diff --git a/src/h3_blackwell_runtime/vae_decoder.py b/src/h3_blackwell_runtime/vae_decoder.py
index 450a046..06b8823 100644
--- a/src/h3_blackwell_runtime/vae_decoder.py
+++ b/src/h3_blackwell_runtime/vae_decoder.py
@@ -236,12 +236,27 @@ class MiniMaxH3VideoVAE(nn.Module):
     @staticmethod
     def blend(a: torch.Tensor, b: torch.Tensor, extent: int, dim: int) -> torch.Tensor:
         extent = min(a.shape[dim], b.shape[dim], extent)
+
+        positions = torch.arange(extent, device=b.device, dtype=b.dtype)
+        weight_a = 1 - positions / extent
+        weight_b = positions / extent
+
         shape = [1] * a.ndim
         shape[dim] = extent
-        position = torch.arange(extent, device=b.device, dtype=b.dtype).view(shape)
-        blended = a.narrow(dim, a.shape[dim] - extent, extent) * (1 - position / extent) + b.narrow(dim, 0, extent) * (position / extent)
+        weight_a = weight_a.view(shape)
+        weight_b = weight_b.view(shape)
+
+        slice_a = [slice(None)] * a.ndim
+        slice_a[dim] = slice(-extent, None)
+        slice_b = [slice(None)] * b.ndim
+        slice_b[dim] = slice(0, extent)
+
+        blended = a[tuple(slice_a)] * weight_a + b[tuple(slice_b)] * weight_b
+
         if extent < b.shape[dim]:
-            return torch.cat((blended, b.narrow(dim, extent, b.shape[dim] - extent)), dim=dim)
+            slice_b_rest = [slice(None)] * b.ndim
+            slice_b_rest[dim] = slice(extent, None)
+            return torch.cat((blended, b[tuple(slice_b_rest)]), dim=dim)
         return blended
 
     def tiled_decode(self, z: torch.Tensor) -> torch.Tensor: