diff --git a/nodes.py b/nodes.py
index a356b1b..28a3df4 100644
--- a/nodes.py
+++ b/nodes.py
@@ -6,7 +6,8 @@ import folder_paths
 from .stabledelight_comfyui.pipeline_yoso_delight import YosoDelightPipeline
 
 class StableDelightNode:
-    upscale_methods = ["bilinear", "nearest-exact", "area", "bicubic"]
+    resample_methods = ["bilinear","nearest", "nearest-exact",  "bicubic", "area"]
+    
     @classmethod
     def INPUT_TYPES(s):
         return {
@@ -18,35 +19,13 @@ class StableDelightNode:
                     "max": 4096,
                     "step": 64
                 }),
-                "t_start": ("FLOAT", {
-                    "default": 0.0,
+                "resample_method": (s.resample_methods,),
+                "controlnet_conditioning_scale": ("FLOAT", {
+                    "default": 1.0,
                     "min": 0.0,
-                    "max": 1.0,
-                    "step": 0.01
+                    "max": 10.0,
+                    "step": 0.1
                 }),
-                "match_input_resolution": ("BOOLEAN", {
-                    "default": False
-                }),
-                "ensemble_size": ("INT", {
-                    "default": 1,
-                    "min": 1,
-                    "max": 10,
-                    "step": 1
-                }),
-                "batch_size": ("INT", {
-                    "default": 1,
-                    "min": 1,
-                    "max": 4,
-                    "step": 1
-                }),
-            },
-            "optional": {
-                "seed": ("INT", {
-                    "default": -1,
-                    "min": -1,
-                    "max": 0xffffffffffffffff
-                }),
-                "resample_method": (s.upscale_methods,),
             }
         }
 
@@ -69,34 +48,8 @@ class StableDelightNode:
         except:
             pass
 
-    def resize_image(self, input_image, resolution):
-        # Convert tensor to PIL Image
-        if torch.is_tensor(input_image):
-            if input_image.ndim == 4:
-                input_image = input_image[0]
-            input_image = (input_image * 255).clamp(0, 255).to(torch.uint8)
-            input_image = Image.fromarray(input_image.cpu().numpy())
-        
-        # Get image dimensions
-        W, H = input_image.size
-        k = float(resolution) / min(H, W)
-        H *= k
-        W *= k
-        H = int(np.round(H / 64.0)) * 64
-        W = int(np.round(W / 64.0)) * 64
-        
-        # Resize the image
-        return input_image.resize((W, H), Image.Resampling.LANCZOS)
-
-    def delight_image(self, image, processing_resolution, t_start, match_input_resolution, 
-                     ensemble_size, batch_size, seed=-1, resample_method="lanczos"):
-        # Set random seed if provided
-        if seed != -1:
-            generator = torch.Generator(device=self.device).manual_seed(seed)
-        else:
-            generator = None
-            
-        # Convert from ComfyUI image format to PIL and resize
+    def delight_image(self, image, processing_resolution, resample_method, controlnet_conditioning_scale):
+        # Convert from ComfyUI image format to PIL
         if torch.is_tensor(image):
             if image.ndim == 4:
                 image = image[0]
@@ -106,14 +59,10 @@ class StableDelightNode:
         # Process image
         pipe_out = self.pipe(
             image,
-            match_input_resolution=match_input_resolution,
             processing_resolution=processing_resolution,
-            t_start=t_start,
-            ensemble_size=ensemble_size,
-            batch_size=batch_size,
-            generator=generator,
             resample_method_input=resample_method,
-            resample_method_output=resample_method
+            resample_method_output=resample_method,
+            controlnet_conditioning_scale=controlnet_conditioning_scale
         )
         
         # Convert output to ComfyUI format
@@ -126,4 +75,4 @@ class StableDelightNode:
         if processed.ndim == 3:
             processed = processed.unsqueeze(0)
         
-        return (processed,) 
\ No newline at end of file
+        return (processed,)
\ No newline at end of file