diff --git a/src/diffusers/models/transformers/transformer_hunyuan_video.py b/src/diffusers/models/transformers/transformer_hunyuan_video.py
index e3f24d97f3..6cb97af936 100644
--- a/src/diffusers/models/transformers/transformer_hunyuan_video.py
+++ b/src/diffusers/models/transformers/transformer_hunyuan_video.py
@@ -721,6 +721,7 @@ class HunyuanVideoTransformer3DModel(ModelMixin, ConfigMixin, PeftAdapterMixin,
 
         for i in range(batch_size):
             attention_mask[i, : effective_sequence_length[i], : effective_sequence_length[i]] = True
+        attention_mask = attention_mask.unsqueeze(1)  # [B, 1, N, N], for broadcasting across attention heads
 
         # 4. Transformer blocks
         if torch.is_grad_enabled() and self.gradient_checkpointing: