Seedance 2.5 grey-peg test: school hallway walk-and-talk, steady identity (20 s)
Twenty-second tracking take down a blue-locker corridor with a single character kept consistent from start to end; signage and locker geography follow the peg video.
Task: A long continuous camera move down a school hallway keeping the character in medium shot while the hallway geography passes behind her.
Outcome: succeeded
0.63 s: Medium close on the girl; blue lockers recede at right, white tile floor.
6.89 s: A wall sign with a large letter N and a school name passes behind her.
9.39 s: Lockers fill the right side; her ponytail and grey tee unchanged.
13.15 s: Camera has moved slightly lower; corridor lights and doors visible.
15.66 s: Frame widens: black trousers now visible, corridor receding with orange doors.
19.42 s: Same hallway; expression and costume unchanged.
Intent vs result: The 19.25 s peg video moves down the same hallway with a grey figure at lower centre and the wall sign near 8 s; the output reproduces the corridor, the sign placement and the locker side.
Publication update (2026-10-29): the founder has now cleared public use of this output, including incorporated input likenesses and soundtrack. Earlier rights/likeness holds described above are resolved by that confirmation. Reference-input files remain private. Audio remains not listened to; visual observations cover sampled frames only.
Structured fields
{
"inputs": [
{
"description": "5 linked image input(s) recorded in the generation metadata (details withheld)."
},
{
"description": "1 linked video input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-09-25T02:51:13Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 20.042
},
{
"name": "resolution",
"value": "1280x720"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 0
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5 text-and-reference video generation with a grey-peg motion video (a rendered blocking pre-visualisation that fixes camera path and positions), several approved scene stills and per-character face/front/back reference photos, plus a long structured prompt (look statement, reference-use rules, cast, camera, ordered choreography, continuity, sound). Historical founder test period using an older mannequin-based blocking pipeline. Sampled inspection: 16 timestamped frames from 0.63 s to 19.42 s of a 20.04 s file, plus ffmpeg scene detection at threshold 0.30 and blackdetect.",
"parameters": {
"seed": "unset",
"model": "seedance_2_5 (label in job metadata)",
"multi_shots": false,
"aspect_ratio": "16:9",
"audio_requested": true,
"resolution_label": "720p",
"requested_duration_s": 20
},
"limitations": [
"Sampled visual inspection from timestamped frames (contact sheets), not full real-time playback; motion smoothness, micro-timing and lip-sync are unrated.",
"Audio was not listened to; the file has an audio track but sound, dialogue and music are unassessed.",
"Prompt intent is taken from private job metadata and summarised here only in general terms; the founder's taste and intent for each test are unknown.",
"Single historical generation without a fixed seed; not a controlled benchmark and not validation of any current product or pipeline.",
"Sign text legibility uncertain at 320 px; no motion-quality judgement."
],
"artifact_ids": [
"ast_01M64VJEPXV8C7BKPN9TSHJS64"
]
}Evidence claims
- [sourced_fact] Timestamped observations above come from viewing 16 sampled frames of the output (sampled visual inspection, not full playback).
- [upstream_claim] The generation was run by the founder in an earlier test period; H01 did not run or reproduce it.
- [inference] Long continuous hallway moves are a strong case for a peg video; identity and wardrobe stayed stable for 20 s. Sign lettering beyond the first words was not verified at the sampled size.
Rights
| component | license | hosting | redistribution | modification | training | Evidence and notes |
|---|---|---|---|---|---|---|
| documentation | unknown | permitted | permitted | unknown | unknown | Original analysis written by H01 (an AI agent) for Veyrul from private viewing; no third-party text, frames or audio reproduced. |
| media | unknown | permitted | permitted | unknown | unknown | Founder confirmed public use of all these Higgsfield outputs on 2026-10-29, including incorporated reference inputs, likenesses and soundtrack. Audio has not been listened to; permission does not establish listening or independent review. |