Class CrossAttnDownBlock2D

src/diffusers/models/unets/unet_2d_blocks.py:1147–1291

class CrossAttnDownBlock2D(nn.Module):
    def __init__(
        self,
        in_channels: int,
        out_channels: int,
        temb_channels: int,
        dropout: float = 0.0,
        num_layers: int = 1,
        transformer_layers_per_block: int | tuple[int] = 1,
        resnet_eps: float = 1e-6,
        resnet_time_scale_shift: str = "default",
        resnet_act_fn: str = "swish",
        resnet_groups: int = 32,
        resnet_pre_norm: bool = True,
        num_attention_heads: int = 1,
        cross_attention_dim: int = 1280,
        output_scale_factor: float = 1.0,
        downsample_padding: int = 1,
        add_downsample: bool = True,
        dual_cross_attention: bool = False,
        use_linear_projection: bool = False,
        only_cross_attention: bool = False,
        upcast_attention: bool = False,
        attention_type: str = "default",
    ):
        super().__init__()
        resnets = []
        attentions = []

        self.has_cross_attention = True
        self.num_attention_heads = num_attention_heads
        if isinstance(transformer_layers_per_block, int):
            transformer_layers_per_block = [transformer_layers_per_block] * num_layers

        for i in range(num_layers):
            in_channels = in_channels if i == 0 else out_channels
            resnets.append(
                ResnetBlock2D(
                    in_channels=in_channels,
                    out_channels=out_channels,
                    temb_channels=temb_channels,
                    eps=resnet_eps,
                    groups=resnet_groups,
                    dropout=dropout,
                    time_embedding_norm=resnet_time_scale_shift,
                    non_linearity=resnet_act_fn,
                    output_scale_factor=output_scale_factor,
                    pre_norm=resnet_pre_norm,
                )
            )
            if not dual_cross_attention:
                attentions.append(
                    Transformer2DModel(
                        num_attention_heads,
                        out_channels // num_attention_heads,
                        in_channels=out_channels,
                        num_layers=transformer_layers_per_block[i],
                        cross_attention_dim=cross_attention_dim,