Class WanRMS_norm

architecture/autoencoder_kl_wan.py:179–202

r""" A custom RMS normalization layer. Args: dim (int): The number of dimensions to normalize over. channel_first (bool, optional): Whether the input tensor has channels as the first dimension. Default is True. images (bool, optional): Whether the input r

class WanRMS_norm(nn.Module):
    r"""
    A custom RMS normalization layer.

    Args:
        dim (int): The number of dimensions to normalize over.
        channel_first (bool, optional): Whether the input tensor has channels as the first dimension.
            Default is True.
        images (bool, optional): Whether the input represents image data. Default is True.
        bias (bool, optional): Whether to include a learnable bias term. Default is False.
    """

    def __init__(self, dim: int, channel_first: bool = True, images: bool = True, bias: bool = False) -> None:
        super().__init__()
        broadcastable_dims = (1, 1, 1) if not images else (1, 1)
        shape = (dim, *broadcastable_dims) if channel_first else (dim,)

        self.channel_first = channel_first
        self.scale = dim**0.5
        self.gamma = nn.Parameter(torch.ones(shape))
        self.bias = nn.Parameter(torch.zeros(shape)) if bias else 0.0

    def forward(self, x):
        return F.normalize(x, dim=(1 if self.channel_first else -1)) * self.scale * self.gamma + self.bias


class WanUpsample(nn.Upsample):