diff --git a/invokeai/app/invocations/latent.py b/invokeai/app/invocations/latent.py
index 095fdc2649..b77363ceb8 100644
--- a/invokeai/app/invocations/latent.py
+++ b/invokeai/app/invocations/latent.py
@@ -860,9 +860,9 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
                 vae.disable_tiling()
 
             # clear memory as vae decode can request a lot
-            # torch.cuda.empty_cache()
-            # if choose_torch_device() == torch.device("mps"):
-            #     mps.empty_cache()
+            torch.cuda.empty_cache()
+            if choose_torch_device() == torch.device("mps"):
+                mps.empty_cache()
 
             with torch.inference_mode():
                 # copied from diffusers pipeline
@@ -874,9 +874,9 @@ class LatentsToImageInvocation(BaseInvocation, WithMetadata):
 
                 image = VaeImageProcessor.numpy_to_pil(np_image)[0]
 
-        # torch.cuda.empty_cache()
-        # if choose_torch_device() == torch.device("mps"):
-        #     mps.empty_cache()
+        torch.cuda.empty_cache()
+        if choose_torch_device() == torch.device("mps"):
+            mps.empty_cache()
 
         image_dto = context.services.images.create(
             image=image,
diff --git a/invokeai/backend/model_management/seamless.py b/invokeai/backend/model_management/seamless.py
index 3f7c6dfd87..bfdf9e0c53 100644
--- a/invokeai/backend/model_management/seamless.py
+++ b/invokeai/backend/model_management/seamless.py
@@ -7,33 +7,23 @@ import torch.nn as nn
 from diffusers.models import AutoencoderKL, UNet2DConditionModel
 
 
-def _conv_forward_asymmetric(self, input, weight, bias=None):
+def _conv_forward_asymmetric(self, input, weight, bias):
     """
-    Optimized patch for Conv2d._conv_forward that supports asymmetric padding.
-    Combines padding for both axes into a single operation.
+    Patch for Conv2d._conv_forward that supports asymmetric padding
     """
-    # Calculate the combined padding for both x and y axes
-    combined_padding = (
-        self.asymmetric_padding["x"][0], self.asymmetric_padding["x"][1],
-        self.asymmetric_padding["y"][2], self.asymmetric_padding["y"][3]
-    )
-    
-    # Apply combined padding in a single operation
-    working = nn.functional.pad(input, combined_padding, mode=self.asymmetric_padding_mode["x"])
-    
-    # Perform the convolution with no additional padding (since it's already applied)
+    working = nn.functional.pad(input, self.asymmetric_padding["x"], mode=self.asymmetric_padding_mode["x"])
+    working = nn.functional.pad(working, self.asymmetric_padding["y"], mode=self.asymmetric_padding_mode["y"])
     return nn.functional.conv2d(
         working,
         weight,
         bias,
         self.stride,
-        (0, 0),  # No additional padding needed as we've already padded
+        nn.modules.utils._pair(0),
         self.dilation,
-        self.groups
+        self.groups,
     )
 
 
-
 @contextmanager
 def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL], seamless_axes: List[str]):
     try:
@@ -81,16 +71,23 @@ def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL], seamless_axe
             """
 
             if isinstance(m, (nn.Conv2d, nn.ConvTranspose2d)):
-                # Directly set padding mode and values without redundant checks
-                m.asymmetric_padding_mode = {
-                    "x": "circular" if "x" in seamless_axes else "constant",
-                    "y": "circular" if "y" in seamless_axes else "constant"
-                }
-                m.asymmetric_padding = {
-                    "x": (m.padding[0], m.padding[1], 0, 0),
-                    "y": (0, 0, m.padding[2], m.padding[3])
-                }
-                # Backup and override the conv forward method
+                m.asymmetric_padding_mode = {}
+                m.asymmetric_padding = {}
+                m.asymmetric_padding_mode["x"] = "circular" if ("x" in seamless_axes) else "constant"
+                m.asymmetric_padding["x"] = (
+                    m._reversed_padding_repeated_twice[0],
+                    m._reversed_padding_repeated_twice[1],
+                    0,
+                    0,
+                )
+                m.asymmetric_padding_mode["y"] = "circular" if ("y" in seamless_axes) else "constant"
+                m.asymmetric_padding["y"] = (
+                    0,
+                    0,
+                    m._reversed_padding_repeated_twice[2],
+                    m._reversed_padding_repeated_twice[3],
+                )
+
                 to_restore.append((m, m._conv_forward))
                 m._conv_forward = _conv_forward_asymmetric.__get__(m, nn.Conv2d)
 
@@ -99,5 +96,7 @@ def set_seamless(model: Union[UNet2DConditionModel, AutoencoderKL], seamless_axe
     finally:
         for module, orig_conv_forward in to_restore:
             module._conv_forward = orig_conv_forward
-            del module.asymmetric_padding_mode
-            del module.asymmetric_padding
+            if hasattr(module, "asymmetric_padding_mode"):
+                del module.asymmetric_padding_mode
+            if hasattr(module, "asymmetric_padding"):
+                del module.asymmetric_padding