Seedance 2.5 live-action test: 19 s table-wide pivot to a basketball court, a man at the fence smiles and falls onto his back
A camera along a chain-link fence that starts on a blue table with people, pivots to a basketball court where two men play, follows a man in a dark tank top and blue shorts to the fence for a low close-up of him smiling with arms raised, then tilts down to him lying on his back on a red court area with his arms out.
Task: Stage a table-wide that pivots to a basketball court, a follow of a man to the fence, a low close of him hanging and a tilt down to his backward fall as one continuous live-action take of 19 s.
Outcome: succeeded
0.79 s: Through a chain-link fence: a young man in white at the left, a blue table and two people beyond it, a brick building behind.
2.38 s: The camera moves along the fence; a person walks past the table.
3.97 s: A basketball court: two men play, one in a dark top and red shorts dribbling, one in a dark tank top and blue shorts.
5.55 s: The two stand on the court; one holds a ball.
7.14 s: The man in blue shorts moves toward the camera, a hoop behind.
8.73 s: A man's torso and blue shorts fill the frame as he comes up to the fence; a person low on the court behind him.
10.31 s: Close, through the fence: a man in a dark tank top with his arms raised above his head, smiling.
11.90 s: Same; he looks forward, arms up.
13.49 s: Same; his head tilts, still smiling.
15.07 s: The camera tilts down: his head and shoulders at the bottom, the court beyond with a person lying down.
16.66 s: He lies on his back on the court's red area, arms out, in blue shorts.
18.25 s: Same; he lies still.
Intent vs result: The sampled frames follow the plan: a table-wide, a pivot to the court, a follow to the fence, a low close-up and a tilt down to a man lying on his back. The fall itself falls between samples; the picture is slapstick and not graphic. 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": "19 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": "2026-09-25T07:26:45Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 19.042
},
{
"name": "resolution",
"value": "854x480"
},
{
"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, 19 s, 16:9, 480p 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 0.79 s to 18.25 s of a 19.04 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": "480p",
"requested_duration_s": 19
},
"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_01M64XX7DZ2V2SGXX5V3S8FPQH"
]
}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 pivot from a table to a court uses one passing body to join two areas of the same place.
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. |