diff --git a/src/diffusers/pipelines/wan/pipeline_wan_vace.py b/src/diffusers/pipelines/wan/pipeline_wan_vace.py
index e5f83dd401ad..99e1f5116b85 100644
--- a/src/diffusers/pipelines/wan/pipeline_wan_vace.py
+++ b/src/diffusers/pipelines/wan/pipeline_wan_vace.py
@@ -525,8 +525,7 @@ def prepare_video_latents(
             latents = retrieve_latents(self.vae.encode(video), generator, sample_mode="argmax").unbind(0)
             latents = ((latents.float() - latents_mean) * latents_std).to(vae_dtype)
         else:
-            mask = mask.to(dtype=vae_dtype)
-            mask = torch.where(mask > 0.5, 1.0, 0.0)
+            mask = torch.where(mask > 0.5, 1.0, 0.0).to(dtype=vae_dtype)
             inactive = video * (1 - mask)
             reactive = video * mask
             inactive = retrieve_latents(self.vae.encode(inactive), generator, sample_mode="argmax")
diff --git a/tests/lora/test_lora_layers_wanvace.py b/tests/lora/test_lora_layers_wanvace.py
index f976577653b2..a0954fa4fa05 100644
--- a/tests/lora/test_lora_layers_wanvace.py
+++ b/tests/lora/test_lora_layers_wanvace.py
@@ -18,7 +18,6 @@
 import unittest
 
 import numpy as np
-import pytest
 import safetensors.torch
 import torch
 from PIL import Image
@@ -160,11 +159,6 @@ def test_simple_inference_with_text_lora_fused(self):
     def test_simple_inference_with_text_lora_save_load(self):
         pass
 
-    @pytest.mark.xfail(
-        condition=True,
-        reason="RuntimeError: Input type (float) and bias type (c10::BFloat16) should be the same",
-        strict=True,
-    )
     def test_layerwise_casting_inference_denoiser(self):
         super().test_layerwise_casting_inference_denoiser()