AUTOMATIC1111
[Bug]: JSONDecodeError | Failed to create model
Is there an existing issue for this?
- [X] I have searched the existing issues and checked the recent builds/commits
What happened?
When I press the webui-user batch, I get this error on the cmd This happened at first time, when installation started and it happens every time
Steps to reproduce the problem
- Git clone AUTOMATIC1111 repository
- Run webui-user.bat
What should have happened?
The programm should start by connecting to the local server
Commit where the problem happens
0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8
What platforms do you use to access the UI ?
Windows
What browsers do you use to access the UI ?
Microsoft Edge
Command Line Arguments
--medvram
List of extensions
No
Console logs
venv "D:\Stable Diffusion Web UI\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Commit hash: 0cc0ee1bcb4c24a8c9715f66cede06601bfc00c8
Installing requirements for Web UI
Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
Loading weights [c6bbc15e32] from D:\Stable Diffusion Web UI\stable-diffusion-webui\models\Stable-diffusion\sd-v1-5-inpainting.ckpt
Creating model from config: D:\Stable Diffusion Web UI\stable-diffusion-webui\configs\v1-inpainting-inference.yaml
LatentInpaintDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.54 M params.
Failed to create model quickly; will retry using slow method.
LatentInpaintDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.54 M params.
loading stable diffusion model: JSONDecodeError
Traceback (most recent call last):
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\webui.py", line 111, in initialize
modules.sd_models.load_model()
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\modules\sd_models.py", line 406, in load_model
sd_model = instantiate_from_config(sd_config.model)
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\util.py", line 79, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1644, in __init__
super().__init__(concat_keys, *args, **kwargs)
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 1509, in __init__
super().__init__(*args, **kwargs)
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 563, in __init__
self.instantiate_cond_stage(cond_stage_config)
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 630, in instantiate_cond_stage
model = instantiate_from_config(config)
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\util.py", line 79, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\modules\encoders\modules.py", line 99, in __init__
self.tokenizer = CLIPTokenizer.from_pretrained(version)
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\venv\lib\site-packages\transformers\tokenization_utils_base.py", line 1801, in from_pretrained
return cls._from_pretrained(
File "D:\Stable Diffusion Web UI\stable-diffusion-webui\venv\lib\site-packages\transformers\tokenization_utils_base.py", line 1972, in _from_pretrained
special_tokens_map = json.load(special_tokens_map_handle)
File "C:\Users\jeart\AppData\Local\Programs\Python\Python310\lib\json\__init__.py", line 293, in load
return loads(fp.read(),
File "C:\Users\jeart\AppData\Local\Programs\Python\Python310\lib\json\__init__.py", line 346, in loads
return _default_decoder.decode(s)
File "C:\Users\jeart\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "C:\Users\jeart\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
Stable diffusion model failed to load, exiting
Для продолжения нажмите любую клавишу . . .
Additional information
That happened after reinstalling windows. Before reinstall it worked well and nothing happened unless I had faced a conflict with NVIDIA driver. After autoinstallation of NVIDIA driver version 531.18 by NVIDIA GeFroce Experience, my system started to crush every time when Stable Diffusion Web UI was used. Now, With NVIDIA driver 528.49 version, I guess this problem is solved, but suddenly this JSONDecodeError problem appeared and I don't know what am I supposed to do.
I am running on the same issue, "Failed to create model quickly;" followed by "loading stable diffusion model: JSONDecodeError...". I am running windows 10 64bit with a gtx960, 2gb of vram. I had a previous version of the web-ui working on this same system a few months ago. I Tried updating the gpu drivers, cuda, downgrading from python 3.10.7 to 3.10.6, and updating pip... nothing worked so far.
Deleting cache.json and cache.json.lock in the root dir ended up fixing it for me. Was running some code refactoring and it ended up messing up a lot of stuff (all of my embeddings are corrupted yay), and then i was suddenly getting this error.
I tried deleting cache.json already, but it didn't do it for me. I do not have a cache.json.lock file anywhere tough. I am not doing anything funny with the files other than trying suggested fixes. I also re-downloaded it from git multiple times and it's always the same problem.
found it, Delete the "huggingface" dir in .cache folder. the relaunch .bat C:\Users\CURRENTUSER\ .cache\huggingface
found it, Delete the "huggingface" dir in .cache folder. the relaunch .bat C:\Users\CURRENTUSER\ .cache\huggingface
This worked for me too! Thank you so much KeypressHAPPY.
Mac User here, I have a similar error, but a different trace. This happens after trying to run prompts in the browser:
File "/Users/wein/Documents/stable-diffusion-webui/modules/call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "/Users/wein/Documents/stable-diffusion-webui/modules/ui_common.py", line 46, in save_files
data = json.loads(js_data)
File "/usr/local/Cellar/[email protected]/3.10.10_1/Frameworks/Python.framework/Versions/3.10/lib/python3.10/json/__init__.py", line 346, in loads
return _default_decoder.decode(s)
File "/usr/local/Cellar/[email protected]/3.10.10_1/Frameworks/Python.framework/Versions/3.10/lib/python3.10/json/decoder.py", line 337, in decode
obj, end = self.raw_decode(s, idx=_w(s, 0).end())
File "/usr/local/Cellar/[email protected]/3.10.10_1/Frameworks/Python.framework/Versions/3.10/lib/python3.10/json/decoder.py", line 355, in raw_decode
raise JSONDecodeError("Expecting value", s, err.value) from None
json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
found it, Delete the "huggingface" dir in .cache folder. the relaunch .bat C:\Users\CURRENTUSER\ .cache\huggingface
TKU!!! I downloaded the model files again and deleted the following directories C:\Users\kura.cache\huggingface and files cache.json in the root directory.
KeypressHAPPY's solution fixed my issue as well, I wish I knew what caused it in the first place as it was fairly random, but glad to have it working again. Thanks a ton!
