diff --git a/comfy/model_base.py b/comfy/model_base.py
index 315b5d1e..8f588e2b 100644
--- a/comfy/model_base.py
+++ b/comfy/model_base.py
@@ -1017,11 +1017,14 @@ class WAN21(BaseModel):
         if mask is None:
             mask = torch.zeros_like(noise)[:, :4]
         else:
-            mask = 1.0 - torch.mean(mask, dim=1, keepdim=True)
+            if mask.shape[1] != 4:
+                mask = torch.mean(mask, dim=1, keepdim=True)
+            mask = 1.0 - mask
             mask = utils.common_upscale(mask.to(device), noise.shape[-1], noise.shape[-2], "bilinear", "center")
             if mask.shape[-3] < noise.shape[-3]:
                 mask = torch.nn.functional.pad(mask, (0, 0, 0, 0, 0, noise.shape[-3] - mask.shape[-3]), mode='constant', value=0)
-            mask = mask.repeat(1, 4, 1, 1, 1)
+            if mask.shape[1] == 1:
+                mask = mask.repeat(1, 4, 1, 1, 1)
             mask = utils.resize_to_batch_size(mask, noise.shape[0])
 
         return torch.cat((mask, image), dim=1)
diff --git a/comfy_extras/nodes_wan.py b/comfy_extras/nodes_wan.py
index 428874bc..2d0f31ac 100644
--- a/comfy_extras/nodes_wan.py
+++ b/comfy_extras/nodes_wan.py
@@ -99,7 +99,61 @@ class WanFunControlToVideo:
         out_latent["samples"] = latent
         return (positive, negative, out_latent)
 
+class WanFunInpaintToVideo:
+    @classmethod
+    def INPUT_TYPES(s):
+        return {"required": {"positive": ("CONDITIONING", ),
+                             "negative": ("CONDITIONING", ),
+                             "vae": ("VAE", ),
+                             "width": ("INT", {"default": 832, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                             "height": ("INT", {"default": 480, "min": 16, "max": nodes.MAX_RESOLUTION, "step": 16}),
+                             "length": ("INT", {"default": 81, "min": 1, "max": nodes.MAX_RESOLUTION, "step": 4}),
+                             "batch_size": ("INT", {"default": 1, "min": 1, "max": 4096}),
+                },
+                "optional": {"clip_vision_output": ("CLIP_VISION_OUTPUT", ),
+                             "start_image": ("IMAGE", ),
+                             "end_image": ("IMAGE", ),
+                }}
+
+    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "LATENT")
+    RETURN_NAMES = ("positive", "negative", "latent")
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/video_models"
+
+    def encode(self, positive, negative, vae, width, height, length, batch_size, start_image=None, end_image=None, clip_vision_output=None):
+        latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        if start_image is not None:
+            start_image = comfy.utils.common_upscale(start_image[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+        if end_image is not None:
+            end_image = comfy.utils.common_upscale(end_image[-length:].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+
+        image = torch.ones((length, height, width, 3)) * 0.5
+        mask = torch.ones((1, 1, latent.shape[2] * 4, latent.shape[-2], latent.shape[-1]))
+
+        if start_image is not None:
+            image[:start_image.shape[0]] = start_image
+            mask[:, :, :start_image.shape[0] + 3] = 0.0
+
+        if end_image is not None:
+            image[-end_image.shape[0]:] = end_image
+            mask[:, :, -end_image.shape[0]:] = 0.0
+
+        concat_latent_image = vae.encode(image[:, :, :, :3])
+        mask = mask.view(1, mask.shape[2] // 4, 4, mask.shape[3], mask.shape[4]).transpose(1, 2)
+        positive = node_helpers.conditioning_set_values(positive, {"concat_latent_image": concat_latent_image, "concat_mask": mask})
+        negative = node_helpers.conditioning_set_values(negative, {"concat_latent_image": concat_latent_image, "concat_mask": mask})
+
+        if clip_vision_output is not None:
+            positive = node_helpers.conditioning_set_values(positive, {"clip_vision_output": clip_vision_output})
+            negative = node_helpers.conditioning_set_values(negative, {"clip_vision_output": clip_vision_output})
+
+        out_latent = {}
+        out_latent["samples"] = latent
+        return (positive, negative, out_latent)
+
 NODE_CLASS_MAPPINGS = {
     "WanImageToVideo": WanImageToVideo,
     "WanFunControlToVideo": WanFunControlToVideo,
+    "WanFunInpaintToVideo": WanFunInpaintToVideo,
 }