treatment record
glitch-08
The preferred look over pass frames 6,252-9,131 - the window between glitch-06 and glitch-07. With this, every frame Pass 2 has published is treated.
- status
- preferred
- upstream
- pass-02 frames 6,252–9,131
- evidence
- A lossless frame sequence was written and manifested; the video is derived from it.
Its window on pass 2's full 43,200-frame axis.
what it looks like · 12 frames
f0062654:21
f0065054:31
f0067694:42
f0070334:53
f0072975:04
f0075615:15
f0078015:25
f0080655:36
f0083295:47
f0085935:58
f0088576:09
f0091216:20This treatment kept no sampled frames of its own, so these are the source frames it consumed — pass-02 6,252–9,131, before the treatment was applied.
Nothing. Same recipe as glitch-06 and glitch-07; this exists purely to close a coverage gap that opened because treatments were being run on the newest frames while the pass kept moving.
Upstream
- pass
- pass-02
- frames
- 6,252–9,131
- source
regenerable: hstack of passes/pass-02/{frames,text} 6252-9131 (image left, text right)- source sha256
4115045d1be2
Regenerating the source
ffmpeg -framerate 24 -start_number 6252 -i frames/frame_%06d.png -framerate 24 -start_number 6252 -i text/frame_%06d.png -frames:v 2880 -filter_complex '[0:v][1:v]hstack=inputs=2' -c:v prores_ks -profile:v 4 -pix_fmt yuv444p10le source.mov |
Render
- composite
- under
- device
- cpu
- frames
- 2,880
- clip length
- 2 m 00 s
- time to render it
- 31 m 19 s
- chunking
- 160-frame windows, 18 of them, 124-frame lead-in discarded
- overlay draws
- box, mask, skeleton, face_mesh
- overlay hold
- 1 frame
- stroke / bracket / label floor
- 5 / 56 / 4,800 px²
Displacement layers
| grid | max offset | angle | sparsity | jitter | hold | stagger | seed | envelope |
|---|---|---|---|---|---|---|---|---|
| 4×3 | 32 | 90° | 0.5 | 0.8 | 8 | 0.6 | 5 | none |
| 8×7 | 22 | 0° | 0.8 | 0.8 | 6 | 0.5 | 9 | none |
| 20×18 | 14 | 0° | 0.93 | 0.8 | 4 | 0.8 | 13 | none |
What the detector found
- model
yolo11n-seg.pt + yolo11n-pose.pt- confidence floor
- 0.15
- detections
- 1,047
- per frame
- 0.364
| label | detections | |
|---|---|---|
| person | 347 | |
| train | 101 | |
| bench | 74 | |
| refrigerator | 58 | |
| traffic light | 57 | |
| bird | 41 | |
| truck | 32 | |
| suitcase | 30 | |
| vase | 26 | |
| clock | 24 |
Outputs
| file | frames | geometry | runtime | bytes | sha256 |
|---|---|---|---|---|---|
previews/glitch-08.under-contours-skeletons.f006252-009131.mp4 | 6,252–9,131 | 1536x1344 | 2 m 00 s | 598.9 MB | beae935821ae |
Named and hashed, not hosted. Nothing in this repository is a master.
Frame sequence
- directory
frames/- files
- 2,880
- bytes
- 4.0 GB
- geometry
- 1536x1344
- lossless
- yes
- manifest
frames-manifest.json
The treatment's record, the same way a pass's frames are its record. preview.mp4 is derived from these, not the other way round — extracting frames back out of it returns the codec's opinion of the pixels.
Provenance
This treatment was run as a local process rather than dispatched through the mesh, so it has no task id, no lease and no event trail. That is a gap in the record, and it is recorded as one.