '--center_crop', '--train_batch_size=1', '--mixed_precision=fp16', '--use_8bit_adam', '--gradient_accumulation_steps=1', '--gradient_checkpointing', '--learning_rate=5e-6', '--lr_scheduler=constant', '--lr_warmup_steps=0', '--num_class_images=100', '--sample_batch_size=4', '--max_train_steps=800']' returned non-zero exit status 1.

I don't know if huggingface is having issues right now

[patrickvonplaten]

Could you try upgrading the huggingface_hub library?:

pip install --upgrade huggingface_hub

[github-actions]

This issue has been automatically marked as stale because it has not had recent activity. If you think this still needs to be addressed please comment on this thread.

Please note that issues that do not follow the contributing guidelines are likely to be ignored.

[Ali-Hasan-Khan]

Hey guys! I found a solution(at least for me) to this problem, the issue is caused by the "$" symbol when giving MODEL_NAME (and other env variables). It's working for me if you directly pass the string paths as argument to the 'accelerate launch' command for example:

!accelerate launch train_custom_diffusion.py \ --pretrained_model_name_or_path="CompVis/stable-diffusion-v1-4" \ --instance_data_dir="./data/cat" \ --output_dir="/content" \ --class_data_dir=./real_reg/samples_cat/ \ --with_prior_preservation --prior_loss_weight=1.0 \ --class_prompt="cat" --num_class_images=200 \ --instance_prompt="photo of a <new1> cat" \ --resolution=512 \ --train_batch_size=2 \ --learning_rate=1e-5 \ --lr_warmup_steps=0 \ --max_train_steps=250 \ --scale_lr --hflip \ --modifier_token "<new1>" --class_data_dir=./real_reg/samples_cat/ --with_prior_preservation --prior_loss_weight=1.0 --class_prompt="cat" --num_class_images=200 --instance_prompt="photo of a cat" --resolution=512 --train_batch_size=2 --learning_rate=1e-5 --lr_warmup_steps=0 --max_train_steps=250 --scale_lr --hflip \ --modifier_token "<new1>"