Method forward

examples/community/matryoshka.py:3309–3613

r""" The [`NestedUNet2DConditionModel`] forward method. Args: sample (`torch.Tensor`): The noisy input tensor with the following shape `(batch, channel, height, width)`. timestep (`torch.Tensor` or `float` or `int`): The number of timesteps to

(
        self,
        sample: torch.Tensor,
        timestep: Union[torch.Tensor, float, int],
        encoder_hidden_states: torch.Tensor,
        cond_emb: Optional[torch.Tensor] = None,
        from_nested: bool = False,
        class_labels: Optional[torch.Tensor] = None,
        timestep_cond: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
        down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
        mid_block_additional_residual: Optional[torch.Tensor] = None,
        down_intrablock_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
        encoder_attention_mask: Optional[torch.Tensor] = None,
        return_dict: bool = True,
    )

        return "nested_unet"

    def forward(
        self,
        sample: torch.Tensor,
        timestep: Union[torch.Tensor, float, int],
        encoder_hidden_states: torch.Tensor,
        cond_emb: Optional[torch.Tensor] = None,
        from_nested: bool = False,
        class_labels: Optional[torch.Tensor] = None,
        timestep_cond: Optional[torch.Tensor] = None,
        attention_mask: Optional[torch.Tensor] = None,
        cross_attention_kwargs: Optional[Dict[str, Any]] = None,
        added_cond_kwargs: Optional[Dict[str, torch.Tensor]] = None,
        down_block_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
        mid_block_additional_residual: Optional[torch.Tensor] = None,
        down_intrablock_additional_residuals: Optional[Tuple[torch.Tensor]] = None,
        encoder_attention_mask: Optional[torch.Tensor] = None,
        return_dict: bool = True,
    ) -> Union[MatryoshkaUNet2DConditionOutput, Tuple]:
        r"""
        The [`NestedUNet2DConditionModel`] forward method.

        Args:
            sample (`torch.Tensor`):
                The noisy input tensor with the following shape `(batch, channel, height, width)`.
            timestep (`torch.Tensor` or `float` or `int`): The number of timesteps to denoise an input.
            encoder_hidden_states (`torch.Tensor`):
                The encoder hidden states with shape `(batch, sequence_length, feature_dim)`.
            class_labels (`torch.Tensor`, *optional*, defaults to `None`):
                Optional class labels for conditioning. Their embeddings will be summed with the timestep embeddings.
            timestep_cond: (`torch.Tensor`, *optional*, defaults to `None`):
                Conditional embeddings for timestep. If provided, the embeddings will be summed with the samples passed
                through the `self.time_embedding` layer to obtain the timestep embeddings.
            attention_mask (`torch.Tensor`, *optional*, defaults to `None`):
                An attention mask of shape `(batch, key_tokens)` is applied to `encoder_hidden_states`. If `1` the mask
                is kept, otherwise if `0` it is discarded. Mask will be converted into a bias, which adds large
                negative values to the attention scores corresponding to "discard" tokens.
            cross_attention_kwargs (`dict`, *optional*):
                A kwargs dictionary that if specified is passed along to the `AttentionProcessor` as defined under
                `self.processor` in
                [diffusers.models.attention_processor](https://github.com/huggingface/diffusers/blob/main/src/diffusers/models/attention_processor.py).
            added_cond_kwargs: (`dict`, *optional*):
                A kwargs dictionary containing additional embeddings that if specified are added to the embeddings that
                are passed along to the UNet blocks.
            down_block_additional_residuals: (`tuple` of `torch.Tensor`, *optional*):
                A tuple of tensors that if specified are added to the residuals of down unet blocks.
            mid_block_additional_residual: (`torch.Tensor`, *optional*):
                A tensor that if specified is added to the residual of the middle unet block.
            down_intrablock_additional_residuals (`tuple` of `torch.Tensor`, *optional*):
                additional residuals to be added within UNet down blocks, for example from T2I-Adapter side model(s)
            encoder_attention_mask (`torch.Tensor`):
                A cross-attention mask of shape `(batch, sequence_length)` is applied to `encoder_hidden_states`. If
                `True` the mask is kept, otherwise if `False` it is discarded. Mask will be converted into a bias,
                which adds large negative values to the attention scores corresponding to "discard" tokens.
            return_dict (`bool`, *optional*, defaults to `True`):
                Whether or not to return a [`~NestedUNet2DConditionOutput`] instead of a plain
                tuple.

        Returns: