Fix head_to_batch_dim for IPAdapterAttnProcessor (#7077)

* Fix IPAdapterAttnProcessor

* Fix batch_to_head_dim and revert reshape

src/diffusers/models/attention_processor.py

@@ -559,12 +559,16 @@ class Attention(nn.Module):
             `torch.Tensor`: The reshaped tensor.
         """
         head_size = self.heads
+        if tensor.ndim == 3:
             batch_size, seq_len, dim = tensor.shape
-        tensor = tensor.reshape(batch_size, seq_len, head_size, dim // head_size)
+            extra_dim = 1
+        else:
+            batch_size, extra_dim, seq_len, dim = tensor.shape
+        tensor = tensor.reshape(batch_size, seq_len * extra_dim, head_size, dim // head_size)
         tensor = tensor.permute(0, 2, 1, 3)
 
         if out_dim == 3:
-            tensor = tensor.reshape(batch_size * head_size, seq_len, dim // head_size)
+            tensor = tensor.reshape(batch_size * head_size, seq_len * extra_dim, dim // head_size)
 
         return tensor