Add usage example

README.md

@@ -25,6 +25,35 @@ The original ArcFace model and its theoretical foundation are described in the p
 
 AuraFace is a highly discriminative face recognition model designed using the Additive Angular Margin Loss approach. It builds upon the principles introduced in ArcFace and has been trained on commercially and publicly available data sources to enable its usage in commercial setting. AuraFace is tailored for scenarios requiring robust and accurate face recognition capabilities with minimal computational overhead.
 
+## Usage Example
+
+To get a face embedding using AuraFace, it can be used via [InsightFace](https://github.com/deepinsight/insightface/tree/master) as shown in the example:
+
+```python
+from huggingface_hub import snapshot_download
+from insightface.app import FaceAnalysis
+import numpy as np
+import cv2
+
+snapshot_download(
+    "fal/AuraFace-v1",
+    local_dir="models/auraface",
+)
+face_app = FaceAnalysis(
+    name="auraface",
+    providers=["CUDAExecutionProvider", "CPUExecutionProvider"],
+    root=".",
+)
+
+input_image = cv2.imread("test.png")
+
+cv2_image = np.array(input_image.convert("RGB"))
+
+cv2_image = cv2_image[:, :, ::-1]
+faces = face_app.get(cv2_image)
+embedding = faces[0].normed_embedding
+```
+
 ## Intended Use
 
 ### Primary Use Cases