Re-render the samples through the full pipeline at 1024x640

.gitattributes

@@ -110,3 +110,11 @@ samples/idol/idol-10s-bf16.mp4 filter=lfs diff=lfs merge=lfs -text
 samples/idol/idol-15s.mp4 filter=lfs diff=lfs merge=lfs -text
 samples/idol/idol-10s-1024x640-2pass.mp4 filter=lfs diff=lfs merge=lfs -text
 samples/idol/sharpness-1pass-vs-2pass.png filter=lfs diff=lfs merge=lfs -text
+samples/sharp/00-robot.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/01-dune.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/02-forge-unpadded-local.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/02-forge.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/03-road.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/04-smoke.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/05-idol-15s.mp4 filter=lfs diff=lfs merge=lfs -text
+samples/sharp/sheet.png filter=lfs diff=lfs merge=lfs -text

samples/sharp/00-robot.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:989a5203550b42ae616e258398a7f36b20896bc86f5ee09728c8f024d548cf1d
+size 1562023

samples/sharp/01-dune.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a3b5d2c455d43b86254fd002b469ffef06e78438ef07c8033bf00345c72871
+size 573208

samples/sharp/02-forge-unpadded-local.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95f5f59400a4fec548d0c10b436d656ff7eab16ae260ef149df10e23b4b15b63
+size 462652

samples/sharp/02-forge.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa91b6bbbdc3af4dd324c0a9ba5449836c7a2ab94d337abf86dc639f8797c2f
+size 1743460

samples/sharp/03-road.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de20479a64e2b837338c77fd5f14f4db370013e1fb6b395510c81960357db04
+size 934042

samples/sharp/04-smoke.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d23d14e8cfa9df2969e76f42fc023c21aaa7d2cffce311e287f92ab409cda86f
+size 657191

samples/sharp/05-idol-15s.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b167fc290bde99935f1af16f0839cd25f60bb45c4132ef6b3781a076a9ac06a2
+size 9985850

samples/sharp/README.md

@@ -0,0 +1,75 @@
+# Full-pipeline renders — 1024x640
+
+These are the samples as the vendor's graph actually produces them: sample at
+512x320, upscale the latent 2x, sample again at 1024x640. Everything else in
+`../` stops after the first pass.
+
+That second pass was skipped in this project from the start, on a written
+assumption that a 16 GB card could not afford four times the token count. It
+was never measured. Measured, it peaks at **10.03 GiB** and adds about a minute
+— and it is the difference between soft and sharp: **4.1x the Laplacian
+variance** against the one-pass output enlarged afterwards, on a common grid.
+The comparison crop is at `../idol/sharpness-1pass-vs-2pass.png`.
+
+| file | seconds | prompt |
+|---|---:|---|
+| `00-robot.mp4` | 2.0 | humanoid robot, rain-slick loading bay |
+| `01-dune.mp4` | 2.0 | lone figure walking a red dune at sunset |
+| `02-forge.mp4` | 2.0 | blacksmith, anvil, sparks — **does not follow the prompt, see below** |
+| `02-forge-unpadded-local.mp4` | 2.0 | the same prompt, encoded unpadded, which does |
+| `03-road.mp4` | 2.0 | sports car through a wet mountain hairpin at night |
+| `04-smoke.mp4` | 2.0 | rescue robot in a collapsed corridor |
+| `05-idol-15s.mp4` | **15.0** | the anime idol prompt, 361 frames |
+
+Prompts are the ones in `../README.md` and `../idol/prompt.txt`, unchanged.
+
+## Rendered on the Space, not the workstation
+
+All six came from
+[the Space](https://huggingface.co/spaces/topabaem/LTX-2.5-Text-Encoder-4bit-8GB-Demo),
+which runs this same 4-bit encoder on ZeroGPU. The 15-second two-pass render
+takes 110 s there. The local V100 was lent to another job at the time, and this
+did not need it.
+
+One consequence worth stating: the Space encodes through ComfyUI's own path,
+which left-pads every prompt to 1024 tokens. The clips in `../` were encoded
+unpadded. Same encoder, same weights, slightly different conditioning — so
+these are not the one-pass clips with a second pass bolted on, they are
+different samples.
+
+## One of these does not follow its prompt, and it is informative
+
+`02-forge.mp4` is not a forge. It is a man beside a tree, and three seeds
+(20260815, 7, 42) all landed somewhere unrelated.
+
+That prompt renders correctly in `../` — anvil, glowing steel, hammer, sparks.
+`02-forge-unpadded-local.mp4` is that render, kept here for the comparison.
+
+The difference is not the second pass: re-running on the Space at `refine=0`,
+same seed, still gives the man and the tree. It is **the conditioning path**.
+The Space encodes the way ComfyUI does, left-padding every prompt to 1024
+tokens; the clips in `../` were encoded unpadded. Same encoder, same weights,
+same DiT, same seed, same resolution — and one finds the forge while the other
+does not.
+
+It does not run one way. On this batch the padded path produced a *better*
+robot, dune and idol than the unpadded renders in `../` did, and the unpadded
+path is the one that finds the forge. The honest statement is that padding
+changes **which prompts land**, not how good the output is, and this project's
+own note in `ltx_conditioning_dump.py` — that the padded path is simply the
+right one for feeding a DiT — is not supported by that.
+
+Which of the two is closer to what Lightricks intended has not been established
+here, and neither has whether the padded implementation is faithful.
+
+## What is deliberately not here
+
+**The BF16 comparison in `../` was not regenerated.** Both of its sides are
+one-pass and differ only in the encoder, which is the whole point of it.
+Re-rendering one side at twice the resolution would have replaced a controlled
+comparison with a pretty one.
+
+**Image-to-video cannot use the second pass yet.** `LTXVLatentUpsampler`
+discards the noise mask, so a guide would have to be rebuilt at the new scale,
+and nothing does that. The Space hides the control on that tab rather than
+offering something that would fail.