join() argument must be str, bytes, or os.PathLike object, not 'NoneType' #802

ricoty · 2023-01-19T15:24:39Z

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:

Tsubashi · 2023-01-19T17:29:51Z

I had this same error. For me, uninstalling CUDA 11.3 and rebooting did the trick.

ricoty · 2023-01-19T18:05:27Z

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.

art-phony · 2023-01-19T18:31:09Z

Same error happens to me. I just uninstall / reinstall CUDA 11.8, but it doesn't works.

FYI:

Initializing Dreambooth
If submitting an issue on github, please provide the below text for debugging purposes:

Python revision: 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Dreambooth revision: c2269b8585d994efa31c6582fc19a890253c804e
SD-WebUI revision: b165e341e70300f66c8a77b9383041f4147b24a8

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 1.13.1+cu117 installed.
[+] torchvision version 0.14.1+cu117 installed.

Starting Dreambooth training...
Initializing dreambooth training...
Replace CrossAttention.forward to use xformers
Instance Bucket 0: Resolution (768, 768), Count: 80
Class Bucket 0: Resolution (768, 768), Count: 332
Target Bucket 0: Resolution (768, 768), Count: 0
We need a total of 0 images.
Nothing to generate.
Traceback (most recent call last):
  File "E:\AI_Drawing\automatic1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\scripts\dreambooth.py", line 561, in start_training
    result = main(config, use_txt2img=use_txt2img)
  File "E:\AI_Drawing\automatic1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\train_dreambooth.py", line 973, in main
    return inner_loop()
  File "E:\AI_Drawing\automatic1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\memory.py", line 116, in decorator
    return function(batch_size, grad_size, prof, *args, **kwargs)
  File "E:\AI_Drawing\automatic1111\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 "E:\AI_Drawing\automatic1111\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\osuwa\AppData\Local\Programs\Python\Python310\lib\ntpath.py", line 143, in join
    genericpath._check_arg_types('join', path, *paths)
  File "C:\Users\osuwa\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 'list'
Training completed, reloading SD Model.
Restored system models.
Returning result: Exception training model: 'join() argument must be str, bytes, or os.PathLike object, not 'list''.

ricoty · 2023-01-19T23:16:29Z

Same error happens to me. I just uninstall / reinstall CUDA 11.8, but it doesn't works.

FYI:

Initializing Dreambooth
If submitting an issue on github, please provide the below text for debugging purposes:

Python revision: 3.10.9 (tags/v3.10.9:1dd9be6, Dec  6 2022, 20:01:21) [MSC v.1934 64 bit (AMD64)]
Dreambooth revision: c2269b8585d994efa31c6582fc19a890253c804e
SD-WebUI revision: b165e341e70300f66c8a77b9383041f4147b24a8

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 1.13.1+cu117 installed.
[+] torchvision version 0.14.1+cu117 installed.

Starting Dreambooth training...
Initializing dreambooth training...
Replace CrossAttention.forward to use xformers
Instance Bucket 0: Resolution (768, 768), Count: 80
Class Bucket 0: Resolution (768, 768), Count: 332
Target Bucket 0: Resolution (768, 768), Count: 0
We need a total of 0 images.
Nothing to generate.
Traceback (most recent call last):
  File "E:\AI_Drawing\automatic1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\scripts\dreambooth.py", line 561, in start_training
    result = main(config, use_txt2img=use_txt2img)
  File "E:\AI_Drawing\automatic1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\train_dreambooth.py", line 973, in main
    return inner_loop()
  File "E:\AI_Drawing\automatic1111\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\memory.py", line 116, in decorator
    return function(batch_size, grad_size, prof, *args, **kwargs)
  File "E:\AI_Drawing\automatic1111\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 "E:\AI_Drawing\automatic1111\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\osuwa\AppData\Local\Programs\Python\Python310\lib\ntpath.py", line 143, in join
    genericpath._check_arg_types('join', path, *paths)
  File "C:\Users\osuwa\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 'list'
Training completed, reloading SD Model.
Restored system models.
Returning result: Exception training model: 'join() argument must be str, bytes, or os.PathLike object, not 'list''.

this is a different error, you are experiencing an empty list error instead of nonetype error
"TypeError: join() argument must be str, bytes, or os.PathLike object, not 'list'"
"TypeError: join() argument must be str, bytes, or os.PathLike object, not 'NoneType'"

john-cianfarani · 2023-01-20T01:31:01Z

Having the exact same error

nathan-kennedy · 2023-01-20T03:14:45Z

Just had the same issue. Somehow I didn't have xformers installed. Seems to have resolved itself after relaunching the webui with -xformers

ddzbs · 2023-01-20T08:10:14Z

Having the exact same error

john-cianfarani · 2023-01-20T14:38:26Z

Tried again this morning did a git pull on the ui and the dreambooth extension and I receive the same error.

Dreambooth revision: c2269b8
SD-WebUI revision: e33cace2c2074ef342d027c1f31ffc4b3c3e877e

Jc7out · 2023-01-25T18:15:09Z

Same error.

fipil · 2023-03-01T19:18:03Z

Same error.
Dreambooth rev d4e2f7d

SoundGuy · 2023-03-02T23:17:18Z

I'm getting a similar error :

Got scheduler: <class 'diffusers.schedulers.scheduling_deis_multistep.DEISMultistepScheduler'>
Traceback (most recent call last):
File "G:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\ui_functions.py", line 555, in start_training
result = main(use_txt2img=use_txt2img)
File "G:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\train_dreambooth.py", line 1133, in main
return inner_loop()
File "G:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\memory.py", line 123, in decorator
return function(batch_size, grad_size, prof, *args, **kwargs)
File "G:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\train_dreambooth.py", line 198, in inner_loop
count, instance_prompts, class_prompts = generate_classifiers(args, use_txt2img=use_txt2img,
File "G:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\utils\gen_utils.py", line 134, in generate_classifiers
builder = ImageBuilder(
File "G:\stable-diffusion-webui\extensions\sd_dreambooth_extension\helpers\image_builder.py", line 126, in init
lora_model_path = os.path.join(shared.models_path, "lora", lora_model)
File "C:\Users\art2\AppData\Local\Programs\Python\Python310\lib\ntpath.py", line 143, in join
genericpath._check_arg_types('join', path, *paths)
File "C:\Users\art2\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 'list'

Anonym271 · 2023-03-04T13:20:13Z

I am also getting the 'list' version of this error at the current version (commit 5075d48) when generating class images for lora training:

Generating class images 0/492::   0%|                                                          | 0/492 [00:00<?, ?it/s]Using scheduler: DEISMultistep
Traceback (most recent call last):
  File "F:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\ui_functions.py", line 760, in ui_classifiers
    count, images = generate_classifiers(config, use_txt2img=use_txt2img, ui=True)
  File "F:\stable-diffusion-webui\extensions\sd_dreambooth_extension\dreambooth\utils\gen_utils.py", line 134, in generate_classifiers
    builder = ImageBuilder(
  File "F:\stable-diffusion-webui\extensions\sd_dreambooth_extension\helpers\image_builder.py", line 136, in __init__
    lora_model_path = os.path.join(shared.models_path, "lora", lora_model)
  File "C:\Users\xy\AppData\Local\Programs\Python\Python310\lib\ntpath.py", line 117, in join
    genericpath._check_arg_types('join', path, *paths)
  File "C:\Users\xy\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 'list'

Anonym271 · 2023-03-04T13:53:29Z

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:

            if config.use_lora and lora_model != "":
                lora_model_path = os.path.join(shared.models_path, "lora", lora_model)

Now if you want to train a lora config.use_lora is True and lora_model is not "" (because it is []) and so it tries to load an existing lora model.

As a workaround I edited my model's db_config.json file (under models/dreambooth/<your_model>) and replaced "lora_model_name": [] with "lora_model_name": "", this fixed the error.

harrywang · 2023-03-04T21:39:32Z

This worked for me. Thanks! @Anonym271

caretaker0815 · 2023-03-05T03:35:42Z

Helped me too. Thanks a lot @Anonym271

GitHubGuy89 · 2023-03-07T07:29:02Z

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:
cloneofsimo/lora#147 (comment)

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.

kc1025 · 2023-03-27T05:47:36Z

Thank you for helping me solve the problem.

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:
            if config.use_lora and lora_model != "":
                lora_model_path = os.path.join(shared.models_path, "lora", lora_model)
Now if you want to train a lora config.use_lora is True and lora_model is not "" (because it is []) and so it tries to load an existing lora model.

As a workaround I edited my model's db_config.json file (under models/dreambooth/<your_model>) and replaced "lora_model_name": [] with "lora_model_name": "", this fixed the error.

Thank you for helping me solve the problem.

ricoty added the new Just added, you should probably sort this. label Jan 19, 2023

Anime4000 mentioned this issue Jan 19, 2023

Gradio return Empty DropDownList as blank list #804

Closed

d8ahazard linked a pull request Jan 20, 2023 that will close this issue

So many fixes, so much wow. #806

Merged

d8ahazard closed this as completed in #806 Jan 21, 2023

HanJammer mentioned this issue Jan 22, 2023

Exception training model: 'join() argument must be str, bytes, or os.PathLike object, not 'list''. cloneofsimo/lora#147

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

join() argument must be str, bytes, or os.PathLike object, not 'NoneType' #802

join() argument must be str, bytes, or os.PathLike object, not 'NoneType' #802

ricoty commented Jan 19, 2023

Tsubashi commented Jan 19, 2023 •

edited

Loading

ricoty commented Jan 19, 2023 •

edited

Loading

art-phony commented Jan 19, 2023 •

edited

Loading

ricoty commented Jan 19, 2023

john-cianfarani commented Jan 20, 2023

nathan-kennedy commented Jan 20, 2023

ddzbs commented Jan 20, 2023

john-cianfarani commented Jan 20, 2023

Jc7out commented Jan 25, 2023

fipil commented Mar 1, 2023 •

edited

Loading

SoundGuy commented Mar 2, 2023

Anonym271 commented Mar 4, 2023

Anonym271 commented Mar 4, 2023

harrywang commented Mar 4, 2023

caretaker0815 commented Mar 5, 2023

GitHubGuy89 commented Mar 7, 2023

kc1025 commented Mar 27, 2023

join() argument must be str, bytes, or os.PathLike object, not 'NoneType' #802

join() argument must be str, bytes, or os.PathLike object, not 'NoneType' #802

Comments

ricoty commented Jan 19, 2023

Kindly read the entire form below and fill it out with the requested information.

Tsubashi commented Jan 19, 2023 • edited Loading

ricoty commented Jan 19, 2023 • edited Loading

art-phony commented Jan 19, 2023 • edited Loading

ricoty commented Jan 19, 2023

john-cianfarani commented Jan 20, 2023

nathan-kennedy commented Jan 20, 2023

ddzbs commented Jan 20, 2023

john-cianfarani commented Jan 20, 2023

Jc7out commented Jan 25, 2023

fipil commented Mar 1, 2023 • edited Loading

SoundGuy commented Mar 2, 2023

Anonym271 commented Mar 4, 2023

Anonym271 commented Mar 4, 2023

harrywang commented Mar 4, 2023

caretaker0815 commented Mar 5, 2023

GitHubGuy89 commented Mar 7, 2023

kc1025 commented Mar 27, 2023

Tsubashi commented Jan 19, 2023 •

edited

Loading

ricoty commented Jan 19, 2023 •

edited

Loading

art-phony commented Jan 19, 2023 •

edited

Loading

fipil commented Mar 1, 2023 •

edited

Loading