Cross attention module to Wan Attention (#12058)

* Cross attention module to Wan Attention

* Apply style fixes

---------

Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Aryan <[email protected]>

Author: 3 people

src/diffusers/models/transformers/transformer_wan.py

@@ -180,6 +180,7 @@ def __init__(
         added_kv_proj_dim: Optional[int] = None,
         cross_attention_dim_head: Optional[int] = None,
         processor=None,
+        is_cross_attention=None,
     ):
         super().__init__()
 
@@ -207,6 +208,8 @@ def __init__(
             self.add_v_proj = torch.nn.Linear(added_kv_proj_dim, self.inner_dim, bias=True)
             self.norm_added_k = torch.nn.RMSNorm(dim_head * heads, eps=eps)
 
+        self.is_cross_attention = cross_attention_dim_head is not None
+
         self.set_processor(processor)
 
     def fuse_projections(self):