Seedance 2.5 live-action test: 26 s wide school hallway, a man stops at a trophy case, a woman approaches and both walk away
A wide school hallway with a man in a red tee standing before a lit trophy case, a woman farther back who approaches and slides past, then both walk away along the hall past a large blue wall letter and lockers.
Task: Stage a wide school hallway in which a man in a red tee stops at a trophy case, a woman approaches and the two walk away down the hall as one continuous live-action take of 26 s.
Outcome: succeeded
1.09 s: Wide hallway: a man in a red tee stands at the left facing a lit trophy case; a long hall beyond with a distant figure.
3.26 s: He steps forward, looking up; a blue wall letter, a distant woman.
5.43 s: He stands looking up; the woman far down the hall.
7.60 s: Same; he stands still facing the case.
9.77 s: A woman stands beside him at the far right, farther back.
11.94 s: Same; two figures, the woman at the right.
14.11 s: She walks across behind him.
16.28 s: She walks toward the right while he looks at the case.
18.45 s: Closer: he looks at the case at the left; she stands by the wall letter.
20.62 s: He turns his back to the camera; she stands by the wall letter.
22.79 s: Both walk away along the hall: man at the left, woman at the right.
24.96 s: They walk away down the long hallway, small.
Intent vs result: The sampled frames follow the plan: a stop at the case, a woman approaching and passing, then both leaving toward the lockers. The framing stays wide for most of the take. The linked inputs are recorded by count only; their disclosure and rights basis are unconfirmed, and the prompt asks that they set the faces and wardrobe of the people shown, so likeness is a hold. Spoken lines were requested and not heard.
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": "9 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": "2026-09-25T02:54:21Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 26.042
},
{
"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, linked reference inputs recorded in the job metadata (images that set the place, light, wardrobe and the people and one blocking video), a long structured prompt in a shot-by-shot format for one continuous live-action take with spoken lines requested, 26 s, 16:9, 720p label, audio requested, no seed set. One of a set of live-action school-scene runs on 25 September 2026 (UTC). Sampled inspection: 12 timestamped frames from 1.09 s to 24.96 s of a 26.04 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": 26
},
"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."
],
"artifact_ids": [
"ast_01M64XWCEYJ82DJHWJM799P6QY"
]
}Evidence claims
- [sourced_fact] Timestamped observations above come from viewing 12 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] A single wide master lets two people interact without any cut.
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. |