Class UNetMidBlock2D

src/diffusers/models/unets/unet_2d_blocks.py:589–748

A 2D UNet mid-block [`UNetMidBlock2D`] with multiple residual blocks and optional attention blocks. Args: in_channels (`int`): The number of input channels. temb_channels (`int`): The number of temporal embedding channels. dropout (`float`, *optional*, defaults to 0

class UNetMidBlock2D(nn.Module):
    """
    A 2D UNet mid-block [`UNetMidBlock2D`] with multiple residual blocks and optional attention blocks.

    Args:
        in_channels (`int`): The number of input channels.
        temb_channels (`int`): The number of temporal embedding channels.
        dropout (`float`, *optional*, defaults to 0.0): The dropout rate.
        num_layers (`int`, *optional*, defaults to 1): The number of residual blocks.
        resnet_eps (`float`, *optional*, 1e-6 ): The epsilon value for the resnet blocks.
        resnet_time_scale_shift (`str`, *optional*, defaults to `default`):
            The type of normalization to apply to the time embeddings. This can help to improve the performance of the
            model on tasks with long-range temporal dependencies.
        resnet_act_fn (`str`, *optional*, defaults to `swish`): The activation function for the resnet blocks.
        resnet_groups (`int`, *optional*, defaults to 32):
            The number of groups to use in the group normalization layers of the resnet blocks.
        attn_groups (`int | None`, *optional*, defaults to None): The number of groups for the attention blocks.
        resnet_pre_norm (`bool`, *optional*, defaults to `True`):
            Whether to use pre-normalization for the resnet blocks.
        add_attention (`bool`, *optional*, defaults to `True`): Whether to add attention blocks.
        attention_head_dim (`int`, *optional*, defaults to 1):
            Dimension of a single attention head. The number of attention heads is determined based on this value and
            the number of input channels.
        output_scale_factor (`float`, *optional*, defaults to 1.0): The output scale factor.

    Returns:
        `torch.Tensor`: The output of the last residual block, which is a tensor of shape `(batch_size, in_channels,
        height, width)`.

    """

    def __init__(
        self,
        in_channels: int,
        temb_channels: int,
        dropout: float = 0.0,
        num_layers: int = 1,
        resnet_eps: float = 1e-6,
        resnet_time_scale_shift: str = "default",  # default, spatial
        resnet_act_fn: str = "swish",
        resnet_groups: int = 32,
        attn_groups: int | None = None,
        resnet_pre_norm: bool = True,
        add_attention: bool = True,
        attention_head_dim: int = 1,
        output_scale_factor: float = 1.0,
    ):
        super().__init__()
        resnet_groups = resnet_groups if resnet_groups is not None else min(in_channels // 4, 32)
        self.add_attention = add_attention

        if attn_groups is None:
            attn_groups = resnet_groups if resnet_time_scale_shift == "default" else None

        # there is always at least one resnet
        if resnet_time_scale_shift == "spatial":
            resnets = [
                ResnetBlockCondNorm2D(