diff --git a/modules/ipex_specific/__init__.py b/modules/ipex_specific/__init__.py
index 8dbec2830..9206b95f2 100644
--- a/modules/ipex_specific/__init__.py
+++ b/modules/ipex_specific/__init__.py
@@ -115,10 +115,15 @@ def ipex_init():
     CondFunc('torch.nn.modules.Linear.forward',
         lambda orig_func, self, input: orig_func(self, input.to(self.weight.data.dtype)),
         lambda orig_func, self, input: input.dtype != self.weight.data.dtype)
+    CondFunc('torch.nn.functional.layer_norm',
+        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
+        orig_func(input.to(weight.data.dtype), normalized_shape, weight, *args, **kwargs),
+        lambda orig_func, input, normalized_shape=None, weight=None, *args, **kwargs:
+        input.dtype != weight.data.dtype and weight is not None)
     #Diffusers bfloat16:
-    CondFunc('torch.nn.modules.Conv2d._conv_forward',
-        lambda orig_func, self, input, weight, bias=None: orig_func(self, input.to(weight.data.dtype), weight, bias=bias),
-        lambda orig_func, self, input, weight, bias=None: input.dtype != weight.data.dtype)
+    CondFunc('torch.nn.functional.conv2d',
+        lambda orig_func, input, weight, *args, **kwargs: orig_func(input.to(weight.data.dtype), weight, *args, **kwargs),
+        lambda orig_func, input, weight, *args, **kwargs: input.dtype != weight.data.dtype)
 
     #Functions that does not work with the XPU:
     #UniPC:
diff --git a/modules/ipex_specific/diffusers.py b/modules/ipex_specific/diffusers.py
index 7253e8cd5..2312fcf8b 100644
--- a/modules/ipex_specific/diffusers.py
+++ b/modules/ipex_specific/diffusers.py
@@ -52,12 +52,13 @@ class SlicedAttnProcessor:
             (batch_size_attention, query_tokens, dim // attn.heads), device=query.device, dtype=query.dtype
         )
 
-        block_size = (batch_size_attention * query_tokens * shape_three) / 1024 * 1.2 #MB
+        block_multiply = 2.4 if query.dtype == torch.float32 else 1.2
+        block_size = (batch_size_attention * query_tokens * shape_three) / 1024 * block_multiply #MB
         split_2_slice_size = query_tokens
         if block_size >= 4000:
             do_split_2 = True
             #Find something divisible with the query_tokens
-            while ((self.slice_size * split_2_slice_size * shape_three) / 1024 * 1.2) > 4000:
+            while ((self.slice_size * split_2_slice_size * shape_three) / 1024 * block_multiply) > 4000:
                 split_2_slice_size = split_2_slice_size // 2
         else:
             do_split_2 = False