Method save_pretrained

src/diffusers/models/modeling_utils.py:669–844

Save a model and its configuration file to a directory so that it can be reloaded using the [`~models.ModelMixin.from_pretrained`] class method. Arguments: save_directory (`str` or `os.PathLike`): Directory to save a model and its configuration f

(
        self,
        save_directory: str | os.PathLike,
        is_main_process: bool = True,
        save_function: Callable | None = None,
        safe_serialization: bool = True,
        variant: str | None = None,
        max_shard_size: int | str = "10GB",
        push_to_hub: bool = False,
        use_flashpack: bool = False,
        **kwargs,
    )

            processor._attention_backend = None

    def save_pretrained(
        self,
        save_directory: str | os.PathLike,
        is_main_process: bool = True,
        save_function: Callable | None = None,
        safe_serialization: bool = True,
        variant: str | None = None,
        max_shard_size: int | str = "10GB",
        push_to_hub: bool = False,
        use_flashpack: bool = False,
        **kwargs,
    ):
        """
        Save a model and its configuration file to a directory so that it can be reloaded using the
        [`~models.ModelMixin.from_pretrained`] class method.

        Arguments:
            save_directory (`str` or `os.PathLike`):
                Directory to save a model and its configuration file to. Will be created if it doesn't exist.
            is_main_process (`bool`, *optional*, defaults to `True`):
                Whether the process calling this is the main process or not. Useful during distributed training and you
                need to call this function on all processes. In this case, set `is_main_process=True` only on the main
                process to avoid race conditions.
            save_function (`Callable`):
                The function to use to save the state dictionary. Useful during distributed training when you need to
                replace `torch.save` with another method. Can be configured with the environment variable
                `DIFFUSERS_SAVE_MODE`.
            safe_serialization (`bool`, *optional*, defaults to `True`):
                Whether to save the model using `safetensors` or the traditional PyTorch way with `pickle`.
            variant (`str`, *optional*):
                If specified, weights are saved in the format `pytorch_model.<variant>.bin`.
            max_shard_size (`int` or `str`, defaults to `"10GB"`):
                The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size
                lower than this size. If expressed as a string, needs to be digits followed by a unit (like `"5GB"`).
                If expressed as an integer, the unit is bytes. Note that this limit will be decreased after a certain
                period of time (starting from Oct 2024) to allow users to upgrade to the latest version of `diffusers`.
                This is to establish a common default size for this argument across different libraries in the Hugging
                Face ecosystem (`transformers`, and `accelerate`, for example).
            push_to_hub (`bool`, *optional*, defaults to `False`):
                Whether or not to push your model to the Hugging Face Hub after saving it. You can specify the
                repository you want to push to with `repo_id` (will default to the name of `save_directory` in your
                namespace).
            kwargs (`dict[str, Any]`, *optional*):
                Additional keyword arguments passed along to the [`~utils.PushToHubMixin.push_to_hub`] method.
        """
        if os.path.isfile(save_directory):
            logger.error(f"Provided path ({save_directory}) should be a directory, not a file")
            return

        hf_quantizer = getattr(self, "hf_quantizer", None)
        if hf_quantizer is not None:
            quantization_serializable = (
                hf_quantizer is not None
                and isinstance(hf_quantizer, DiffusersQuantizer)
                and hf_quantizer.is_serializable
            )
            if not quantization_serializable:
                raise ValueError(