treatment record
glitch-07
The preferred look applied to the most recent 1,440 published frames: segmentation contours and id boxes merged with pose skeletons, composited 'under' so the blockouts cut and carry the HUD.
- status
- preferred
- upstream
- pass-02 frames 9,132–10,571
- 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
f0091456:21
f0092656:26
f0093856:31
f0095296:37
f0096496:42
f0097696:47
f0099136:53
f0100336:58
f0101537:03
f0102977:09
f0104177:14
f0105617:20This treatment kept no sampled frames of its own, so these are the source frames it consumed — pass-02 9,132–10,571, before the treatment was applied.
Same recipe as glitch-06, different window. Nothing about the treatment changed - this exists because glitch-06 stopped at frame 6,251 and the pass did not.
Upstream
- pass
- pass-02
- frames
- 9,132–10,571
- source
regenerable: hstack of passes/pass-02/{frames,text} 9132-10571 (image left, text right)- source sha256
dde16d6b2eb7
Regenerating the source
ffmpeg -framerate 24 -start_number 9132 -i frames/frame_%06d.png -framerate 24 -start_number 9132 -i text/frame_%06d.png -frames:v 1440 -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
- 1,440
- clip length
- 1 m 00 s
- time to render it
- 14 m 43 s
- chunking
- 160-frame windows, 9 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
- 483
- per frame
- 0.335
| label | detections | |
|---|---|---|
| person | 147 | |
| bench | 53 | |
| car | 38 | |
| train | 23 | |
| refrigerator | 22 | |
| traffic light | 22 | |
| clock | 18 | |
| truck | 14 | |
| boat | 14 | |
| tie | 12 |
Outputs
| file | frames | geometry | runtime | bytes | sha256 |
|---|---|---|---|---|---|
previews/glitch-07.under-contours-skeletons.f009132-010571.mp4 | 9,132–10,571 | 1536x1344 | 1 m 00 s | 299.5 MB | 46acd0aec121 |
Named and hashed, not hosted. Nothing in this repository is a master.
Frame sequence
- directory
frames/- files
- 1,440
- bytes
- 2.0 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.