diff --git a/comfy/model_base.py b/comfy/model_base.py
index 364f54644..b13a74fe6 100644
--- a/comfy/model_base.py
+++ b/comfy/model_base.py
@@ -1076,10 +1076,11 @@ class WAN21(BaseModel):
             shape_image[1] = extra_channels
             image = torch.zeros(shape_image, dtype=noise.dtype, layout=noise.layout, device=noise.device)
         else:
-            image = utils.common_upscale(image.to(device), noise.shape[-1], noise.shape[-2], "bilinear", "center")
-            for i in range(0, image.shape[1], 36):
-                image[:, i: i + 36] = self.process_latent_in(image[:, i: i + 36])
-            image = utils.resize_to_batch_size(image, noise.shape[0])
+            image = image.to(device)
+            # image = utils.common_upscale(image.to(device), noise.shape[-1], noise.shape[-2], "bilinear", "center")
+            # for i in range(0, image.shape[1], 36):
+            #     image[:, i: i + 36] = self.process_latent_in(image[:, i: i + 36])
+            # image = utils.resize_to_batch_size(image, noise.shape[0])
 
         print(f"image shape: {image.shape}")
         if not self.image_to_video or extra_channels == image.shape[1]: