Card: why the pyramid (11x less compute)

README.md

@@ -20,8 +20,24 @@ learnable layer-slice mixer (10.0M), and the AE decoder retrained as a pixel-spa
 | training | FLUX-Reason-6M, one RTX 4080 |
 | licence | MIT |
 
-**Training is still running** — the bundled `transformer/` is a snapshot of step **212 000** (lr was
-restarted at 1e-4 on step 192 000, so it is mid-recovery and will be replaced).
+## Why the pyramid
+
+At the same parameter count, a flat classic DiT (12 blocks at width 1024, one resolution) costs
+**232 GFLOP** per forward pass of the body; the pyramid costs **20.4** — **11× less compute**. The
+step itself runs 97 ms vs 196 ms because it is memory-bound, and the detail metric is 0.54 vs 0.18
+(ground truth 0.913, AE ceiling 0.859).
+
+- Width grows as tokens shrink: expensive layers run on 16–64 tokens, while the 1024-token grid keeps
+  cheap 3×3 convolutions — convolutions are local, so anatomy and texture survive.
+- Additive skip connections at every level: fine structure is built at its own level instead of being
+  pulled through one single-resolution attention stack.
+- Text reaches all four levels; the 16-token bottleneck (width 1536, full attention) holds composition
+  and symmetry.
+
+## Training in progress
+
+The bundled `transformer/` is a snapshot of step **212 000**; lr was restarted at 1e-4 on step 192 000,
+so it is mid-recovery and will be replaced.
 
 ## Examples