huggingface/autotrain-advanced

[BUG]i cannot train loras with this

Closed this issue · 1 comments

Prerequisites

  • I have read the documentation.
  • I have checked other issues for similar problems.

Backend

Local

Interface Used

CLI

CLI Command

No response

UI Screenshots & Parameters

No response

Error Logs

File "/usr/local/lib/python3.10/dist-packages/autotrain/trainers/common.py", line 212, in wrapper
return func(*args, **kwargs)
File "/usr/local/lib/python3.10/dist-packages/autotrain/trainers/dreambooth/main.py", line 122, in train
main(_args)
File "/usr/local/lib/python3.10/dist-packages/autotrain/trainers/dreambooth/train_xl.py", line 798, in main
train_dataset = DreamBoothDataset(
File "/usr/local/lib/python3.10/dist-packages/autotrain/trainers/dreambooth/train_xl.py", line 184, in init
raise ValueError("Instance images root doesn't exists.")
ValueError: Instance images root doesn't exists

Additional Information

so when cached download error was cming then i commented that part but now this is coming

autotrain doesnt support dreambooth anymore. to train loras please use: https://huggingface.co/spaces/autotrain-projects/train-flux-lora-ease