Experimenting with included demo.jpeg

[lavalava45]

Experimenting with included demo.jpeg

Starting job extras
*** Error completing request
*** Arguments: (0, <PIL.Image.Image image mode=RGB size=793x468 at 0x190C2038730>, None, '', '', True, 0, 1, 512, 512, True, 'None', 'None', 0, 0, 0, 0, True, 35, False) {}
Traceback (most recent call last):
File "D:\stable-diffusion-webui\modules\call_queue.py", line 58, in f
res = list(func(*args, **kwargs))
File "D:\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "D:\stable-diffusion-webui\modules\postprocessing.py", line 62, in run_postprocessing
scripts.scripts_postproc.run(pp, args)
File "D:\stable-diffusion-webui\modules\scripts_postprocessing.py", line 130, in run
script.process(pp, **process_args)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\scripts\postprocessing_deoldify.py", line 63, in process
pp.image = self.process_image(pp.image, render_factor, artistic)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\scripts\postprocessing_deoldify.py", line 55, in process_image
vis = get_image_colorizer(root_folder=Path(paths_internal.models_path),render_factor=render_factor, artistic=artistic)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\deoldify\visualize.py", line 417, in get_image_colorizer
return get_stable_image_colorizer(root_folder=root_folder, render_factor=render_factor)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\deoldify\visualize.py", line 426, in get_stable_image_colorizer
learn = gen_inference_wide(root_folder=root_folder, weights_name=weights_name)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\deoldify\generators.py", line 19, in gen_inference_wide
learn.load(weights_name)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\fastai\basic_train.py", line 271, in load
state = torch.load(source, map_location=device)
File "D:\stable-diffusion-webui\modules\safe.py", line 108, in load
return load_with_extra(filename, *args, extra_handler=global_extra_handler, **kwargs)
File "D:\stable-diffusion-webui\modules\safe.py", line 156, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "D:\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "D:\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 1051, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: unexpected EOF, expected 7913014 more bytes. The file might be corrupted.

---

2023-08-07 18:32:29 INFO [httpx] HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
2023-08-07 18:32:29 INFO [httpx] HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"
HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"

[SpenserCai]

Please confirm whether --disable-safe-unpickle is loaded in the start command. At the same time, confirm whether the model is downloaded completely.

[SpenserCai]

you can download the model from here then put to stable-diffusion-webui\models\deoldify\

[lavalava45]

Hello again! Had to redownload all the models to be sure that the problem is not with them,
and here is my COMMANDLINE_ARGS=--opt-sdp-attention --opt-split-attention --autolaunch --deepdanbooru --api --disable-safe-unpickle

Restarted WebUI once more. Forgot to report that it works with "artistic" option activated but still throwing an error without it:

2023-08-07 22:42:09 INFO [modules.shared] Starting job extras
Starting job extras
*** Error completing request
*** Arguments: (0, <PIL.Image.Image image mode=RGB size=2400x1770 at 0x191478CF6D0>, None, '', '', True, 0, 1, 512, 512, True, 'None', 'None', 0, 0, 0, 0, True, 35, False) {}
Traceback (most recent call last):
File "D:\stable-diffusion-webui\modules\call_queue.py", line 58, in f
res = list(func(*args, **kwargs))
File "D:\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "D:\stable-diffusion-webui\modules\postprocessing.py", line 62, in run_postprocessing
scripts.scripts_postproc.run(pp, args)
File "D:\stable-diffusion-webui\modules\scripts_postprocessing.py", line 130, in run
script.process(pp, **process_args)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\scripts\postprocessing_deoldify.py", line 63, in process
pp.image = self.process_image(pp.image, render_factor, artistic)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\scripts\postprocessing_deoldify.py", line 55, in process_image
vis = get_image_colorizer(root_folder=Path(paths_internal.models_path),render_factor=render_factor, artistic=artistic)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\deoldify\visualize.py", line 417, in get_image_colorizer
return get_stable_image_colorizer(root_folder=root_folder, render_factor=render_factor)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\deoldify\visualize.py", line 426, in get_stable_image_colorizer
learn = gen_inference_wide(root_folder=root_folder, weights_name=weights_name)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\deoldify\generators.py", line 19, in gen_inference_wide
learn.load(weights_name)
File "D:\stable-diffusion-webui\extensions\sd-webui-deoldify\fastai\basic_train.py", line 271, in load
state = torch.load(source, map_location=device)
File "D:\stable-diffusion-webui\modules\safe.py", line 108, in load
return load_with_extra(filename, *args, extra_handler=global_extra_handler, **kwargs)
File "D:\stable-diffusion-webui\modules\safe.py", line 156, in load_with_extra
return unsafe_torch_load(filename, *args, **kwargs)
File "D:\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 815, in load
return _legacy_load(opened_file, map_location, pickle_module, **pickle_load_args)
File "D:\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 1051, in _legacy_load
typed_storage._untyped_storage._set_from_file(
RuntimeError: unexpected EOF, expected 7913014 more bytes. The file might be corrupted.

---

2023-08-07 22:42:22 INFO [httpx] HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
HTTP Request: POST http://127.0.0.1:7860/api/predict "HTTP/1.1 200 OK"
2023-08-07 22:42:22 INFO [httpx] HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"
HTTP Request: POST http://127.0.0.1:7860/reset "HTTP/1.1 200 OK"

[SpenserCai]

from the error message, it is indeed an error caused by incomplete model files. You can try to compare the SHA256 of the model. For example, ColorizeArtistic_gen.pth's SHA256 is: 3f750246fa220529323b85a8905f9b49c0e5d427099185334d048fb

[lavalava45]

HugginFace shows another hash number for this model - it's
SHA256: 3f750246fa220529323b85a8905f9b49c0e5d427099185334d048fb5b5e22477

The one that I have locally has the same hash (other 2 models also has same hash as HugginFace's) -
3f750246fa220529323b85a8905f9b49c0e5d427099185334d048fb5b5e22477 *ColorizeArtistic_gen.pth

but it's different from the hash you've posted above (I think your's is truncated somehow).

[SpenserCai]

Yes, he has been phased out. This way, hash is correct. You can try using other black and white images to test it

[SpenserCai]

Your question seems like this, you can try deleting the demo model directory and restarting it to download the model again