Error loading model from Hugging Face in ddim-inversion.ipynb on Colab

[euminds]

I am trying to run ddim-inversion.ipynb on Colab. When load a model from Hugging Face using the diffusers library, it seems an error.

pipe = StableDiffusionPipeline.from_pretrained(path) pipe.scheduler = DDIMScheduler.from_config(path / "scheduler") pipe = pipe.to("cuda")

HFValidationError Traceback (most recent call last) /usr/local/lib/python3.8/dist-packages/diffusers/configuration_utils.py in get_config_dict(cls, pretrained_model_name_or_path, **kwargs) 222 # Load from URL or cache if already cached --> 223 config_file = hf_hub_download( 224 pretrained_model_name_or_path,

4 frames /usr/local/lib/python3.8/dist-packages/huggingface_hub/utils/_validators.py in _inner_fn(*args, **kwargs) 113 if arg_name == "repo_id": --> 114 validate_repo_id(arg_value) 115

/usr/local/lib/python3.8/dist-packages/huggingface_hub/utils/_validators.py in validate_repo_id(repo_id) 165 if repo_id.count("/") > 1: --> 166 raise HFValidationError( 167 "Repo id must be in the form 'repo_name' or 'namespace/repo_name':"

HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/root/models/stable-diffusion-v1-4'. Use repo_type argument if needed.

During handling of the above exception, another exception occurred:

OSError Traceback (most recent call last) in ----> 1 pipe = StableDiffusionPipeline.from_pretrained(path) 2 pipe.scheduler = DDIMScheduler.from_config(path / "scheduler") 3 pipe = pipe.to("cuda")

/usr/local/lib/python3.8/dist-packages/diffusers/pipeline_utils.py in from_pretrained(cls, pretrained_model_name_or_path, **kwargs) 343 # use snapshot download here to get it working from from_pretrained 344 if not os.path.isdir(pretrained_model_name_or_path): --> 345 config_dict = cls.get_config_dict( 346 pretrained_model_name_or_path, 347 cache_dir=cache_dir,

/usr/local/lib/python3.8/dist-packages/diffusers/configuration_utils.py in get_config_dict(cls, pretrained_model_name_or_path, **kwargs) 258 ) 259 except ValueError: --> 260 raise EnvironmentError( 261 f"We couldn't connect to '{HUGGINGFACE_CO_RESOLVE_ENDPOINT}' to load this model, couldn't find it" 262 f" in the cached files and it looks like {pretrained_model_name_or_path} is not the path to a"

OSError: We couldn't connect to 'https://huggingface.co/' to load this model, couldn't find it in the cached files and it looks like /root/models/stable-diffusion-v1-4 is not the path to a directory containing a model_index.json file. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Where path is path = "~/models/stable-diffusion-v1-4" path = Path(path).expanduser()

[cccntu]

That’s because the path is pointing to my local model. You can change that to your local model or model id on huggingface hub