embed speed chart + consumer note + cross-links

README.md

@@ -34,6 +34,10 @@ Part of the **BODY** suite by **Philip Hofmann** — networks built to be
 real-world usable first, not benchmark-chasing. See
 [Relation to NERVE](#relation-to-nerve) for which one to pick.
 
+All HEART models were trained on a single consumer GPU (**RTX 3060, 12 GB**) — this network trains and runs on ordinary consumer hardware, no server-class GPU required.
+
+**NERVE links:** [models & configs](https://huggingface.co/Phips/NERVE) · [try it online (ZeroGPU)](https://huggingface.co/spaces/Phips/nerve) · [convert a checkpoint](https://huggingface.co/spaces/Phips/nerve-convert) · [local app](https://github.com/Phhofm/nerve-app) · [train your own (Colab)](https://github.com/Phhofm/nerve-train)
+
 > Short version: copy `heart_arch.py` into traiNNer-redux, train with
 > `lq_size: 96`, export to ONNX, run it (ONNX Runtime verified). Details below.
 
@@ -317,6 +321,8 @@ options as NERVE's published config (`builderOptimizationLevel=5` + CUDA graphs)
 | HEART 4x OTF GAN | 16.7M | 809 ms | 753 ms | **270 ms** | 679 MB |
 | HAT_M 4x | 20.8M | 1485 ms | 849 ms | 598 ms (107 FPS) | 2428 MB |
 
+![HEART vs HAT_M — PyTorch / ONNX / TensorRT speed and VRAM](docs/heart_speed.png)
+
 **Verdict.** At a 256px tile HEART is **~1.8x faster than HAT_M** in PyTorch and
 uses **~3.6x less VRAM** (679 MB vs 2.4 GB) — a bigger margin than our earlier
 30k-iteration note suggested. Under **TensorRT** both get dramatically faster,