diff --git a/comfy/ldm/modules/diffusionmodules/upscaling.py b/comfy/ldm/modules/diffusionmodules/upscaling.py
index 709a7f5..768a47f 100644
--- a/comfy/ldm/modules/diffusionmodules/upscaling.py
+++ b/comfy/ldm/modules/diffusionmodules/upscaling.py
@@ -43,8 +43,8 @@ class AbstractLowScaleModel(nn.Module):
 
     def q_sample(self, x_start, t, noise=None):
         noise = default(noise, lambda: torch.randn_like(x_start))
-        return (extract_into_tensor(self.sqrt_alphas_cumprod, t, x_start.shape) * x_start +
-                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod, t, x_start.shape) * noise)
+        return (extract_into_tensor(self.sqrt_alphas_cumprod.to(x_start.device), t, x_start.shape) * x_start +
+                extract_into_tensor(self.sqrt_one_minus_alphas_cumprod.to(x_start.device), t, x_start.shape) * noise)
 
     def forward(self, x):
         return x, None
diff --git a/comfy/ldm/modules/encoders/noise_aug_modules.py b/comfy/ldm/modules/encoders/noise_aug_modules.py
index b59bf20..66767b5 100644
--- a/comfy/ldm/modules/encoders/noise_aug_modules.py
+++ b/comfy/ldm/modules/encoders/noise_aug_modules.py
@@ -15,12 +15,12 @@ class CLIPEmbeddingNoiseAugmentation(ImageConcatWithNoiseAugmentation):
 
     def scale(self, x):
         # re-normalize to centered mean and unit variance
-        x = (x - self.data_mean) * 1. / self.data_std
+        x = (x - self.data_mean.to(x.device)) * 1. / self.data_std.to(x.device)
         return x
 
     def unscale(self, x):
         # back to original data stats
-        x = (x * self.data_std) + self.data_mean
+        x = (x * self.data_std.to(x.device)) + self.data_mean.to(x.device)
         return x
 
     def forward(self, x, noise_level=None):