Class CustomDiffusionAttnProcessor2_0

models_diffusers/attention_processor.py:1382–1493

r""" Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0’s memory-efficient scaled dot-product attention. Args: train_kv (`bool`, defaults to `True`): Whether to newly train the key and value matrices corresponding to the text featu

class CustomDiffusionAttnProcessor2_0(nn.Module):
    r"""
    Processor for implementing attention for the Custom Diffusion method using PyTorch 2.0’s memory-efficient scaled
    dot-product attention.

    Args:
        train_kv (`bool`, defaults to `True`):
            Whether to newly train the key and value matrices corresponding to the text features.
        train_q_out (`bool`, defaults to `True`):
            Whether to newly train query matrices corresponding to the latent image features.
        hidden_size (`int`, *optional*, defaults to `None`):
            The hidden size of the attention layer.
        cross_attention_dim (`int`, *optional*, defaults to `None`):
            The number of channels in the `encoder_hidden_states`.
        out_bias (`bool`, defaults to `True`):
            Whether to include the bias parameter in `train_q_out`.
        dropout (`float`, *optional*, defaults to 0.0):
            The dropout probability to use.
    """

    def __init__(
        self,
        train_kv: bool = True,
        train_q_out: bool = True,
        hidden_size: Optional[int] = None,
        cross_attention_dim: Optional[int] = None,
        out_bias: bool = True,
        dropout: float = 0.0,
    ):
        super().__init__()
        self.train_kv = train_kv
        self.train_q_out = train_q_out

        self.hidden_size = hidden_size
        self.cross_attention_dim = cross_attention_dim

        # `_custom_diffusion` id for easy serialization and loading.
        if self.train_kv:
            self.to_k_custom_diffusion = nn.Linear(cross_attention_dim or hidden_size, hidden_size, bias=False)
            self.to_v_custom_diffusion = nn.Linear(cross_attention_dim or hidden_size, hidden_size, bias=False)
        if self.train_q_out:
            self.to_q_custom_diffusion = nn.Linear(hidden_size, hidden_size, bias=False)
            self.to_out_custom_diffusion = nn.ModuleList([])
            self.to_out_custom_diffusion.append(nn.Linear(hidden_size, hidden_size, bias=out_bias))
            self.to_out_custom_diffusion.append(nn.Dropout(dropout))

    def __call__(
        self,
        attn: Attention,
        hidden_states: torch.FloatTensor,
        encoder_hidden_states: Optional[torch.FloatTensor] = None,
        attention_mask: Optional[torch.FloatTensor] = None,
    ) -> torch.FloatTensor:
        batch_size, sequence_length, _ = hidden_states.shape
        attention_mask = attn.prepare_attention_mask(attention_mask, sequence_length, batch_size)
        if self.train_q_out:
            query = self.to_q_custom_diffusion(hidden_states)
        else: