Method forward

wan/modules/model.py:278–317

r""" Args: x(Tensor): Shape [B, L, C] e(Tensor): Shape [B, 6, C] seq_lens(Tensor): Shape [B], length of each sequence in batch grid_sizes(Tensor): Shape [B, 3], the second dimension contains (F, H, W) freqs(Tensor): Rope freqs, shap

(
        self,
        x,
        e,
        seq_lens,
        grid_sizes,
        freqs,
        context,
        context_lens,
    )

        self.modulation = nn.Parameter(torch.randn(1, 6, dim) / dim**0.5)

    def forward(
        self,
        x,
        e,
        seq_lens,
        grid_sizes,
        freqs,
        context,
        context_lens,
    ):
        r"""
        Args:
            x(Tensor): Shape [B, L, C]
            e(Tensor): Shape [B, 6, C]
            seq_lens(Tensor): Shape [B], length of each sequence in batch
            grid_sizes(Tensor): Shape [B, 3], the second dimension contains (F, H, W)
            freqs(Tensor): Rope freqs, shape [1024, C / num_heads / 2]
        """
        assert e.dtype == torch.float32
        with amp.autocast(dtype=torch.float32):
            e = (self.modulation.to(e.device) + e).chunk(6, dim=1)
        assert e[0].dtype == torch.float32

        # self-attention
        y = self.self_attn(
            self.norm1(x).float() * (1 + e[1]) + e[0], seq_lens, grid_sizes,
            freqs)
        with amp.autocast(dtype=torch.float32):
            x = x + y * e[2]

        # cross-attention & ffn function
        def cross_attn_ffn(x, context, context_lens, e):
            x = x + self.cross_attn(self.norm3(x), context, context_lens)
            y = self.ffn(self.norm2(x).float() * (1 + e[4]) + e[3])
            with amp.autocast(dtype=torch.float32):
                x = x + y * e[5]
            return x

        x = cross_attn_ffn(x, context, context_lens, e)
        return x


class Head(nn.Module):