Dreambooth colab notebook doesn't work

[gimena8569]

I've been trying to use this colab notebook:

https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb

But I have this error when I execute the "Model Download" cell:

---

Detecting model version...

CalledProcessError Traceback (most recent call last)
in <cell line: 144>()
277 wget.download('https://github.com/TheLastBen/fast-stable-diffusion/raw/main/Dreambooth/det.py')
278 print('Detecting model version...')
--> 279 Custom_Model_Version=check_output('python det.py '+sftnsr+' --MODEL_PATH '+modelnm, shell=True).decode('utf-8').replace('\n', '')
280 clear_output()
281 print(''+Custom_Model_Version+' Detected')

1 frames
/usr/lib/python3.10/subprocess.py in run(input, capture_output, timeout, check, *popenargs, **kwargs)
524 retcode = process.poll()
525 if check and retcode:
--> 526 raise CalledProcessError(retcode, process.args,
527 output=stdout, stderr=stderr)
528 return CompletedProcess(process.args, retcode, stdout, stderr)

CalledProcessError: Command 'python det.py --MODEL_PATH model.ckpt' returned non-zero exit status 1.

---

The same error with any model. Please, help

[mdlieber99]

same error here

[wptm]

I've put these two lines at the very top of the code which seems to be working:
!pip uninstall wandb -y
!pip install wandb==0.15.12

[mdlieber99]

that worked! thanks wptm

[gimena8569]

I've put these two lines at the very top of the code which seems to be working: !pip uninstall wandb -y !pip install wandb==0.15.12

Thank you very much for replying. It worked!. In my case, I have added the code lines that you wrote before "Model Download" cell and the following code line before "Training cell".

!pip install --upgrade torch tensorboard

[wptm]

I'm putting these lines at the very top of the training too:
!pip uninstall protobuf -y
!pip install protobuf==3.20.3
!pip uninstall wandb -y
!pip install wandb==0.15.12

[vajayattila]

Hello,

I am encountering an issue when trying to load an existing model in the Dreambooth section of the notebook hosted at:

https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb

I am using Colab Pro with Python version 3.11.11. After inputting the name of my model in the "Create/Load a Session" parameter and pressing the play button, I receive the following error message:

Session found, loading the trained model ...
Detecting model version...

---------------------------------------------------------------------------

CalledProcessError                        Traceback (most recent call last)

<ipython-input-5-f883e597f758> in <cell line: 0>()
     99   wget.download('https://github.com/TheLastBen/fast-stable-diffusion/raw/main/Dreambooth/det.py')
    100   print('Detecting model version...')
--> 101   Model_Version=check_output('python det.py --MODEL_PATH '+MDLPTH, shell=True).decode('utf-8').replace('\n', '')
    102   clear_output()
    103   print(''+Model_Version+' Detected')

1 frames

/usr/lib/python3.11/subprocess.py in check_output(timeout, *popenargs, **kwargs)
    464         kwargs['input'] = empty
    465 
--> 466     return run(*popenargs, stdout=PIPE, timeout=timeout, check=True,
    467                **kwargs).stdout
    468 

/usr/lib/python3.11/subprocess.py in run(input, capture_output, timeout, check, *popenargs, **kwargs)
    569         retcode = process.poll()
    570         if check and retcode:
--> 571             raise CalledProcessError(retcode, process.args,
    572                                      output=stdout, stderr=stderr)
    573     return CompletedProcess(process.args, retcode, stdout, stderr)

CalledProcessError: Command 'python det.py --MODEL_PATH /content/gdrive/MyDrive/Fast-Dreambooth/Sessions/heFatRT/heFatRT.ckpt' returned non-zero exit status 1.

Could you please help me understand and resolve this issue? I would really appreciate any guidance or fixes you can provide.

Thank you very much for your support!

[TheLastBen]

fixed, use the latest notebook

[vajayattila]

Thank you. It is works now.