document ncnn usage + what we tested / what we did not

README.md

@@ -54,7 +54,17 @@ Pick a model and run it:
 
 - **ONNX Runtime** (verified): use `onnx/*.onnx` (dynamic H/W). TensorRT /
   DirectML should work too (same op set) but are untested here.
-- **ncnn** (verified): use `ncnn/*.ncnn.param` + `*.ncnn.bin` (fp16).
+- **ncnn** (verified, fp16): `ncnn/*.ncnn.param` + `*.ncnn.bin`. Feed images with
+  `Mat.from_pixels`:
+  ```python
+  import ncnn
+  net = ncnn.Net(); net.load_param("4x_NERVE_fp16.ncnn.param"); net.load_model("4x_NERVE_fp16.ncnn.bin")
+  ex = net.create_extractor()
+  ex.input("in0", ncnn.Mat.from_pixels(bgr_uint8, ncnn.Mat.PixelType.PIXEL_BGR2RGB, w, h))
+  out = ex.extract("out0")[1]   # CHW float, 4x
+  ```
+  (Use `from_pixels`; the ncnn Python binding's raw-array constructor misbehaves
+  on large inputs. Outputs are fp16, so expect small deviations at hard edges.)
 - **chaiNNer**: load the `onnx/*.onnx` files directly. Loading the
   `.safetensors` via spandrel needs NERVE registered in your chaiNNer/spandrel
   build (not upstream yet).
@@ -185,8 +195,14 @@ development log — including dead ends and raw numbers — is in
   variant made thin lines *worse* and was reverted.
 - **OTF/GAN capability**: the small net trained productively under the full
   Real-ESRGAN OTF GAN recipe (no collapse).
+- **Runtime validation**: every released `.safetensors` loads (strict) and runs;
+  every `.onnx` loads in ONNX Runtime; the ncnn models were run at multiple input
+  sizes up to 720x720 (2880x2880 output).
 - **Deployability**: dynamic-ONNX export + ORT parity and ncnn conversion were
   verified at every stage (the numbers are in the log).
+- **Not tested here** (community welcome): TensorRT / DirectML *speed* and
+  fixed-shape static exports, CoreML, and on-device benchmarks. Train more
+  variants, benchmark, and share — the arch is standard ops only.
 
 ## Examples