Merge branch 'main' of https://huggingface.co/stabilityai/control-lora into main

README.md

@@ -23,11 +23,13 @@ Each Control-LoRA has been trained on a diverse range of image concepts and aspe
 ### MiDaS and ClipDrop Depth
 ![canny](samples/depth-sample.jpeg)
 
+This Control-LoRA utilizes a grayscale depth map for guided generation.
+
 Depth estimation is an image processing technique that determines the distance of objects in a scene, providing a depth map that highlights variations in proximity.
 
-The Control-LoRA utilizes a grayscale depth map for guided generation.
+The model was trained on the depth results of `MiDaS dpt_beit_large_512`.
 
-In the example above, we compare the depth results of `MiDaS dpt_beit_large_512` and the `Portrait Depth Estimation` (available in the [ClipDrop API by Stability AI](https://clipdrop.co/apis/docs/portrait-depth-estimation)).
+It was further finetuned on the `Portrait Depth Estimation` model available in the [ClipDrop API by Stability AI](https://clipdrop.co/apis/docs/portrait-depth-estimation).
 
 ### Canny Edge
 ![canny](samples/canny-sample.jpeg)