Upload README.md with huggingface_hub

README.md

@@ -45,18 +45,25 @@ encoder and both H3 VAEs from
 
 ## Benchmarks (RTX PRO 6000 Blackwell Max-Q, 96 GB, SageAttention, 1344×768×124f, 20 steps)
 
-| DiT variant | Size | s/step | Notes |
-|---|---|---|---|
-| bf16 (reference) | 66.3 GB | 14.65 | baseline quality |
-| pruned int8_convrot (official) | 21.0 GB | 22.7 | pruned arch, W8A16 dequant path |
-| **nvfp4 (this repo)** | 38.6 GB | 19.8* | full (unpruned) model |
-| **nvfp4_fpmm (this repo)** | 38.6 GB | ~bf16* | full (unpruned) model |
+All on the same card, same seed, SageAttention. **torch cu130 build strongly
+recommended** — it enables comfy_kitchen's optimized CUDA kernels (on cu128
+the FP4 path runs emulated and is ~2.3× slower).
 
-\* measured on torch 2.8+cu128, where comfy_kitchen runs **fallback** (emulated)
-FP4 ops — a cu130 torch build unlocks the optimized CUDA kernels and these
-numbers will be updated. Same-seed visual quality vs bf16: no quantization
-artifacts observed (trajectory divergence only, PSNR vs bf16 ≈ within the
-pipeline's chaotic-divergence regime; see sample).
+| DiT variant | Size | s/step (cu130) | s/step (cu128) | Notes |
+|---|---|---|---|---|
+| **nvfp4 (this repo)** | 38.6 GB | **8.47** | 19.8 (emulated) | full model, **1.5× faster than bf16** |
+| convrot W4A4 (measured, not shipped) | 37.4 GB | 9.69 | — | visible text-rendering artifacts |
+| bf16 (reference) | 66.3 GB | 12.76 | 14.65 | baseline quality |
+| **nvfp4_fpmm (this repo)** | 38.6 GB | — | 14.99 | ties bf16 on cu128, 42 % less VRAM |
+| pruned int8_convrot (official) | 21.0 GB | — | 22.7 | pruned arch, W8A16 dequant path |
+
+Stacking ComfyUI's `EasyCache` (threshold 0.1) on top cuts wall time a further
+~1.4× with deviation within the pipeline's run-to-run variance.
+
+Same-seed visual quality of `nvfp4` vs bf16: no quantization artifacts observed
+(trajectory divergence only — diffusion is chaotic under any weight
+perturbation; see sample). The W4A4 experiment degraded fine text rendering,
+which is why it is not shipped.
 
 A same-seed sample generated with this checkpoint is in
 [`assets/sample_r2v_5s.mp4`](assets/sample_r2v_5s.mp4).