The 25-second clip, with the schedule that actually fixes it

.gitattributes

@@ -122,3 +122,5 @@ samples/long/ab.png filter=lfs diff=lfs merge=lfs -text
 samples/long/crop_ab.png filter=lfs diff=lfs merge=lfs -text
 samples/long/idol25-fit.mp4 filter=lfs diff=lfs merge=lfs -text
 samples/long/idol25-nofit.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/long/idol25-final.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/long/ghosting-fixed-vs-adaptive.png filter=lfs diff=lfs merge=lfs -text

samples/long/idol25-final.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714b6888de93aa37c46bdc55be14b4adc175312cb7d6e10733b07dccd8213a3c
+size 19826732

samples/long/schedule.md

@@ -0,0 +1,57 @@
+# What actually breaks a 25-second clip
+
+## Not the positions — the schedule
+
+`ltx_render_clips` samples with `DISTILLED_SIGMAS`, nine fixed numbers solved
+for the clip lengths the distillation used. `LTXVScheduler` instead derives its
+shift from the **latent's own token count**. A 25-second clip carries about 4.4x
+the tokens of a 2-second one, and the fixed schedule does not know that.
+
+The result is a sample that has not converged. On screen it is ghosting —
+furniture and curtains rendered semi-transparent, overlapping themselves — and
+roughly half the colour.
+
+| 25 s, 512x320, same prompt and seed | saturation | contrast | ghosting |
+|---|---:|---:|---|
+| fixed 8 (what this project shipped) | 0.094 | 0.108 | severe |
+| adaptive 8 | 0.127 | 0.124 | gone |
+| **adaptive 20** | 0.108 | **0.166** | gone, hands and fabric resolved |
+| *15 s reference* | *0.208* | *0.161* | — |
+
+Final render, 25 s at 1024x640 with the second pass: **saturation 0.161,
+contrast 0.180** — colour close to the fifteen-second reference and contrast
+above it.
+
+Long clips now switch to the adaptive schedule automatically past 15 s, in
+`ltx_av_generate`. A caller passing `steps` explicitly still overrides it.
+
+## Three times a metric pointed the wrong way
+
+Worth recording, because the same mistake kept recurring in different clothes.
+
+1. **Laplacian variance said the broken clips had improved 2.5x.** They were
+   sharper *and* broken — fused fingers, blown highlights, collapsing
+   proportions. Sharpness cannot see any of that.
+2. **"Nothing degrades over the clip"** came from the same measure: the
+   first-fifth to last-fifth sharpness ratio was flat. Saturation across the
+   whole clip had halved, which no sharpness statistic reports.
+3. **Saturation then preferred adaptive-8 over adaptive-20** (0.127 against
+   0.108). Side by side, adaptive-20 is clearly better: cleaner hands, defined
+   dress, a legible star belt. Saturation rewards a colour cast as readily as
+   colour.
+
+The common error was choosing a measure before enumerating how the thing could
+fail. "It will get blurry" was assumed, so sharpness was measured, and the
+actual failure was colour and anatomy. The user looking at the clips found it
+in seconds.
+
+## Not established
+
+* One prompt, one seed, one duration. Where the fixed schedule starts failing
+  was not bracketed — 15 s is where the switch was placed, from one good clip at
+  15 s and one bad one at 25 s, not from a sweep.
+* 20 steps was picked over 8 by eye. 12, 16, 30 were not tried.
+* The two-pass at 25 s does not fit a 16 GB card (OOM at 601 frames); the final
+  render was done on the Space's H200. One pass at 25 s does fit, at 6.58 GiB.
+* Position interpolation is still applied above 20 s and still measurably
+  sharpens. It is not what fixed this.