returned non-zero exit status 1. Something went wrong

[wallatomic]

Hi, I'm trying this since yesterday an I got the same results:

subprocess.CalledProcessError: Command '['/usr/bin/python3', '/content/diffusers/examples/dreambooth/train_dreambooth.py', '--image_captions_filename', '--save_starting_step=500', '--save_n_steps=0', '--train_text_encoder', '--pretrained_model_name_or_path=/content/stable-diffusion-v1-5', '--instance_data_dir=/content/data/jsr2', '--output_dir=/content/models/jsr2', '--instance_prompt=', '--seed=96576', '--resolution=512', '--mixed_precision=no', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--use_8bit_adam', '--learning_rate=2e-6', '--lr_scheduler=polynomial', '--center_crop', '--lr_warmup_steps=0', '--max_train_steps=1000']' returned non-zero exit status 1. Something went wrong

[wallatomic]

Traceback (most recent call last): File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 694, in main() File "/content/diffusers/examples/dreambooth/train_dreambooth.py", line 439, 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 137, in validate_repo_id "Repo id must be in the form 'repo_name' or 'namespace/repo_name':" huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/content/stable-diffusion-v1-5'. Use repo_type argument if needed. Traceback (most recent call last): File "/usr/local/bin/accelerate", line 8, in 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 837, in launch_command simple_launcher(args) File "/usr/local/lib/python3.7/dist-packages/accelerate/commands/launch.py", line 354, in simple_launcher raise subprocess.CalledProcessError(returncode=process.returncode, cmd=cmd) subprocess.CalledProcessError: Command '['/usr/bin/python3', '/content/diffusers/examples/dreambooth/train_dreambooth.py', '--image_captions_filename', '--save_starting_step=500', '--save_n_steps=0', '--train_text_encoder', '--pretrained_model_name_or_path=/content/stable-diffusion-v1-5', '--instance_data_dir=/content/data/jsr2', '--output_dir=/content/models/jsr2', '--instance_prompt=', '--seed=96576', '--resolution=512', '--mixed_precision=no', '--train_batch_size=1', '--gradient_accumulation_steps=1', '--use_8bit_adam', '--learning_rate=2e-6', '--lr_scheduler=polynomial', '--center_crop', '--lr_warmup_steps=0', '--max_train_steps=1000']' returned non-zero exit status 1. Something went wrong

[TheLastBen]

Did you accept the terms at https://huggingface.co/runwayml/stable-diffusion-v1-5 ?

[wallatomic]

yes

[TheLastBen]

make sure there is a folder "stable-diffusion-v1-5" in the colab file explorer

[wallatomic]

there is not. Do I have to create it manually? I have to put the model inside? I tried the same notebook yesterday and it worked. this changed?

[TheLastBen]

when you put your huggingface token in the "download model" cell and run it, it should download the model, you don't have to do it manually, did you run the cell ?

[wallatomic]

yes, i followed all the steps

[TheLastBen]

there should be a model folder, try a clean run

[TheLastBen]

and make sure you use the latest colab notebook

[wallatomic]

How can I check if it is the latest? The link is not the same? https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb

[TheLastBen]

yes that is the link, just avoid saving the notebook to your gdrive, or regularly use the one from the link

[wallatomic]

Ok, yes, it seems I was using an outdated notebook. I'm trying it now and I see that the folder with the images doesn't appear anymore under "data". it is me, or it changed? Where are the images now?

[TheLastBen]

Yes, everything is moved to your gdrive to allow resuming training easily after disconnecting from a session, look in the folder "Fast-Dreambooth" in your gdrive.

[wallatomic]

Excellent! Thank you Ben! I really appreciate it ☕😉

[TheLastBen]

happy to help