diff --git a/README.md b/README.md
index 39da520..b530bd9 100644
--- a/README.md
+++ b/README.md
@@ -143,6 +143,23 @@ resulting latent as you normally would in your workflow.
     - **LATENT**: The latent image output by the Core ML model. This can be decoded using a VAE Decoder or used as input
       to the next node in your workflow.
 
+#### Core ML Adapter (Experimental) (`CoreMLModelAdapter`)
+
+![CoreMLModelAdapter](./assets/adapter.png?raw=true)
+
+This node allows you to use a Core ML as a standard ComfyUI model. This is an experimental node and may not work with
+all models and nodes. Please use with caution and pay attention to the expected inputs of the model.
+
+- **Input**:
+    - **coreml_model**: The Core ML model to use as a ComfyUI model.
+- **Output**:
+    - **MODEL**: The Core ML model wrapped in a ComfyUI model.
+
+> [!NOTE]
+> While this approach allows you to use Core ML models with many ComfyUI nodes (both standard and custom), the
+> expected inputs of the model will not be checked, which may cause errors. Please make sure to use a model compatible
+> with the expected parameters.
+
 ### Example Workflows
 
 > [!NOTE]
diff --git a/__init__.py b/__init__.py
index b259a08..8a0d5c9 100644
--- a/__init__.py
+++ b/__init__.py
@@ -3,13 +3,15 @@ import sys
 
 sys.path.append(os.path.dirname(__file__))
 
-from coreml_suite.nodes import CoreMLLoaderUNet, CoreMLSampler
+from coreml_suite.nodes import CoreMLLoaderUNet, CoreMLSampler, CoreMLModelAdapter
 
 NODE_CLASS_MAPPINGS = {
     "CoreMLUNetLoader": CoreMLLoaderUNet,
     "CoreMLSampler": CoreMLSampler,
+    "CoreMLModelAdapter": CoreMLModelAdapter,
 }
 NODE_DISPLAY_NAME_MAPPINGS = {
     "CoreMLUNetLoader": "Load Core ML UNet",
     "CoreMLSampler": "Core ML Sampler",
+    "CoreMLModelAdapter": "Core ML Adapter (Experimental)",
 }
diff --git a/assets/adapter.png b/assets/adapter.png
new file mode 100644
index 0000000..df21d92
Binary files /dev/null and b/assets/adapter.png differ
diff --git a/coreml_suite/nodes.py b/coreml_suite/nodes.py
index 7246a6f..d1e58bb 100644
--- a/coreml_suite/nodes.py
+++ b/coreml_suite/nodes.py
@@ -28,24 +28,24 @@ class CoreMLSampler(KSampler):
     CATEGORY = "Core ML Suite"
 
     def sample(
-        self,
-        coreml_model,
-        seed,
-        steps,
-        cfg,
-        sampler_name,
-        scheduler,
-        positive,
-        negative,
-        latent_image=None,
-        denoise=1.0,
+            self,
+            coreml_model,
+            seed,
+            steps,
+            cfg,
+            sampler_name,
+            scheduler,
+            positive,
+            negative,
+            latent_image=None,
+            denoise=1.0,
     ):
         sample_shape = coreml_model.expected_inputs["sample"]["shape"]
         latent_image = reshape_latent_image(latent_image, sample_shape)
         latent_image["samples"] = latent_image["samples"][0:1]
 
         model_config = get_model_config()
-        wrapped_model = CoreMLModelWrapper(model_config, coreml_model)
+        wrapped_model = CoreMLModelAdapter(model_config, coreml_model)
         model = ModelPatcher(wrapped_model, get_torch_device(), None)
 
         return super().sample(
@@ -99,9 +99,6 @@ class CoreMLLoader:
 
         sources = "compiled" if coreml_name.endswith(".mlmodelc") else "packages"
 
-        return self._load(coreml_path, compute_unit, sources)
-
-    def _load(self, coreml_path, compute_unit, sources):
         return (CoreMLModel(coreml_path, compute_unit, sources),)
 
 
@@ -109,3 +106,29 @@ class CoreMLLoaderUNet(CoreMLLoader):
     PACKAGE_DIRNAME = "unet"
     RETURN_TYPES = ("COREML_UNET",)
     RETURN_NAMES = ("coreml_model",)
+
+
+class CoreMLModelAdapter:
+    """
+    Adapter Node to use CoreML models as Comfy models. This is an experimental
+    feature and may not work as expected.
+    """
+
+    @classmethod
+    def INPUT_TYPES(s):
+        return {
+            "required": {
+                "coreml_model": ("COREML_UNET",),
+            }
+        }
+
+    RETURN_TYPES = ("MODEL",)
+
+    FUNCTION = "wrap"
+    CATEGORY = "Core ML Suite"
+
+    def wrap(self, coreml_model):
+        model_config = get_model_config()
+        wrapped_model = CoreMLModelWrapper(model_config, coreml_model)
+        patched_model = ModelPatcher(wrapped_model, get_torch_device(), None)
+        return (patched_model,)