Models

🤗 Diffusers provides pretrained models for popular algorithms and modules to create custom diffusion systems. The primary function of models is to denoise an input sample as modeled by the distribution p_{θ}(x_{t-1}|x_{t})

All models are built from the base ModelMixin class which is a mindspore.nn.Cell providing basic functionality for saving and loading models, locally and from the Hugging Face Hub.

mindone.diffusers.ModelMixin

Bases: Cell, PushToHubMixin

Base class for all models.

[ModelMixin] takes care of storing the model configuration and provides methods for loading, downloading and saving models.

- **config_name** ([`str`]) -- Filename to save a model to when calling [`~models.ModelMixin.save_pretrained`].

Source code in mindone/diffusers/models/modeling_utils.py

class ModelMixin(nn.Cell, PushToHubMixin):
    r"""
    Base class for all models.

    [`ModelMixin`] takes care of storing the model configuration and provides methods for loading, downloading and
    saving models.

        - **config_name** ([`str`]) -- Filename to save a model to when calling [`~models.ModelMixin.save_pretrained`].
    """

    config_name = CONFIG_NAME
    _automatically_saved_args = ["_diffusers_version", "_class_name", "_name_or_path"]
    _supports_gradient_checkpointing = False
    _keys_to_ignore_on_load_unexpected = None
    _no_split_modules = None

    def __init__(self):
        super().__init__()

    def __getattr__(self, name: str) -> Any:
        """The only reason we overwrite `getattr` here is to gracefully deprecate accessing
        config attributes directly. See https://github.com/huggingface/diffusers/pull/3129 We need to overwrite
        __getattr__ here in addition so that we don't trigger `nn.Cell`'s __getattr__':
        https://pytorch.org/docs/stable/_modules/torch/nn/modules/module.html#Module
        """

        is_in_config = "_internal_dict" in self.__dict__ and hasattr(self.__dict__["_internal_dict"], name)
        is_attribute = name in self.__dict__

        if is_in_config and not is_attribute:
            deprecation_message = f"Accessing config attribute `{name}` directly via '{type(self).__name__}' object attribute is deprecated. Please access '{name}' over '{type(self).__name__}'s config object instead, e.g. 'unet.config.{name}'."  # noqa: E501
            deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False, stacklevel=3)
            return self._internal_dict[name]

        # call PyTorch's https://pytorch.org/docs/stable/_modules/torch/nn/modules/module.html#Module
        return super().__getattr__(name)

    @property
    def is_gradient_checkpointing(self) -> bool:
        """
        Whether gradient checkpointing is activated for this model or not.
        """
        return any(hasattr(m, "gradient_checkpointing") and m.gradient_checkpointing for _, m in self.cells_and_names())

    def enable_gradient_checkpointing(self) -> None:
        """
        Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or
        *checkpoint activations* in other frameworks).
        """
        if not self._supports_gradient_checkpointing:
            raise ValueError(f"{self.__class__.__name__} does not support gradient checkpointing.")
        self.apply(partial(self._set_gradient_checkpointing, value=True))

    def disable_gradient_checkpointing(self) -> None:
        """
        Deactivates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or
        *checkpoint activations* in other frameworks).
        """
        if self._supports_gradient_checkpointing:
            self.apply(partial(self._set_gradient_checkpointing, value=False))

    def enable_flash_sdp(self, enabled: bool):
        r"""
        .. warning:: This flag is beta and subject to change.

        Enables or disables flash scaled dot product attention.
        """

        # Recursively walk through all the children.
        # Any children which exposes the enable_flash_sdp method
        # gets the message
        def fn_recursive_set_mem_eff(module: nn.Cell):
            if hasattr(module, "enable_flash_sdp"):
                module.enable_flash_sdp(enabled)

            for child in module.cells():
                fn_recursive_set_mem_eff(child)

        for module in self.cells():
            if isinstance(module, nn.Cell):
                fn_recursive_set_mem_eff(module)

    def set_flash_attention_force_cast_dtype(self, force_cast_dtype: Optional[ms.Type]):
        r"""
        Since the flash-attention operator in MindSpore only supports float16 and bfloat16 data types, we need to manually
        set whether to force data type conversion.

        When the attention interface encounters data of an unsupported data type,
        if `force_cast_dtype` is not None, the function will forcibly convert the data to `force_cast_dtype` for computation
        and then restore it to the original data type afterward. If `force_cast_dtype` is None, it will fall back to the
        original attention calculation using mathematical formulas.

        Parameters:
            force_cast_dtype (Optional): The data type to which the input data should be forcibly converted. If None, no forced
            conversion is performed.
        """

        # Recursively walk through all the children.
        # Any children which exposes the set_flash_attention_force_cast_dtype method
        # gets the message
        def fn_recursive_set_mem_eff(module: nn.Cell):
            if hasattr(module, "set_flash_attention_force_cast_dtype"):
                module.set_flash_attention_force_cast_dtype(force_cast_dtype)

            for child in module.cells():
                fn_recursive_set_mem_eff(child)

        for module in self.cells():
            if isinstance(module, nn.Cell):
                fn_recursive_set_mem_eff(module)

    def set_use_memory_efficient_attention_xformers(self, valid: bool, attention_op: Optional[Callable] = None) -> None:
        # Recursively walk through all the children.
        # Any children which exposes the set_use_memory_efficient_attention_xformers method
        # gets the message
        def fn_recursive_set_mem_eff(module: nn.Cell):
            if hasattr(module, "set_use_memory_efficient_attention_xformers"):
                module.set_use_memory_efficient_attention_xformers(valid, attention_op)

            for child in module.cells():
                fn_recursive_set_mem_eff(child)

        for module in self.cells():
            if isinstance(module, nn.Cell):
                fn_recursive_set_mem_eff(module)

    def enable_xformers_memory_efficient_attention(self, attention_op: Optional[Callable] = None) -> None:
        r"""
        Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).

        When this option is enabled, you should observe lower GPU memory usage and a potential speed up during
        inference. Speed up during training is not guaranteed.

        <Tip warning={true}>

        ⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes
        precedent.

        </Tip>

        Parameters:
            attention_op (`Callable`, *optional*):
                Not supported for now.

        Examples:

        ```py
        >>> import mindspore as ms
        >>> from mindone.diffusers import UNet2DConditionModel

        >>> model = UNet2DConditionModel.from_pretrained(
        ...     "stabilityai/stable-diffusion-2-1", subfolder="unet", mindspore_dtype=ms.float16
        ... )
        >>> model.enable_xformers_memory_efficient_attention()
        ```
        """
        self.set_use_memory_efficient_attention_xformers(True, attention_op)

    def disable_xformers_memory_efficient_attention(self) -> None:
        r"""
        Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).
        """
        self.set_use_memory_efficient_attention_xformers(False)

    def save_pretrained(
        self,
        save_directory: Union[str, os.PathLike],
        is_main_process: bool = True,
        save_function: Optional[Callable] = None,
        safe_serialization: bool = True,
        variant: Optional[str] = None,
        max_shard_size: Union[int, str] = "10GB",
        push_to_hub: 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 `mindspore.save_checkpoint` 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

        weights_name = SAFETENSORS_WEIGHTS_NAME if safe_serialization else WEIGHTS_NAME
        weights_name = _add_variant(weights_name, variant)
        weight_name_split = weights_name.split(".")
        if len(weight_name_split) in [2, 3]:
            weights_name_pattern = weight_name_split[0] + "{suffix}." + ".".join(weight_name_split[1:])
        else:
            raise ValueError(f"Invalid {weights_name} provided.")

        os.makedirs(save_directory, exist_ok=True)

        if push_to_hub:
            commit_message = kwargs.pop("commit_message", None)
            private = kwargs.pop("private", False)
            create_pr = kwargs.pop("create_pr", False)
            token = kwargs.pop("token", None)
            repo_id = kwargs.pop("repo_id", save_directory.split(os.path.sep)[-1])
            repo_id = create_repo(repo_id, exist_ok=True, private=private, token=token).repo_id

        # Only save the model itself if we are using distributed training
        model_to_save = self

        # Attach architecture to the config
        # Save the config
        if is_main_process:
            model_to_save.save_config(save_directory)

        # Save the model
        state_dict = {k: v for k, v in model_to_save.parameters_and_names()}

        # Save the model
        state_dict_split = split_torch_state_dict_into_shards(
            state_dict, max_shard_size=max_shard_size, filename_pattern=weights_name_pattern
        )

        # Clean the folder from a previous save
        if is_main_process:
            for filename in os.listdir(save_directory):
                if filename in state_dict_split.filename_to_tensors.keys():
                    continue
                full_filename = os.path.join(save_directory, filename)
                if not os.path.isfile(full_filename):
                    continue
                weights_without_ext = weights_name_pattern.replace(".bin", "").replace(".safetensors", "")
                weights_without_ext = weights_without_ext.replace("{suffix}", "")
                filename_without_ext = filename.replace(".bin", "").replace(".safetensors", "")
                # make sure that file to be deleted matches format of sharded file, e.g. pytorch_model-00001-of-00005
                if (
                    filename.startswith(weights_without_ext)
                    and _REGEX_SHARD.fullmatch(filename_without_ext) is not None
                ):
                    os.remove(full_filename)

        for filename, tensors in state_dict_split.filename_to_tensors.items():
            shard = {tensor: state_dict[tensor] for tensor in tensors}
            filepath = os.path.join(save_directory, filename)
            if safe_serialization:
                # At some point we will need to deal better with save_function (used for TPU and other distributed
                # joyfulness), but for now this enough.
                safe_save_file(shard, filepath, metadata={"format": "np"})
            else:
                ms.save_checkpoint(shard, filepath)

        if state_dict_split.is_sharded:
            index = {
                "metadata": state_dict_split.metadata,
                "weight_map": state_dict_split.tensor_to_filename,
            }
            save_index_file = SAFE_WEIGHTS_INDEX_NAME if safe_serialization else WEIGHTS_INDEX_NAME
            save_index_file = os.path.join(save_directory, _add_variant(save_index_file, variant))
            # Save the index as well
            with open(save_index_file, "w", encoding="utf-8") as f:
                content = json.dumps(index, indent=2, sort_keys=True) + "\n"
                f.write(content)
            logger.info(
                f"The model is bigger than the maximum size per checkpoint ({max_shard_size}) and is going to be "
                f"split in {len(state_dict_split.filename_to_tensors)} checkpoint shards. You can find where each parameters has been saved in the "
                f"index located at {save_index_file}."
            )
        else:
            path_to_weights = os.path.join(save_directory, weights_name)
            logger.info(f"Model weights saved in {path_to_weights}")

        if push_to_hub:
            # Create a new empty model card and eventually tag it
            model_card = load_or_create_model_card(repo_id, token=token)
            model_card = populate_model_card(model_card)
            model_card.save(Path(save_directory, "README.md").as_posix())

            self._upload_folder(
                save_directory,
                repo_id,
                token=token,
                commit_message=commit_message,
                create_pr=create_pr,
            )

    @classmethod
    @validate_hf_hub_args
    def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.PathLike]], **kwargs):
        r"""
        Instantiate a pretrained PyTorch model from a pretrained model configuration.

        The model is set in evaluation mode - `model.eval()` - by default, and dropout modules are deactivated. To
        train the model, set it back in training mode with `model.train()`.

        Parameters:
            pretrained_model_name_or_path (`str` or `os.PathLike`, *optional*):
                Can be either:

                    - A string, the *model id* (for example `google/ddpm-celebahq-256`) of a pretrained model hosted on
                      the Hub.
                    - A path to a *directory* (for example `./my_model_directory`) containing the model weights saved
                      with [`~ModelMixin.save_pretrained`].

            cache_dir (`Union[str, os.PathLike]`, *optional*):
                Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
                is not used.
            mindspore_dtype (`str` or `mindspore.Type`, *optional*):
                Override the default `mindspore.Type` and load the model with another dtype. If `"auto"` is passed, the
                dtype is automatically derived from the model's weights.
            force_download (`bool`, *optional*, defaults to `False`):
                Whether or not to force the (re-)download of the model weights and configuration files, overriding the
                cached versions if they exist.
            proxies (`Dict[str, str]`, *optional*):
                A dictionary of proxy servers to use by protocol or endpoint, for example, `{'http': 'foo.bar:3128',
                'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
            output_loading_info (`bool`, *optional*, defaults to `False`):
                Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.
            local_files_only(`bool`, *optional*, defaults to `False`):
                Whether to only load local model weights and configuration files or not. If set to `True`, the model
                won't be downloaded from the Hub.
            token (`str` or *bool*, *optional*):
                The token to use as HTTP bearer authorization for remote files. If `True`, the token generated from
                `diffusers-cli login` (stored in `~/.huggingface`) is used.
            revision (`str`, *optional*, defaults to `"main"`):
                The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
                allowed by Git.
            from_flax (`bool`, *optional*, defaults to `False`):
                Load the model weights from a Flax checkpoint save file.
            subfolder (`str`, *optional*, defaults to `""`):
                The subfolder location of a model file within a larger model repository on the Hub or locally.
            mirror (`str`, *optional*):
                Mirror source to resolve accessibility issues if you're downloading a model in China. We do not
                guarantee the timeliness or safety of the source, and you should refer to the mirror site for more
                information.
            variant (`str`, *optional*):
                Load weights from a specified `variant` filename such as `"fp16"` or `"ema"`. This is ignored when
                loading `from_flax`.
            use_safetensors (`bool`, *optional*, defaults to `None`):
                If set to `None`, the `safetensors` weights are downloaded if they're available **and** if the
                `safetensors` library is installed. If set to `True`, the model is forcibly loaded from `safetensors`
                weights. If set to `False`, `safetensors` weights are not loaded.

        <Tip>

        To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with
        `huggingface-cli login`. You can also activate the special
        ["offline-mode"](https://huggingface.co/diffusers/installation.html#offline-mode) to use this method in a
        firewalled environment.

        </Tip>

        Example:

        ```py
        from mindone.diffusers import UNet2DConditionModel

        unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet")
        ```

        If you get the error message below, you need to finetune the weights for your downstream task:

        ```bash
        Some weights of UNet2DConditionModel were not initialized from the model checkpoint at
        runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
        - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
        You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
        ```
        """
        cache_dir = kwargs.pop("cache_dir", None)
        ignore_mismatched_sizes = kwargs.pop("ignore_mismatched_sizes", False)
        force_download = kwargs.pop("force_download", False)
        from_flax = kwargs.pop("from_flax", False)
        proxies = kwargs.pop("proxies", None)
        output_loading_info = kwargs.pop("output_loading_info", False)
        local_files_only = kwargs.pop("local_files_only", None)
        token = kwargs.pop("token", None)
        revision = kwargs.pop("revision", None)
        mindspore_dtype = kwargs.pop("mindspore_dtype", None)
        subfolder = kwargs.pop("subfolder", None)
        variant = kwargs.pop("variant", None)
        use_safetensors = kwargs.pop("use_safetensors", None)

        allow_pickle = False
        if use_safetensors is None:
            use_safetensors = True
            allow_pickle = True

        # Load config if we don't provide a configuration
        config_path = pretrained_model_name_or_path

        user_agent = {
            "diffusers": __version__,
            "file_type": "model",
            "framework": "pytorch",
        }

        # load config
        config, unused_kwargs, commit_hash = cls.load_config(
            config_path,
            cache_dir=cache_dir,
            return_unused_kwargs=True,
            return_commit_hash=True,
            force_download=force_download,
            proxies=proxies,
            local_files_only=local_files_only,
            token=token,
            revision=revision,
            subfolder=subfolder,
            user_agent=user_agent,
            **kwargs,
        )

        # Determine if we're loading from a directory of sharded checkpoints.
        is_sharded = False
        index_file = None
        is_local = os.path.isdir(pretrained_model_name_or_path)
        index_file = _fetch_index_file(
            is_local=is_local,
            pretrained_model_name_or_path=pretrained_model_name_or_path,
            subfolder=subfolder or "",
            use_safetensors=use_safetensors,
            cache_dir=cache_dir,
            variant=variant,
            force_download=force_download,
            proxies=proxies,
            local_files_only=local_files_only,
            token=token,
            revision=revision,
            user_agent=user_agent,
            commit_hash=commit_hash,
        )
        if index_file is not None and index_file.is_file():
            is_sharded = True

        # load model
        model_file = None
        if from_flax:
            raise NotImplementedError("loading flax checkpoint in mindspore model is not yet supported.")
        else:
            if is_sharded:
                sharded_ckpt_cached_folder, sharded_metadata = _get_checkpoint_shard_files(
                    pretrained_model_name_or_path,
                    index_file,
                    cache_dir=cache_dir,
                    proxies=proxies,
                    local_files_only=local_files_only,
                    token=token,
                    user_agent=user_agent,
                    revision=revision,
                    subfolder=subfolder or "",
                )

            elif use_safetensors and not is_sharded:
                try:
                    model_file = _get_model_file(
                        pretrained_model_name_or_path,
                        weights_name=_add_variant(SAFETENSORS_WEIGHTS_NAME, variant),
                        cache_dir=cache_dir,
                        force_download=force_download,
                        proxies=proxies,
                        local_files_only=local_files_only,
                        token=token,
                        revision=revision,
                        subfolder=subfolder,
                        user_agent=user_agent,
                        commit_hash=commit_hash,
                    )
                except IOError as e:
                    logger.error(f"An error occurred while trying to fetch {pretrained_model_name_or_path}: {e}")
                    if not allow_pickle:
                        raise
                    logger.warning(
                        "Defaulting to unsafe serialization. Pass `allow_pickle=False` to raise an error instead."
                    )

            if model_file is None and not is_sharded:
                model_file = _get_model_file(
                    pretrained_model_name_or_path,
                    weights_name=_add_variant(WEIGHTS_NAME, variant),
                    cache_dir=cache_dir,
                    force_download=force_download,
                    proxies=proxies,
                    local_files_only=local_files_only,
                    token=token,
                    revision=revision,
                    subfolder=subfolder,
                    user_agent=user_agent,
                    commit_hash=commit_hash,
                )

            model = cls.from_config(config, **unused_kwargs)

            if is_sharded:
                load_checkpoint_and_dispatch(
                    model,
                    index_file,  # TODO: check accelerate
                    dtype=mindspore_dtype,
                    strict=True,
                )
            else:
                state_dict = load_state_dict(model_file, variant=variant)
                model._convert_deprecated_attention_blocks(state_dict)

                model, missing_keys, unexpected_keys, mismatched_keys, error_msgs = cls._load_pretrained_model(
                    model,
                    state_dict,
                    model_file,
                    pretrained_model_name_or_path,
                    ignore_mismatched_sizes=ignore_mismatched_sizes,
                )

                loading_info = {
                    "missing_keys": missing_keys,
                    "unexpected_keys": unexpected_keys,
                    "mismatched_keys": mismatched_keys,
                    "error_msgs": error_msgs,
                }

        if mindspore_dtype is not None and not isinstance(mindspore_dtype, ms.Type):
            raise ValueError(
                f"{mindspore_dtype} needs to be of type `ms.Type`, e.g. `ms.float16`, but is {type(mindspore_dtype)}."
            )
        elif mindspore_dtype is not None:
            model = model.to(mindspore_dtype)

        model.register_to_config(_name_or_path=pretrained_model_name_or_path)

        # Set model in evaluation mode to deactivate DropOut modules by default
        model.set_train(False)
        if not is_sharded and output_loading_info:
            return model, loading_info

        return model

    @classmethod
    def _load_pretrained_model(
        cls,
        model,
        state_dict: OrderedDict,
        resolved_archive_file,
        pretrained_model_name_or_path: Union[str, os.PathLike],
        ignore_mismatched_sizes: bool = False,
    ):
        state_dict = _convert_state_dict(model, state_dict)
        # Retrieve missing & unexpected_keys
        model_state_dict = {k: v for k, v in model.parameters_and_names()}
        loaded_keys = list(state_dict.keys())

        expected_keys = list(model_state_dict.keys())

        original_loaded_keys = loaded_keys

        missing_keys = list(set(expected_keys) - set(loaded_keys))
        unexpected_keys = list(set(loaded_keys) - set(expected_keys))

        # Make sure we are able to load base models as well as derived models (with heads)
        model_to_load = model

        def _find_mismatched_keys(
            state_dict,
            model_state_dict,
            loaded_keys,
            ignore_mismatched_sizes,
        ):
            mismatched_keys = []
            if ignore_mismatched_sizes:
                for checkpoint_key in loaded_keys:
                    model_key = checkpoint_key

                    if (
                        model_key in model_state_dict
                        and state_dict[checkpoint_key].shape != model_state_dict[model_key].shape
                    ):
                        mismatched_keys.append(
                            (checkpoint_key, state_dict[checkpoint_key].shape, model_state_dict[model_key].shape)
                        )
                        del state_dict[checkpoint_key]
            return mismatched_keys

        if state_dict is not None:
            # Whole checkpoint
            mismatched_keys = _find_mismatched_keys(
                state_dict,
                model_state_dict,
                original_loaded_keys,
                ignore_mismatched_sizes,
            )
            error_msgs = _load_state_dict_into_model(model_to_load, state_dict)

        if len(error_msgs) > 0:
            error_msg = "\n\t".join(error_msgs)
            if "size mismatch" in error_msg:
                error_msg += (
                    "\n\tYou may consider adding `ignore_mismatched_sizes=True` in the model `from_pretrained` method."
                )
            raise RuntimeError(f"Error(s) in loading state_dict for {model.__class__.__name__}:\n\t{error_msg}")

        if len(unexpected_keys) > 0:
            logger.warning(
                f"Some weights of the model checkpoint at {pretrained_model_name_or_path} were not used when"
                f" initializing {model.__class__.__name__}: {unexpected_keys}\n- This IS expected if you are"
                f" initializing {model.__class__.__name__} from the checkpoint of a model trained on another task"
                " or with another architecture (e.g. initializing a BertForSequenceClassification model from a"
                " BertForPreTraining model).\n- This IS NOT expected if you are initializing"
                f" {model.__class__.__name__} from the checkpoint of a model that you expect to be exactly"
                " identical (initializing a BertForSequenceClassification model from a"
                " BertForSequenceClassification model)."
            )
        else:
            logger.info(f"All model checkpoint weights were used when initializing {model.__class__.__name__}.\n")
        if len(missing_keys) > 0:
            logger.warning(
                f"Some weights of {model.__class__.__name__} were not initialized from the model checkpoint at"
                f" {pretrained_model_name_or_path} and are newly initialized: {missing_keys}\nYou should probably"
                " TRAIN this model on a down-stream task to be able to use it for predictions and inference."
            )
        elif len(mismatched_keys) == 0:
            logger.info(
                f"All the weights of {model.__class__.__name__} were initialized from the model checkpoint at"
                f" {pretrained_model_name_or_path}.\nIf your task is similar to the task the model of the"
                f" checkpoint was trained on, you can already use {model.__class__.__name__} for predictions"
                " without further training."
            )
        if len(mismatched_keys) > 0:
            mismatched_warning = "\n".join(
                [
                    f"- {key}: found shape {shape1} in the checkpoint and {shape2} in the model instantiated"
                    for key, shape1, shape2 in mismatched_keys
                ]
            )
            logger.warning(
                f"Some weights of {model.__class__.__name__} were not initialized from the model checkpoint at"
                f" {pretrained_model_name_or_path} and are newly initialized because the shapes did not"
                f" match:\n{mismatched_warning}\nYou should probably TRAIN this model on a down-stream task to be"
                " able to use it for predictions and inference."
            )

        return model, missing_keys, unexpected_keys, mismatched_keys, error_msgs

    @classmethod
    def _get_signature_keys(cls, obj):
        parameters = inspect.signature(obj.__init__).parameters
        required_parameters = {k: v for k, v in parameters.items() if v.default == inspect._empty}
        optional_parameters = set({k for k, v in parameters.items() if v.default != inspect._empty})
        expected_modules = set(required_parameters.keys()) - {"self"}

        return expected_modules, optional_parameters

    def to(self, dtype: Optional[ms.Type] = None):
        for p in self.get_parameters():
            p.set_dtype(dtype)
        return self

    def float(self):
        for p in self.get_parameters():
            p.set_dtype(ms.float32)
        return self

    def half(self):
        for p in self.get_parameters():
            p.set_dtype(ms.float16)
        return self

    @property
    def dtype(self) -> ms.Type:
        """
        `mindspore.Type`: The dtype of the module (assuming that all the module parameters have the same dtype).
        """
        return get_parameter_dtype(self)

    def num_parameters(self, only_trainable: bool = False, exclude_embeddings: bool = False) -> int:
        """
        Get number of (trainable or non-embedding) parameters in the module.

        Args:
            only_trainable (`bool`, *optional*, defaults to `False`):
                Whether or not to return only the number of trainable parameters.
            exclude_embeddings (`bool`, *optional*, defaults to `False`):
                Whether or not to return only the number of non-embedding parameters.

        Returns:
            `int`: The number of parameters.

        Example:

        ```py
        from mindone.diffusers import UNet2DConditionModel

        model_id = "runwayml/stable-diffusion-v1-5"
        unet = UNet2DConditionModel.from_pretrained(model_id, subfolder="unet")
        unet.num_parameters(only_trainable=True)
        859520964
        ```
        """

        if exclude_embeddings:
            embedding_param_names = [
                f"{name}.weight"
                for name, module_type in self.cells_and_names()
                if isinstance(module_type, nn.Embedding)
            ]
            non_embedding_parameters = [
                parameter for name, parameter in self.parameters_and_names() if name not in embedding_param_names
            ]
            return sum(p.numel() for p in non_embedding_parameters if p.requires_grad or not only_trainable)
        else:
            return sum(p.numel() for p in self.get_parameters() if p.requires_grad or not only_trainable)

    def _convert_deprecated_attention_blocks(self, state_dict: OrderedDict) -> None:
        deprecated_attention_block_paths = []

        def recursive_find_attn_block(name, module):
            if hasattr(module, "_from_deprecated_attn_block") and module._from_deprecated_attn_block:
                deprecated_attention_block_paths.append(name)

            for sub_name, sub_module in module.name_cells().items():
                sub_name = sub_name if name == "" else f"{name}.{sub_name}"
                recursive_find_attn_block(sub_name, sub_module)

        recursive_find_attn_block("", self)

        # NOTE: we have to check if the deprecated parameters are in the state dict
        # because it is possible we are loading from a state dict that was already
        # converted

        for path in deprecated_attention_block_paths:
            # group_norm path stays the same

            # query -> to_q
            if f"{path}.query.weight" in state_dict:
                state_dict[f"{path}.to_q.weight"] = state_dict.pop(f"{path}.query.weight")
            if f"{path}.query.bias" in state_dict:
                state_dict[f"{path}.to_q.bias"] = state_dict.pop(f"{path}.query.bias")

            # key -> to_k
            if f"{path}.key.weight" in state_dict:
                state_dict[f"{path}.to_k.weight"] = state_dict.pop(f"{path}.key.weight")
            if f"{path}.key.bias" in state_dict:
                state_dict[f"{path}.to_k.bias"] = state_dict.pop(f"{path}.key.bias")

            # value -> to_v
            if f"{path}.value.weight" in state_dict:
                state_dict[f"{path}.to_v.weight"] = state_dict.pop(f"{path}.value.weight")
            if f"{path}.value.bias" in state_dict:
                state_dict[f"{path}.to_v.bias"] = state_dict.pop(f"{path}.value.bias")

            # proj_attn -> to_out.0
            if f"{path}.proj_attn.weight" in state_dict:
                state_dict[f"{path}.to_out.0.weight"] = state_dict.pop(f"{path}.proj_attn.weight")
            if f"{path}.proj_attn.bias" in state_dict:
                state_dict[f"{path}.to_out.0.bias"] = state_dict.pop(f"{path}.proj_attn.bias")

mindone.diffusers.ModelMixin.dtype: ms.Type property

mindspore.Type: The dtype of the module (assuming that all the module parameters have the same dtype).

mindone.diffusers.ModelMixin.is_gradient_checkpointing: bool property

Whether gradient checkpointing is activated for this model or not.

mindone.diffusers.ModelMixin.__getattr__(name)

The only reason we overwrite getattr here is to gracefully deprecate accessing config attributes directly. See https://github.com/huggingface/diffusers/pull/3129 We need to overwrite getattr here in addition so that we don't trigger nn.Cell's getattr': https://pytorch.org/docs/stable/_modules/torch/nn/modules/module.html#Module

Source code in mindone/diffusers/models/modeling_utils.py

def __getattr__(self, name: str) -> Any:
    """The only reason we overwrite `getattr` here is to gracefully deprecate accessing
    config attributes directly. See https://github.com/huggingface/diffusers/pull/3129 We need to overwrite
    __getattr__ here in addition so that we don't trigger `nn.Cell`'s __getattr__':
    https://pytorch.org/docs/stable/_modules/torch/nn/modules/module.html#Module
    """

    is_in_config = "_internal_dict" in self.__dict__ and hasattr(self.__dict__["_internal_dict"], name)
    is_attribute = name in self.__dict__

    if is_in_config and not is_attribute:
        deprecation_message = f"Accessing config attribute `{name}` directly via '{type(self).__name__}' object attribute is deprecated. Please access '{name}' over '{type(self).__name__}'s config object instead, e.g. 'unet.config.{name}'."  # noqa: E501
        deprecate("direct config name access", "1.0.0", deprecation_message, standard_warn=False, stacklevel=3)
        return self._internal_dict[name]

    # call PyTorch's https://pytorch.org/docs/stable/_modules/torch/nn/modules/module.html#Module
    return super().__getattr__(name)

mindone.diffusers.ModelMixin.disable_gradient_checkpointing()

Deactivates gradient checkpointing for the current model (may be referred to as activation checkpointing or checkpoint activations in other frameworks).

Source code in mindone/diffusers/models/modeling_utils.py

def disable_gradient_checkpointing(self) -> None:
    """
    Deactivates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or
    *checkpoint activations* in other frameworks).
    """
    if self._supports_gradient_checkpointing:
        self.apply(partial(self._set_gradient_checkpointing, value=False))

mindone.diffusers.ModelMixin.disable_xformers_memory_efficient_attention()

Disable memory efficient attention from xFormers.

Source code in mindone/diffusers/models/modeling_utils.py

def disable_xformers_memory_efficient_attention(self) -> None:
    r"""
    Disable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).
    """
    self.set_use_memory_efficient_attention_xformers(False)

mindone.diffusers.ModelMixin.enable_flash_sdp(enabled)

.. warning:: This flag is beta and subject to change.

Enables or disables flash scaled dot product attention.

Source code in mindone/diffusers/models/modeling_utils.py

def enable_flash_sdp(self, enabled: bool):
    r"""
    .. warning:: This flag is beta and subject to change.

    Enables or disables flash scaled dot product attention.
    """

    # Recursively walk through all the children.
    # Any children which exposes the enable_flash_sdp method
    # gets the message
    def fn_recursive_set_mem_eff(module: nn.Cell):
        if hasattr(module, "enable_flash_sdp"):
            module.enable_flash_sdp(enabled)

        for child in module.cells():
            fn_recursive_set_mem_eff(child)

    for module in self.cells():
        if isinstance(module, nn.Cell):
            fn_recursive_set_mem_eff(module)

mindone.diffusers.ModelMixin.enable_gradient_checkpointing()

Activates gradient checkpointing for the current model (may be referred to as activation checkpointing or checkpoint activations in other frameworks).

Source code in mindone/diffusers/models/modeling_utils.py

def enable_gradient_checkpointing(self) -> None:
    """
    Activates gradient checkpointing for the current model (may be referred to as *activation checkpointing* or
    *checkpoint activations* in other frameworks).
    """
    if not self._supports_gradient_checkpointing:
        raise ValueError(f"{self.__class__.__name__} does not support gradient checkpointing.")
    self.apply(partial(self._set_gradient_checkpointing, value=True))

mindone.diffusers.ModelMixin.enable_xformers_memory_efficient_attention(attention_op=None)

Enable memory efficient attention from xFormers.

When this option is enabled, you should observe lower GPU memory usage and a potential speed up during inference. Speed up during training is not guaranteed.

⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes precedent.

PARAMETER	DESCRIPTION
attention_op	Not supported for now. TYPE: `Callable`, *optional* DEFAULT: None

>>> import mindspore as ms
>>> from mindone.diffusers import UNet2DConditionModel

>>> model = UNet2DConditionModel.from_pretrained(
...     "stabilityai/stable-diffusion-2-1", subfolder="unet", mindspore_dtype=ms.float16
... )
>>> model.enable_xformers_memory_efficient_attention()

Source code in mindone/diffusers/models/modeling_utils.py

def enable_xformers_memory_efficient_attention(self, attention_op: Optional[Callable] = None) -> None:
    r"""
    Enable memory efficient attention from [xFormers](https://facebookresearch.github.io/xformers/).

    When this option is enabled, you should observe lower GPU memory usage and a potential speed up during
    inference. Speed up during training is not guaranteed.

    <Tip warning={true}>

    ⚠️ When memory efficient attention and sliced attention are both enabled, memory efficient attention takes
    precedent.

    </Tip>

    Parameters:
        attention_op (`Callable`, *optional*):
            Not supported for now.

    Examples:

    ```py
    >>> import mindspore as ms
    >>> from mindone.diffusers import UNet2DConditionModel

    >>> model = UNet2DConditionModel.from_pretrained(
    ...     "stabilityai/stable-diffusion-2-1", subfolder="unet", mindspore_dtype=ms.float16
    ... )
    >>> model.enable_xformers_memory_efficient_attention()
    ```
    """
    self.set_use_memory_efficient_attention_xformers(True, attention_op)

mindone.diffusers.ModelMixin.from_pretrained(pretrained_model_name_or_path, **kwargs) classmethod

Instantiate a pretrained PyTorch model from a pretrained model configuration.

The model is set in evaluation mode - model.eval() - by default, and dropout modules are deactivated. To train the model, set it back in training mode with model.train().

PARAMETER	DESCRIPTION
pretrained_model_name_or_path	Can be either: - A string, the *model id* (for example `google/ddpm-celebahq-256`) of a pretrained model hosted on the Hub. - A path to a *directory* (for example `./my_model_directory`) containing the model weights saved with [`~ModelMixin.save_pretrained`]. TYPE: `str` or `os.PathLike`, *optional*
cache_dir	Path to a directory where a downloaded pretrained model configuration is cached if the standard cache is not used. TYPE: `Union[str, os.PathLike]`, *optional*
mindspore_dtype	Override the default mindspore.Type and load the model with another dtype. If "auto" is passed, the dtype is automatically derived from the model's weights. TYPE: `str` or `mindspore.Type`, *optional*
force_download	Whether or not to force the (re-)download of the model weights and configuration files, overriding the cached versions if they exist. TYPE: `bool`, *optional*, defaults to `False`
proxies	A dictionary of proxy servers to use by protocol or endpoint, for example, {'http': 'foo.bar:3128', 'http://hostname': 'foo.bar:4012'}. The proxies are used on each request. TYPE: `Dict[str, str]`, *optional*
output_loading_info	Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages. TYPE: `bool`, *optional*, defaults to `False`
local_files_only(`bool`,	Whether to only load local model weights and configuration files or not. If set to True, the model won't be downloaded from the Hub. TYPE: *optional*, defaults to `False`
token	The token to use as HTTP bearer authorization for remote files. If True, the token generated from diffusers-cli login (stored in ~/.huggingface) is used. TYPE: `str` or *bool*, *optional*
revision	The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier allowed by Git. TYPE: `str`, *optional*, defaults to `"main"`
from_flax	Load the model weights from a Flax checkpoint save file. TYPE: `bool`, *optional*, defaults to `False`
subfolder	The subfolder location of a model file within a larger model repository on the Hub or locally. TYPE: `str`, *optional*, defaults to `""`
mirror	Mirror source to resolve accessibility issues if you're downloading a model in China. We do not guarantee the timeliness or safety of the source, and you should refer to the mirror site for more information. TYPE: `str`, *optional*
variant	Load weights from a specified variant filename such as "fp16" or "ema". This is ignored when loading from_flax. TYPE: `str`, *optional*
use_safetensors	If set to None, the safetensors weights are downloaded if they're available and if the safetensors library is installed. If set to True, the model is forcibly loaded from safetensors weights. If set to False, safetensors weights are not loaded. TYPE: `bool`, *optional*, defaults to `None`

To use private or gated models, log-in with huggingface-cli login. You can also activate the special "offline-mode" to use this method in a firewalled environment.

Example:

from mindone.diffusers import UNet2DConditionModel

unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet")

If you get the error message below, you need to finetune the weights for your downstream task:

Some weights of UNet2DConditionModel were not initialized from the model checkpoint at
runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
- conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.

Source code in mindone/diffusers/models/modeling_utils.py

@classmethod
@validate_hf_hub_args
def from_pretrained(cls, pretrained_model_name_or_path: Optional[Union[str, os.PathLike]], **kwargs):
    r"""
    Instantiate a pretrained PyTorch model from a pretrained model configuration.

    The model is set in evaluation mode - `model.eval()` - by default, and dropout modules are deactivated. To
    train the model, set it back in training mode with `model.train()`.

    Parameters:
        pretrained_model_name_or_path (`str` or `os.PathLike`, *optional*):
            Can be either:

                - A string, the *model id* (for example `google/ddpm-celebahq-256`) of a pretrained model hosted on
                  the Hub.
                - A path to a *directory* (for example `./my_model_directory`) containing the model weights saved
                  with [`~ModelMixin.save_pretrained`].

        cache_dir (`Union[str, os.PathLike]`, *optional*):
            Path to a directory where a downloaded pretrained model configuration is cached if the standard cache
            is not used.
        mindspore_dtype (`str` or `mindspore.Type`, *optional*):
            Override the default `mindspore.Type` and load the model with another dtype. If `"auto"` is passed, the
            dtype is automatically derived from the model's weights.
        force_download (`bool`, *optional*, defaults to `False`):
            Whether or not to force the (re-)download of the model weights and configuration files, overriding the
            cached versions if they exist.
        proxies (`Dict[str, str]`, *optional*):
            A dictionary of proxy servers to use by protocol or endpoint, for example, `{'http': 'foo.bar:3128',
            'http://hostname': 'foo.bar:4012'}`. The proxies are used on each request.
        output_loading_info (`bool`, *optional*, defaults to `False`):
            Whether or not to also return a dictionary containing missing keys, unexpected keys and error messages.
        local_files_only(`bool`, *optional*, defaults to `False`):
            Whether to only load local model weights and configuration files or not. If set to `True`, the model
            won't be downloaded from the Hub.
        token (`str` or *bool*, *optional*):
            The token to use as HTTP bearer authorization for remote files. If `True`, the token generated from
            `diffusers-cli login` (stored in `~/.huggingface`) is used.
        revision (`str`, *optional*, defaults to `"main"`):
            The specific model version to use. It can be a branch name, a tag name, a commit id, or any identifier
            allowed by Git.
        from_flax (`bool`, *optional*, defaults to `False`):
            Load the model weights from a Flax checkpoint save file.
        subfolder (`str`, *optional*, defaults to `""`):
            The subfolder location of a model file within a larger model repository on the Hub or locally.
        mirror (`str`, *optional*):
            Mirror source to resolve accessibility issues if you're downloading a model in China. We do not
            guarantee the timeliness or safety of the source, and you should refer to the mirror site for more
            information.
        variant (`str`, *optional*):
            Load weights from a specified `variant` filename such as `"fp16"` or `"ema"`. This is ignored when
            loading `from_flax`.
        use_safetensors (`bool`, *optional*, defaults to `None`):
            If set to `None`, the `safetensors` weights are downloaded if they're available **and** if the
            `safetensors` library is installed. If set to `True`, the model is forcibly loaded from `safetensors`
            weights. If set to `False`, `safetensors` weights are not loaded.

    <Tip>

    To use private or [gated models](https://huggingface.co/docs/hub/models-gated#gated-models), log-in with
    `huggingface-cli login`. You can also activate the special
    ["offline-mode"](https://huggingface.co/diffusers/installation.html#offline-mode) to use this method in a
    firewalled environment.

    </Tip>

    Example:

    ```py
    from mindone.diffusers import UNet2DConditionModel

    unet = UNet2DConditionModel.from_pretrained("runwayml/stable-diffusion-v1-5", subfolder="unet")
    ```

    If you get the error message below, you need to finetune the weights for your downstream task:

    ```bash
    Some weights of UNet2DConditionModel were not initialized from the model checkpoint at
    runwayml/stable-diffusion-v1-5 and are newly initialized because the shapes did not match:
    - conv_in.weight: found shape torch.Size([320, 4, 3, 3]) in the checkpoint and torch.Size([320, 9, 3, 3]) in the model instantiated
    You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
    ```
    """
    cache_dir = kwargs.pop("cache_dir", None)
    ignore_mismatched_sizes = kwargs.pop("ignore_mismatched_sizes", False)
    force_download = kwargs.pop("force_download", False)
    from_flax = kwargs.pop("from_flax", False)
    proxies = kwargs.pop("proxies", None)
    output_loading_info = kwargs.pop("output_loading_info", False)
    local_files_only = kwargs.pop("local_files_only", None)
    token = kwargs.pop("token", None)
    revision = kwargs.pop("revision", None)
    mindspore_dtype = kwargs.pop("mindspore_dtype", None)
    subfolder = kwargs.pop("subfolder", None)
    variant = kwargs.pop("variant", None)
    use_safetensors = kwargs.pop("use_safetensors", None)

    allow_pickle = False
    if use_safetensors is None:
        use_safetensors = True
        allow_pickle = True

    # Load config if we don't provide a configuration
    config_path = pretrained_model_name_or_path

    user_agent = {
        "diffusers": __version__,
        "file_type": "model",
        "framework": "pytorch",
    }

    # load config
    config, unused_kwargs, commit_hash = cls.load_config(
        config_path,
        cache_dir=cache_dir,
        return_unused_kwargs=True,
        return_commit_hash=True,
        force_download=force_download,
        proxies=proxies,
        local_files_only=local_files_only,
        token=token,
        revision=revision,
        subfolder=subfolder,
        user_agent=user_agent,
        **kwargs,
    )

    # Determine if we're loading from a directory of sharded checkpoints.
    is_sharded = False
    index_file = None
    is_local = os.path.isdir(pretrained_model_name_or_path)
    index_file = _fetch_index_file(
        is_local=is_local,
        pretrained_model_name_or_path=pretrained_model_name_or_path,
        subfolder=subfolder or "",
        use_safetensors=use_safetensors,
        cache_dir=cache_dir,
        variant=variant,
        force_download=force_download,
        proxies=proxies,
        local_files_only=local_files_only,
        token=token,
        revision=revision,
        user_agent=user_agent,
        commit_hash=commit_hash,
    )
    if index_file is not None and index_file.is_file():
        is_sharded = True

    # load model
    model_file = None
    if from_flax:
        raise NotImplementedError("loading flax checkpoint in mindspore model is not yet supported.")
    else:
        if is_sharded:
            sharded_ckpt_cached_folder, sharded_metadata = _get_checkpoint_shard_files(
                pretrained_model_name_or_path,
                index_file,
                cache_dir=cache_dir,
                proxies=proxies,
                local_files_only=local_files_only,
                token=token,
                user_agent=user_agent,
                revision=revision,
                subfolder=subfolder or "",
            )

        elif use_safetensors and not is_sharded:
            try:
                model_file = _get_model_file(
                    pretrained_model_name_or_path,
                    weights_name=_add_variant(SAFETENSORS_WEIGHTS_NAME, variant),
                    cache_dir=cache_dir,
                    force_download=force_download,
                    proxies=proxies,
                    local_files_only=local_files_only,
                    token=token,
                    revision=revision,
                    subfolder=subfolder,
                    user_agent=user_agent,
                    commit_hash=commit_hash,
                )
            except IOError as e:
                logger.error(f"An error occurred while trying to fetch {pretrained_model_name_or_path}: {e}")
                if not allow_pickle:
                    raise
                logger.warning(
                    "Defaulting to unsafe serialization. Pass `allow_pickle=False` to raise an error instead."
                )

        if model_file is None and not is_sharded:
            model_file = _get_model_file(
                pretrained_model_name_or_path,
                weights_name=_add_variant(WEIGHTS_NAME, variant),
                cache_dir=cache_dir,
                force_download=force_download,
                proxies=proxies,
                local_files_only=local_files_only,
                token=token,
                revision=revision,
                subfolder=subfolder,
                user_agent=user_agent,
                commit_hash=commit_hash,
            )

        model = cls.from_config(config, **unused_kwargs)

        if is_sharded:
            load_checkpoint_and_dispatch(
                model,
                index_file,  # TODO: check accelerate
                dtype=mindspore_dtype,
                strict=True,
            )
        else:
            state_dict = load_state_dict(model_file, variant=variant)
            model._convert_deprecated_attention_blocks(state_dict)

            model, missing_keys, unexpected_keys, mismatched_keys, error_msgs = cls._load_pretrained_model(
                model,
                state_dict,
                model_file,
                pretrained_model_name_or_path,
                ignore_mismatched_sizes=ignore_mismatched_sizes,
            )

            loading_info = {
                "missing_keys": missing_keys,
                "unexpected_keys": unexpected_keys,
                "mismatched_keys": mismatched_keys,
                "error_msgs": error_msgs,
            }

    if mindspore_dtype is not None and not isinstance(mindspore_dtype, ms.Type):
        raise ValueError(
            f"{mindspore_dtype} needs to be of type `ms.Type`, e.g. `ms.float16`, but is {type(mindspore_dtype)}."
        )
    elif mindspore_dtype is not None:
        model = model.to(mindspore_dtype)

    model.register_to_config(_name_or_path=pretrained_model_name_or_path)

    # Set model in evaluation mode to deactivate DropOut modules by default
    model.set_train(False)
    if not is_sharded and output_loading_info:
        return model, loading_info

    return model

mindone.diffusers.ModelMixin.num_parameters(only_trainable=False, exclude_embeddings=False)

Get number of (trainable or non-embedding) parameters in the module.

PARAMETER	DESCRIPTION
only_trainable	Whether or not to return only the number of trainable parameters. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
exclude_embeddings	Whether or not to return only the number of non-embedding parameters. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False

RETURNS	DESCRIPTION
int	int: The number of parameters.

from mindone.diffusers import UNet2DConditionModel

model_id = "runwayml/stable-diffusion-v1-5"
unet = UNet2DConditionModel.from_pretrained(model_id, subfolder="unet")
unet.num_parameters(only_trainable=True)
859520964

Source code in mindone/diffusers/models/modeling_utils.py

def num_parameters(self, only_trainable: bool = False, exclude_embeddings: bool = False) -> int:
    """
    Get number of (trainable or non-embedding) parameters in the module.

    Args:
        only_trainable (`bool`, *optional*, defaults to `False`):
            Whether or not to return only the number of trainable parameters.
        exclude_embeddings (`bool`, *optional*, defaults to `False`):
            Whether or not to return only the number of non-embedding parameters.

    Returns:
        `int`: The number of parameters.

    Example:

    ```py
    from mindone.diffusers import UNet2DConditionModel

    model_id = "runwayml/stable-diffusion-v1-5"
    unet = UNet2DConditionModel.from_pretrained(model_id, subfolder="unet")
    unet.num_parameters(only_trainable=True)
    859520964
    ```
    """

    if exclude_embeddings:
        embedding_param_names = [
            f"{name}.weight"
            for name, module_type in self.cells_and_names()
            if isinstance(module_type, nn.Embedding)
        ]
        non_embedding_parameters = [
            parameter for name, parameter in self.parameters_and_names() if name not in embedding_param_names
        ]
        return sum(p.numel() for p in non_embedding_parameters if p.requires_grad or not only_trainable)
    else:
        return sum(p.numel() for p in self.get_parameters() if p.requires_grad or not only_trainable)

mindone.diffusers.ModelMixin.save_pretrained(save_directory, is_main_process=True, save_function=None, safe_serialization=True, variant=None, max_shard_size='10GB', push_to_hub=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.

PARAMETER	DESCRIPTION
save_directory	Directory to save a model and its configuration file to. Will be created if it doesn't exist. TYPE: `str` or `os.PathLike`
is_main_process	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. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
save_function	The function to use to save the state dictionary. Useful during distributed training when you need to replace mindspore.save_checkpoint with another method. Can be configured with the environment variable DIFFUSERS_SAVE_MODE. TYPE: `Callable` DEFAULT: None
safe_serialization	Whether to save the model using safetensors or the traditional PyTorch way with pickle. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
variant	If specified, weights are saved in the format pytorch_model.<variant>.bin. TYPE: `str`, *optional* DEFAULT: None
max_shard_size	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). TYPE: `int` or `str`, defaults to `"10GB"` DEFAULT: '10GB'
push_to_hub	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). TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
kwargs	Additional keyword arguments passed along to the [~utils.PushToHubMixin.push_to_hub] method. TYPE: `Dict[str, Any]`, *optional* DEFAULT: {}

Source code in mindone/diffusers/models/modeling_utils.py

def save_pretrained(
    self,
    save_directory: Union[str, os.PathLike],
    is_main_process: bool = True,
    save_function: Optional[Callable] = None,
    safe_serialization: bool = True,
    variant: Optional[str] = None,
    max_shard_size: Union[int, str] = "10GB",
    push_to_hub: 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 `mindspore.save_checkpoint` 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

    weights_name = SAFETENSORS_WEIGHTS_NAME if safe_serialization else WEIGHTS_NAME
    weights_name = _add_variant(weights_name, variant)
    weight_name_split = weights_name.split(".")
    if len(weight_name_split) in [2, 3]:
        weights_name_pattern = weight_name_split[0] + "{suffix}." + ".".join(weight_name_split[1:])
    else:
        raise ValueError(f"Invalid {weights_name} provided.")

    os.makedirs(save_directory, exist_ok=True)

    if push_to_hub:
        commit_message = kwargs.pop("commit_message", None)
        private = kwargs.pop("private", False)
        create_pr = kwargs.pop("create_pr", False)
        token = kwargs.pop("token", None)
        repo_id = kwargs.pop("repo_id", save_directory.split(os.path.sep)[-1])
        repo_id = create_repo(repo_id, exist_ok=True, private=private, token=token).repo_id

    # Only save the model itself if we are using distributed training
    model_to_save = self

    # Attach architecture to the config
    # Save the config
    if is_main_process:
        model_to_save.save_config(save_directory)

    # Save the model
    state_dict = {k: v for k, v in model_to_save.parameters_and_names()}

    # Save the model
    state_dict_split = split_torch_state_dict_into_shards(
        state_dict, max_shard_size=max_shard_size, filename_pattern=weights_name_pattern
    )

    # Clean the folder from a previous save
    if is_main_process:
        for filename in os.listdir(save_directory):
            if filename in state_dict_split.filename_to_tensors.keys():
                continue
            full_filename = os.path.join(save_directory, filename)
            if not os.path.isfile(full_filename):
                continue
            weights_without_ext = weights_name_pattern.replace(".bin", "").replace(".safetensors", "")
            weights_without_ext = weights_without_ext.replace("{suffix}", "")
            filename_without_ext = filename.replace(".bin", "").replace(".safetensors", "")
            # make sure that file to be deleted matches format of sharded file, e.g. pytorch_model-00001-of-00005
            if (
                filename.startswith(weights_without_ext)
                and _REGEX_SHARD.fullmatch(filename_without_ext) is not None
            ):
                os.remove(full_filename)

    for filename, tensors in state_dict_split.filename_to_tensors.items():
        shard = {tensor: state_dict[tensor] for tensor in tensors}
        filepath = os.path.join(save_directory, filename)
        if safe_serialization:
            # At some point we will need to deal better with save_function (used for TPU and other distributed
            # joyfulness), but for now this enough.
            safe_save_file(shard, filepath, metadata={"format": "np"})
        else:
            ms.save_checkpoint(shard, filepath)

    if state_dict_split.is_sharded:
        index = {
            "metadata": state_dict_split.metadata,
            "weight_map": state_dict_split.tensor_to_filename,
        }
        save_index_file = SAFE_WEIGHTS_INDEX_NAME if safe_serialization else WEIGHTS_INDEX_NAME
        save_index_file = os.path.join(save_directory, _add_variant(save_index_file, variant))
        # Save the index as well
        with open(save_index_file, "w", encoding="utf-8") as f:
            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
            f.write(content)
        logger.info(
            f"The model is bigger than the maximum size per checkpoint ({max_shard_size}) and is going to be "
            f"split in {len(state_dict_split.filename_to_tensors)} checkpoint shards. You can find where each parameters has been saved in the "
            f"index located at {save_index_file}."
        )
    else:
        path_to_weights = os.path.join(save_directory, weights_name)
        logger.info(f"Model weights saved in {path_to_weights}")

    if push_to_hub:
        # Create a new empty model card and eventually tag it
        model_card = load_or_create_model_card(repo_id, token=token)
        model_card = populate_model_card(model_card)
        model_card.save(Path(save_directory, "README.md").as_posix())

        self._upload_folder(
            save_directory,
            repo_id,
            token=token,
            commit_message=commit_message,
            create_pr=create_pr,
        )

mindone.diffusers.ModelMixin.set_flash_attention_force_cast_dtype(force_cast_dtype)

Since the flash-attention operator in MindSpore only supports float16 and bfloat16 data types, we need to manually set whether to force data type conversion.

When the attention interface encounters data of an unsupported data type, if force_cast_dtype is not None, the function will forcibly convert the data to force_cast_dtype for computation and then restore it to the original data type afterward. If force_cast_dtype is None, it will fall back to the original attention calculation using mathematical formulas.

PARAMETER	DESCRIPTION
force_cast_dtype	The data type to which the input data should be forcibly converted. If None, no forced TYPE: Optional

Source code in mindone/diffusers/models/modeling_utils.py

def set_flash_attention_force_cast_dtype(self, force_cast_dtype: Optional[ms.Type]):
    r"""
    Since the flash-attention operator in MindSpore only supports float16 and bfloat16 data types, we need to manually
    set whether to force data type conversion.

    When the attention interface encounters data of an unsupported data type,
    if `force_cast_dtype` is not None, the function will forcibly convert the data to `force_cast_dtype` for computation
    and then restore it to the original data type afterward. If `force_cast_dtype` is None, it will fall back to the
    original attention calculation using mathematical formulas.

    Parameters:
        force_cast_dtype (Optional): The data type to which the input data should be forcibly converted. If None, no forced
        conversion is performed.
    """

    # Recursively walk through all the children.
    # Any children which exposes the set_flash_attention_force_cast_dtype method
    # gets the message
    def fn_recursive_set_mem_eff(module: nn.Cell):
        if hasattr(module, "set_flash_attention_force_cast_dtype"):
            module.set_flash_attention_force_cast_dtype(force_cast_dtype)

        for child in module.cells():
            fn_recursive_set_mem_eff(child)

    for module in self.cells():
        if isinstance(module, nn.Cell):
            fn_recursive_set_mem_eff(module)

mindone.diffusers.utils.PushToHubMixin

A Mixin to push a model, scheduler, or pipeline to the Hugging Face Hub.

Source code in mindone/diffusers/utils/hub_utils.py

class PushToHubMixin:
    """
    A Mixin to push a model, scheduler, or pipeline to the Hugging Face Hub.
    """

    def _upload_folder(
        self,
        working_dir: Union[str, os.PathLike],
        repo_id: str,
        token: Optional[str] = None,
        commit_message: Optional[str] = None,
        create_pr: bool = False,
    ):
        """
        Uploads all files in `working_dir` to `repo_id`.
        """
        if commit_message is None:
            if "Model" in self.__class__.__name__:
                commit_message = "Upload model"
            elif "Scheduler" in self.__class__.__name__:
                commit_message = "Upload scheduler"
            else:
                commit_message = f"Upload {self.__class__.__name__}"

        logger.info(f"Uploading the files of {working_dir} to {repo_id}.")
        return upload_folder(
            repo_id=repo_id, folder_path=working_dir, token=token, commit_message=commit_message, create_pr=create_pr
        )

    def push_to_hub(
        self,
        repo_id: str,
        commit_message: Optional[str] = None,
        private: Optional[bool] = None,
        token: Optional[str] = None,
        create_pr: bool = False,
        safe_serialization: bool = True,
        variant: Optional[str] = None,
    ) -> str:
        """
        Upload model, scheduler, or pipeline files to the 🤗 Hugging Face Hub.

        Parameters:
            repo_id (`str`):
                The name of the repository you want to push your model, scheduler, or pipeline files to. It should
                contain your organization name when pushing to an organization. `repo_id` can also be a path to a local
                directory.
            commit_message (`str`, *optional*):
                Message to commit while pushing. Default to `"Upload {object}"`.
            private (`bool`, *optional*):
                Whether or not the repository created should be private.
            token (`str`, *optional*):
                The token to use as HTTP bearer authorization for remote files. The token generated when running
                `huggingface-cli login` (stored in `~/.huggingface`).
            create_pr (`bool`, *optional*, defaults to `False`):
                Whether or not to create a PR with the uploaded files or directly commit.
            safe_serialization (`bool`, *optional*, defaults to `True`):
                Whether or not to convert the model weights to the `safetensors` format.
            variant (`str`, *optional*):
                If specified, weights are saved in the format `pytorch_model.<variant>.bin`.

        Examples:

        ```python
        from mindone.diffusers import UNet2DConditionModel

        unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-2", subfolder="unet")

        # Push the `unet` to your namespace with the name "my-finetuned-unet".
        unet.push_to_hub("my-finetuned-unet")

        # Push the `unet` to an organization with the name "my-finetuned-unet".
        unet.push_to_hub("your-org/my-finetuned-unet")
        ```
        """
        repo_id = create_repo(repo_id, private=private, token=token, exist_ok=True).repo_id

        # Create a new empty model card and eventually tag it
        model_card = load_or_create_model_card(repo_id, token=token)
        model_card = populate_model_card(model_card)

        # Save all files.
        save_kwargs = {"safe_serialization": safe_serialization}
        if "Scheduler" not in self.__class__.__name__:
            save_kwargs.update({"variant": variant})

        with tempfile.TemporaryDirectory() as tmpdir:
            self.save_pretrained(tmpdir, **save_kwargs)

            # Update model card if needed:
            model_card.save(os.path.join(tmpdir, "README.md"))

            return self._upload_folder(
                tmpdir,
                repo_id,
                token=token,
                commit_message=commit_message,
                create_pr=create_pr,
            )

mindone.diffusers.utils.PushToHubMixin.push_to_hub(repo_id, commit_message=None, private=None, token=None, create_pr=False, safe_serialization=True, variant=None)

Upload model, scheduler, or pipeline files to the 🤗 Hugging Face Hub.

PARAMETER	DESCRIPTION
repo_id	The name of the repository you want to push your model, scheduler, or pipeline files to. It should contain your organization name when pushing to an organization. repo_id can also be a path to a local directory. TYPE: `str`
commit_message	Message to commit while pushing. Default to "Upload {object}". TYPE: `str`, *optional* DEFAULT: None
private	Whether or not the repository created should be private. TYPE: `bool`, *optional* DEFAULT: None
token	The token to use as HTTP bearer authorization for remote files. The token generated when running huggingface-cli login (stored in ~/.huggingface). TYPE: `str`, *optional* DEFAULT: None
create_pr	Whether or not to create a PR with the uploaded files or directly commit. TYPE: `bool`, *optional*, defaults to `False` DEFAULT: False
safe_serialization	Whether or not to convert the model weights to the safetensors format. TYPE: `bool`, *optional*, defaults to `True` DEFAULT: True
variant	If specified, weights are saved in the format pytorch_model.<variant>.bin. TYPE: `str`, *optional* DEFAULT: None

from mindone.diffusers import UNet2DConditionModel

unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-2", subfolder="unet")

# Push the `unet` to your namespace with the name "my-finetuned-unet".
unet.push_to_hub("my-finetuned-unet")

# Push the `unet` to an organization with the name "my-finetuned-unet".
unet.push_to_hub("your-org/my-finetuned-unet")

Source code in mindone/diffusers/utils/hub_utils.py

def push_to_hub(
    self,
    repo_id: str,
    commit_message: Optional[str] = None,
    private: Optional[bool] = None,
    token: Optional[str] = None,
    create_pr: bool = False,
    safe_serialization: bool = True,
    variant: Optional[str] = None,
) -> str:
    """
    Upload model, scheduler, or pipeline files to the 🤗 Hugging Face Hub.

    Parameters:
        repo_id (`str`):
            The name of the repository you want to push your model, scheduler, or pipeline files to. It should
            contain your organization name when pushing to an organization. `repo_id` can also be a path to a local
            directory.
        commit_message (`str`, *optional*):
            Message to commit while pushing. Default to `"Upload {object}"`.
        private (`bool`, *optional*):
            Whether or not the repository created should be private.
        token (`str`, *optional*):
            The token to use as HTTP bearer authorization for remote files. The token generated when running
            `huggingface-cli login` (stored in `~/.huggingface`).
        create_pr (`bool`, *optional*, defaults to `False`):
            Whether or not to create a PR with the uploaded files or directly commit.
        safe_serialization (`bool`, *optional*, defaults to `True`):
            Whether or not to convert the model weights to the `safetensors` format.
        variant (`str`, *optional*):
            If specified, weights are saved in the format `pytorch_model.<variant>.bin`.

    Examples:

    ```python
    from mindone.diffusers import UNet2DConditionModel

    unet = UNet2DConditionModel.from_pretrained("stabilityai/stable-diffusion-2", subfolder="unet")

    # Push the `unet` to your namespace with the name "my-finetuned-unet".
    unet.push_to_hub("my-finetuned-unet")

    # Push the `unet` to an organization with the name "my-finetuned-unet".
    unet.push_to_hub("your-org/my-finetuned-unet")
    ```
    """
    repo_id = create_repo(repo_id, private=private, token=token, exist_ok=True).repo_id

    # Create a new empty model card and eventually tag it
    model_card = load_or_create_model_card(repo_id, token=token)
    model_card = populate_model_card(model_card)

    # Save all files.
    save_kwargs = {"safe_serialization": safe_serialization}
    if "Scheduler" not in self.__class__.__name__:
        save_kwargs.update({"variant": variant})

    with tempfile.TemporaryDirectory() as tmpdir:
        self.save_pretrained(tmpdir, **save_kwargs)

        # Update model card if needed:
        model_card.save(os.path.join(tmpdir, "README.md"))

        return self._upload_folder(
            tmpdir,
            repo_id,
            token=token,
            commit_message=commit_message,
            create_pr=create_pr,
        )