Add minimal usage snippets and hero image

README.md

@@ -22,6 +22,8 @@ predicts a per-pixel inverse-depth map (near = bright, far = dark).
 It is the model used by the LiteRT `compiled_model_api/depth_estimation` Android
 sample.
 
+![MiDaS small — input photo and on-device inverse-depth map (LiteRT GPU)](sample-depth.png)
+
 ## Files
 
 | File | Precision | Size |
@@ -71,6 +73,39 @@ The fp16 model compiles to **234 / 234 nodes on the LiteRT GPU delegate
 (best 1.1 ms). `RESIZE_BILINEAR align_corners=True` is GPU-supported as-is; no
 model change needed.
 
+## Minimal usage
+
+**Android (Kotlin, CompiledModel GPU)**
+
+```kotlin
+val model = CompiledModel.create(context.assets, "midas_small_256_fp16.tflite",
+    CompiledModel.Options(Accelerator.GPU), null)
+val inputs = model.createInputBuffers()
+val outputs = model.createOutputBuffers()
+inputs[0].writeFloat(nhwc)             // [1,256,256,3] ImageNet-normalized RGB, NHWC
+model.run(inputs, outputs)
+val depth = outputs[0].readFloat()     // [1,256,256] relative inverse depth
+```
+
+**Python (desktop verification)**
+
+```python
+MEAN = np.array([0.485, 0.456, 0.406], np.float32)
+STD  = np.array([0.229, 0.224, 0.225], np.float32)
+import numpy as np
+from PIL import Image
+from ai_edge_litert.interpreter import Interpreter
+
+img = Image.open("photo.jpg").convert("RGB").resize((256, 256))
+x = ((np.asarray(img, np.float32) / 255 - MEAN) / STD)[None]      # [1,256,256,3] NHWC
+
+it = Interpreter(model_path="midas_small_256_fp16.tflite"); it.allocate_tensors()
+it.set_tensor(it.get_input_details()[0]["index"], x); it.invoke()
+d = it.get_tensor(it.get_output_details()[0]["index"])[0]         # [256,256]
+d = (d - d.min()) / (d.max() - d.min())                           # near = bright
+Image.fromarray((d * 255).astype(np.uint8)).save("depth.png")
+```
+
 ## Training data & PII
 
 This is a weights-exact format conversion of Intel ISL's **MiDaS v2.1 small**; no new