Method __init__

diffsynth/models/wan_video_vae.py:382–431

(self,
                 dim=128,
                 z_dim=4,
                 dim_mult=[1, 2, 4, 4],
                 num_res_blocks=2,
                 attn_scales=[],
                 temperal_upsample=[False, True, True],
                 dropout=0.0)

class Decoder3d(nn.Module):

    def __init__(self,
                 dim=128,
                 z_dim=4,
                 dim_mult=[1, 2, 4, 4],
                 num_res_blocks=2,
                 attn_scales=[],
                 temperal_upsample=[False, True, True],
                 dropout=0.0):
        super().__init__()
        self.dim = dim
        self.z_dim = z_dim
        self.dim_mult = dim_mult
        self.num_res_blocks = num_res_blocks
        self.attn_scales = attn_scales
        self.temperal_upsample = temperal_upsample

        # dimensions
        dims = [dim * u for u in [dim_mult[-1]] + dim_mult[::-1]]
        scale = 1.0 / 2**(len(dim_mult) - 2)

        # init block
        self.conv1 = CausalConv3d(z_dim, dims[0], 3, padding=1)

        # middle blocks
        self.middle = nn.Sequential(ResidualBlock(dims[0], dims[0], dropout),
                                    AttentionBlock(dims[0]),
                                    ResidualBlock(dims[0], dims[0], dropout))

        # upsample blocks
        upsamples = []
        for i, (in_dim, out_dim) in enumerate(zip(dims[:-1], dims[1:])):
            # residual (+attention) blocks
            if i == 1 or i == 2 or i == 3:
                in_dim = in_dim // 2
            for _ in range(num_res_blocks + 1):
                upsamples.append(ResidualBlock(in_dim, out_dim, dropout))
                if scale in attn_scales:
                    upsamples.append(AttentionBlock(out_dim))
                in_dim = out_dim

            # upsample block
            if i != len(dim_mult) - 1:
                mode = 'upsample3d' if temperal_upsample[i] else 'upsample2d'
                upsamples.append(Resample(out_dim, mode=mode))
                scale *= 2.0
        self.upsamples = nn.Sequential(*upsamples)

        # output blocks
        self.head = nn.Sequential(RMS_norm(out_dim, images=False), nn.SiLU(),
                                  CausalConv3d(out_dim, 3, 3, padding=1))

    def forward(self, x, feat_cache=None, feat_idx=[0]):
        ## conv1