Update README.md

README.md

@@ -62,6 +62,24 @@ image
 
 💡 Note: You can compute the conditioning map using the `NormalBaeDetector` from the `controlnet_aux` library
 
+```python
+from controlnet_aux import NormalBaeDetector
+from diffusers.utils import load_image 
+
+normal_bae = NormalBaeDetector.from_pretrained("lllyasviel/Annotators")
+
+# Load an image
+im = load_image(
+  "https://huggingface.co/jasperai/Flux.1-dev-Controlnet-Surface-Normals/resolve/main/examples/output.jpg"
+)
+
+surface = normal_bae(
+  im
+)
+surface
+```
+
+
 # Training
 This model was trained with depth maps computed with [Clipdrop's surface normals estimator model](https://clipdrop.co/apis/docs/portrait-surface-normals) as well as an open-souce surface normals estimation model such as Boundary Aware Encoder (BAE).