Test model does not work

[vitalijmirnyj]

Hello. I love this version of fast dreambooth. But it worked for me great for weeks and now it does not. After i train new model or load an existing model and try to test it on gradio, no links show up. I wonder can i run some previous version that worked? Or can i save the existing version that works when it works, so any new updates would not apply to working model? Thank you

[TheLastBen]

Hi, could you post a screen shot of the testing cell error ?

[vitalijmirnyj]

when i try to add caption over uploaded images i get this error:

KeyError Traceback (most recent call last)

in click(change)
60 with out:
61 out.clear_output()
---> 62 display(Caption(change.new))
63
64 widgets_l.observe(click, names='value')

1 frames

/usr/local/lib/python3.8/dist-packages/PIL/Image.py in save(self, fp, format, **params)
2121 save_handler = SAVE_ALL[format.upper()]
2122 else:
-> 2123 save_handler = SAVE[format.upper()]
2124
2125 if open_fp:

KeyError: 'JPG'

And when i try to test model i get this:
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/webui.py", line 13, in
from modules.call_queue import wrap_queued_call, queue_lock, wrap_gradio_gpu_call
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/call_queue.py", line 7, in
from modules import shared
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/shared.py", line 390, in
"img2img_background_color": OptionInfo("#ffffff", "With img2img, fill image's transparent parts with this color.", ui_components.FormColorPicker, {}),
AttributeError: module 'modules.ui_components' has no attribute 'FormColorPicker'

[TheLastBen]

your sd folder is out of date, remove/rename it and do a clean run with the latest colab

[edbergc7]

Hey @TheLastBen , firstly just wanted to say thank you for all your work , I also get an error after clicking on the "Test the Trained Model " cell after training a model.
here is a screenshot, I can download the model as an alternative and test locally and not via collab.

[edbergc7]

ah just saw your comment i will delete the old SD and try again thanks

[TheLastBen]

This issue will be solved by removing/renaming the folder sd in your gdrive

[vitalijmirnyj]

Thank you very much for your help and great work you are doing.

[vitalijmirnyj]

Don't want to bother, but i still have problems. I deleted sd folder from my gdrive. And run that collab again. Maybe i do not know what is clean run? Is it something specific i must do? This time i get this:
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Downloading100% 961k/961k [00:00<00:00, 28.6MB/s]
Downloading100% 4.52k/4.52k [00:00<00:00, 6.92MB/s]
Failed to create model quickly; will retry using slow method.
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
loading stable diffusion model: TypeError
Traceback (most recent call last):
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/webui.py", line 74, in initialize
modules.sd_models.load_model()
File "/content/gdrive/MyDrive/sd/stable-diffusion-webui/modules/sd_models.py", line 345, in load_model
sd_model = instantiate_from_config(sd_config.model)
File "/content/gdrive/MyDrive/sd/stablediffusion/ldm/util.py", line 79, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/content/gdrive/MyDrive/sd/stablediffusion/ldm/models/diffusion/ddpm.py", line 563, in init
self.instantiate_cond_stage(cond_stage_config)
File "/content/gdrive/MyDrive/sd/stablediffusion/ldm/models/diffusion/ddpm.py", line 630, in instantiate_cond_stage
model = instantiate_from_config(config)
File "/content/gdrive/MyDrive/sd/stablediffusion/ldm/util.py", line 79, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "/content/gdrive/MyDrive/sd/stablediffusion/ldm/modules/encoders/modules.py", line 99, in init
self.tokenizer = CLIPTokenizer.from_pretrained(version)
File "/usr/local/lib/python3.8/dist-packages/transformers/tokenization_utils_base.py", line 1777, in from_pretrained
return cls._from_pretrained(
File "/usr/local/lib/python3.8/dist-packages/transformers/tokenization_utils_base.py", line 1932, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/usr/local/lib/python3.8/dist-packages/transformers/models/clip/tokenization_clip.py", line 328, in init
with open(merges_file, encoding="utf-8") as merges_handle:
TypeError: expected str, bytes or os.PathLike object, not NoneType

Stable diffusion model failed to load, exiting

[TheLastBen]

working on a fix, meanwhile use the A1111 colab to test it

[vitalijmirnyj]

Thank you it works great now.