model card: the temporal-expansion ladder section (measured curve, the eye-vs-meter honesty, usage, provenance)

README.md

@@ -183,6 +183,72 @@ turbo LoRAs does not apply here.
 - Trainer: our ai-toolkit extension for H3 (span-aware packing verified
   bit-exact against ComfyUI)
 
+## The temporal-expansion ladder (new, 2026-08-24)
+
+The "considerably more ambitious" follow-up mentioned above has produced its
+first shippable piece. The pilot learned its task from targets the model
+generated itself; these checkpoints retrain the same recipe against real
+intermediate frames, and every training step is published so you can pick
+your own point on the curve.
+
+**What changed.** Same rank-16, attention-only construction, warm-started
+from the pilot. The training targets are now real: windows cut from the
+public GOPRO_Large deblurring dataset (240 fps source), decimated to the
+working frame rate and re-expanded, so the held tokens are scored against
+frames a real camera actually captured rather than an interpolation. The
+world clock in training is truthful (each token labelled with the real time
+it spans).
+
+**Measured, on scenes the adapter never saw** (four camera shoots fully
+disjoint from training, held-token error in latent space, lower is better;
+the no-adapter baseline is 1.23 and the plain interpolation the pass starts
+from scores 0.26):
+
+| step | 25 | 100 | 175 | 250 | 375 |
+|---|---|---|---|---|---|
+| error | 0.158 | 0.133 | 0.116 | 0.105 | 0.086 |
+
+The curve never turns: more steps keep measuring better, through the last
+checkpoint. And here is the honest part: **the numbers and the eye disagree
+about where to stop.** Step 100 was the pick in playback: fast motion comes
+out smooth and the clip still feels like itself. Step 375 measures best by
+a wide margin, but in side-by-side viewing it can read over-smooth, as if
+the motion had been graded. On a static-content probe the family does not
+invent motion (it lands below the interpolation floor rather than above
+it), so the disagreement is about feel, not correctness. We publish every
+25th step so you can find your own point; if you only take one file, take
+`warm100`.
+
+**Watch instead of reading.** Six arms of one clip, every panel with its
+settings and wall time burned in; the bottom-right panel is the full
+de-rope end to end for cost comparison:
+
+<video controls muted playsinline preload="metadata" width="100%"
+       poster="https://huggingface.co/MATLOWAI/MiniMax-H3-Motion-Adapter/resolve/main/assets/temporal_expansion_2x3_tile_poster.jpg">
+  <source src="https://huggingface.co/MATLOWAI/MiniMax-H3-Motion-Adapter/resolve/main/assets/temporal_expansion_2x3_tile.mp4" type="video/mp4">
+  <a href="https://huggingface.co/MATLOWAI/MiniMax-H3-Motion-Adapter/resolve/main/assets/temporal_expansion_2x3_tile.mp4">Download the comparison tile (mp4, 11 MB)</a>
+</video>
+
+**Use.** Exactly like the pilot: drop a file from `temporal_expansion/`
+into `models/loras/minimax_h3/`, load with a stock `LoraLoaderModelOnly`
+at strength 1.0 on the model that feeds the de-rope or windowed-insertion
+pass. Not for the first text-to-video pass.
+
+**Files.** `temporal_expansion/minimax_h3_temporal_expansion_warm100_r16.safetensors`
+(the playback pick, sha256 cbb23ad4...) and
+`minimax_h3_temporal_expansion_step025_r16.safetensors` through
+`step375_r16.safetensors`, every 25 steps of the same run (step375 sha256
+28f3d41d...). 63 MB each.
+
+**Training facts.** Warm-started from the pilot above; 375 steps, lr 1e-4,
+adamw8bit, bf16; 48 samples derived from GOPRO_Large (Nah et al., the
+public deblurring benchmark) plus the pilot's self-generated set for the
+difficulty gate; the trainer's span-aware packing verified bit-exact
+against ComfyUI. Unlike the pilot, this data includes real footage; the
+source dataset is public and widely used for research, and the derivation
+(decimate, re-expand, score held tokens) is described so it can be
+reproduced or swapped for your own footage.
+
 ## Base model and licence
 
 This is a LoRA for [MiniMax-H3](https://huggingface.co/MiniMaxAI/MiniMax-H3)