Replies: 2 comments
-
The same is happening for me... |
Beta Was this translation helpful? Give feedback.
0 replies
-
most likely the file is trying to load is corrupted |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hello.I am trying to create an image from a depth map by controlnet on the sdxl chekpoint.Unfortunatelly, i cant do that,I always get the error:
*** Error running process: F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\controlnet.py
Traceback (most recent call last):
File "F:\CivitaAi\webui\modules\scripts.py", line 619, in process
script.process(p, *script_args)
File "F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 1143, in process
self.controlnet_hack(p)
File "F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 1128, in controlnet_hack
self.controlnet_main_entry(p)
File "F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 894, in controlnet_main_entry
model_net, control_model_type = Script.load_control_model(p, unet, unit.model)
File "F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 367, in load_control_model
control_model = Script.build_control_model(p, unet, model)
File "F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\controlnet.py", line 395, in build_control_model
state_dict = load_state_dict(model_path)
File "F:\CivitaAi\webui\extensions\sd-webui-controlnet\scripts\utils.py", line 21, in load_state_dict
state_dict = unsafe_torch_load(ckpt_path, map_location=torch.device(location))
File "F:\CivitaAi\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 "F:\CivitaAi\webui\venv\lib\site-packages\torch\serialization.py", line 1033, in _legacy_load
magic_number = pickle_module.load(f, **pickle_load_args)
_pickle.UnpicklingError: invalid load key, '\xb8'.
I have this problem only with sdxl chekpoints and i dont have any problems with sd1.5.I tried different models, different sdxl chekpoints and differenet preprocessors and evene diffrenet automatic1111 version, but result is alwaus the same: _pickle.UnpicklingError: invalid load key, '\xb8'.
How can i solve this error?
Beta Was this translation helpful? Give feedback.
All reactions