diff --git a/__init__.py b/__init__.py
index 5ee7d66..2d25932 100644
--- a/__init__.py
+++ b/__init__.py
@@ -7,6 +7,7 @@ NODE_CLASS_MAPPINGS = {
     "WanFunInpaintToVideoTiledVAE": WanFunInpaintToVideoTiledVAE,
     "WanVaceToVideoTiledVAE": WanVaceToVideoTiledVAE,
     "WanCameraImageToVideoTiledVAE":WanCameraImageToVideoTiledVAE,
+    "WanPhantomSubjectToVideoTiledVAE": WanPhantomSubjectToVideoTiledVAE,
 }
 
 NODE_DISPLAY_NAME_MAPPINGS = {
@@ -16,4 +17,5 @@ NODE_DISPLAY_NAME_MAPPINGS = {
     "WanFunInpaintToVideoTiledVAE": "WanFunInpaintToVideo (Tiled VAE encode)",
     "WanVaceToVideoTiledVAE": "WanVaceToVideo (Tiled VAE encode)",
     "WanCameraImageToVideoTiledVAE": "WanCameraImageToVideo (Tiled VAE encode)",
+    "WanPhantomSubjectToVideoTiledVAE": "WanPhantomSubjectToVideo (Tiled VAE encode)",
 }
diff --git a/nodes_wan.py b/nodes_wan.py
index 334c29f..33143f6 100644
--- a/nodes_wan.py
+++ b/nodes_wan.py
@@ -357,3 +357,46 @@ class WanCameraImageToVideoTiledVAE:
         out_latent = {}
         out_latent["samples"] = latent
         return (positive, negative, out_latent)
+
+class WanPhantomSubjectToVideoTiledVAE:
+    @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}),
+                            
+                                "tile_size": ("INT", {"default": 512, "min": 64, "max": 4096, "step": 64}),
+                                "overlap": ("INT", {"default": 64, "min": 0, "max": 4096, "step": 32}),
+                                "temporal_size": ("INT", {"default": 64, "min": 8, "max": 4096, "step": 4, "tooltip": "Amount of frames to encode at a time."}),
+                                "temporal_overlap": ("INT", {"default": 8, "min": 4, "max": 4096, "step": 4, "tooltip": "Amount of frames to overlap."})
+                },
+                "optional": {"images": ("IMAGE", ),
+                }}
+
+    RETURN_TYPES = ("CONDITIONING", "CONDITIONING", "CONDITIONING", "LATENT")
+    RETURN_NAMES = ("positive", "negative_text", "negative_img_text", "latent")
+    FUNCTION = "encode"
+
+    CATEGORY = "conditioning/video_models"
+
+    def encode(self, positive, negative, vae, width, height, length, batch_size, tile_size, overlap, temporal_size, temporal_overlap, images):
+        latent = torch.zeros([batch_size, 16, ((length - 1) // 4) + 1, height // 8, width // 8], device=comfy.model_management.intermediate_device())
+        cond2 = negative
+        if images is not None:
+            images = comfy.utils.common_upscale(images[:length].movedim(-1, 1), width, height, "bilinear", "center").movedim(1, -1)
+            latent_images = []
+            for i in images:
+                latent_images += [vae.encode_tiled(i.unsqueeze(0)[:, :, :, :3], tile_x=tile_size, tile_y=tile_size, overlap=overlap, tile_t=temporal_size, overlap_t=temporal_overlap)]
+            concat_latent_image = torch.cat(latent_images, dim=2)
+
+            positive = node_helpers.conditioning_set_values(positive, {"time_dim_concat": concat_latent_image})
+            cond2 = node_helpers.conditioning_set_values(negative, {"time_dim_concat": concat_latent_image})
+            negative = node_helpers.conditioning_set_values(negative, {"time_dim_concat": comfy.latent_formats.Wan21().process_out(torch.zeros_like(concat_latent_image))})
+
+        out_latent = {}
+        out_latent["samples"] = latent
+        return (positive, cond2, negative, out_latent)