Method __init__

src/diffusers/models/unets/unet_2d_blocks.py:620–734

(
        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,
    )

    """

    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(
                    in_channels=in_channels,
                    out_channels=in_channels,
                    temb_channels=temb_channels,
                    eps=resnet_eps,
                    groups=resnet_groups,
                    dropout=dropout,
                    time_embedding_norm="spatial",
                    non_linearity=resnet_act_fn,
                    output_scale_factor=output_scale_factor,
                )
            ]
        else:
            resnets = [
                ResnetBlock2D(
                    in_channels=in_channels,
                    out_channels=in_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,
                )
            ]
        attentions = []

        if attention_head_dim is None:
            logger.warning(
                f"It is not recommend to pass `attention_head_dim=None`. Defaulting `attention_head_dim` to `in_channels`: {in_channels}."