Method forward

wan/modules/s2v/model_s2v.py:151–180

Args: x(Tensor): Shape [B, L, num_heads, C / num_heads] seq_lens(Tensor): Shape [B] grid_sizes(Tensor): Shape [B, 3], the second dimension contains (F, H, W) freqs(Tensor): Rope freqs, shape [1024, C / num_heads / 2]

(self, x, seq_lens, grid_sizes, freqs)

class WanS2VSelfAttention(WanSelfAttention):

    def forward(self, x, seq_lens, grid_sizes, freqs):
        """
        Args:
            x(Tensor): Shape [B, L, num_heads, C / num_heads]
            seq_lens(Tensor): Shape [B]
            grid_sizes(Tensor): Shape [B, 3], the second dimension contains (F, H, W)
            freqs(Tensor): Rope freqs, shape [1024, C / num_heads / 2]
        """
        b, s, n, d = *x.shape[:2], self.num_heads, self.head_dim

        # query, key, value function
        def qkv_fn(x):
            q = self.norm_q(self.q(x)).view(b, s, n, d)
            k = self.norm_k(self.k(x)).view(b, s, n, d)
            v = self.v(x).view(b, s, n, d)
            return q, k, v

        q, k, v = qkv_fn(x)

        x = flash_attention(
            q=rope_apply(q, grid_sizes, freqs),
            k=rope_apply(k, grid_sizes, freqs),
            v=v,
            k_lens=seq_lens,
            window_size=self.window_size)

        # output
        x = x.flatten(2)
        x = self.o(x)
        return x


class WanS2VAttentionBlock(WanAttentionBlock):