-
-
Notifications
You must be signed in to change notification settings - Fork 282
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
join() argument must be str, bytes, or os.PathLike object, not 'NoneType' #802
Comments
I had this same error. For me, uninstalling CUDA 11.3 and rebooting did the trick. |
currently running CUDA 12.0 but will give it a go to see if it helps. Uninstalled still same error. |
Same error happens to me. I just uninstall / reinstall CUDA 11.8, but it doesn't works. FYI:
|
this is a different error, you are experiencing an empty list error instead of nonetype error |
Having the exact same error |
Just had the same issue. Somehow I didn't have xformers installed. Seems to have resolved itself after relaunching the webui with -xformers |
Having the exact same error |
Tried again this morning did a git pull on the ui and the dreambooth extension and I receive the same error. Dreambooth revision: c2269b8 |
Same error. |
Same error. |
I'm getting a similar error : Got scheduler: <class 'diffusers.schedulers.scheduling_deis_multistep.DEISMultistepScheduler'> |
I am also getting the 'list' version of this error at the current version (commit 5075d48) when generating class images for lora training:
|
I think I found the problem (for the 'list' error): when generating a new model the default value for "lora_model_name" should be an empty string but for some reason it is an empty list. In helpers/image_builder.py, around line 135, this is a problem:
Now if you want to train a lora As a workaround I edited my model's db_config.json file (under |
This worked for me. Thanks! @Anonym271 |
Helped me too. Thanks a lot @Anonym271 |
For anyone coming here, my lora_model_name was already set to a string in the db_config.json file but I was still having this issue in the newest update that I installed via Automatic1111. This fixed it for me I think: Basically I had to redownload from here and then delete everything in my "extensions\sd_dreambooth_extension" folder and then copy the files into it from what I redownloaded manually. |
Thank you for helping me solve the problem.
Thank you for helping me solve the problem. |
Kindly read the entire form below and fill it out with the requested information.
Please find the following lines in the console and paste them below. If you do not provide this information, your
issue will be automatically closed.
`
Python revision: 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Dreambooth revision: c2269b8
SD-WebUI revision: d1ea518dea3d7584be2927cc486d15ec3e18ddb0
Checking Dreambooth requirements...
[+] bitsandbytes version 0.35.0 installed.
[+] diffusers version 0.10.2 installed.
[+] transformers version 4.25.1 installed.
[+] xformers version 0.0.14.dev0 installed.
[+] torch version 1.12.1+cu113 installed.
[+] torchvision version 0.13.1+cu113 installed.
`
Have you read the Readme?
yes
Have you completely restarted the stable-diffusion-webUI, not just reloaded the UI?
yes
Have you updated Dreambooth to the latest revision?
yes
Have you updated the Stable-Diffusion-WebUI to the latest version?
yes
No, really. Please save us both some trouble and update the SD-WebUI and Extension and restart before posting this.
Reply 'OK' Below to acknowledge that you did this.
Describe the bug
While Using LoRa the training fails
Provide logs
Traceback (most recent call last):
File "C:\AI\auto1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\scripts\dreambooth.py", line 561, in start_training
result = main(config, use_txt2img=use_txt2img)
File "C:\AI\auto1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\train_dreambooth.py", line 973, in main
return inner_loop()
File "C:\AI\auto1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\memory.py", line 116, in decorator
return function(batch_size, grad_size, prof, *args, **kwargs)
File "C:\AI\auto1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\train_dreambooth.py", line 294, in inner_loop
unet_lora_params, text_encoder_lora_params = apply_lora_weights(args.lora_model_name, unet, text_encoder,
File "C:\AI\auto1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\lora_diffusion\lora.py", line 150, in apply_lora_weights
lora_path = os.path.join(paths.models_path, "lora", lora_model)
File "C:\Users\wwans\AppData\Local\Programs\Python\Python310\lib\ntpath.py", line 143, in join
genericpath._check_arg_types('join', path, *paths)
File "C:\Users\wwans\AppData\Local\Programs\Python\Python310\lib\genericpath.py", line 152, in _check_arg_types
raise TypeError(f'{funcname}() argument must be str, bytes, or '
TypeError: join() argument must be str, bytes, or os.PathLike object, not 'NoneType'
Training completed, reloading SD Model.
Restored system models.
Returning result: Exception training model: 'join() argument must be str, bytes, or os.PathLike object, not 'NoneType''.
Environment
What OS?
Windows native
If Windows - WSL or native?
What GPU are you using?
rtx2060 max-Q
Screenshots/Config
If the issue is specific to an error while training, please provide a screenshot of training parameters or the
db_config.json file from /models/dreambooth/MODELNAME/db_config.json
The text was updated successfully, but these errors were encountered: