Seedance 2.5 text-only sequence run: 20 s black stair with red veins, black water, a crouched red-haired man and a grey bundle
A black stair with red veins: a man in a dark coat and a figure in a grey cloak, a red-haired man crouched with a splash of black water, a crouch over a grey bundle, a close of a red-spiky-haired pale man looking down, a close of a long dark-haired person, and two figures on the stair seen from behind.
Task: Render a red-haired man and a woman climbing a drowning black stair with red veins as a wet-stroke test (newer clause), at 20 s.
Outcome: succeeded
0.84 s: A black stair with red veins: a man in a dark coat and a figure in a grey cloak.
2.51 s: A red-haired man crouched, another figure on the stair.
4.18 s: A splash of black water.
5.85 s: The red-haired man crouched.
7.52 s: Crouched over a grey bundle.
9.20 s: Close: a red-spiky-haired pale man looking down, in black armour.
10.87 s: Same.
12.54 s: Close: a long dark-haired person looking down.
14.21 s: Same, looking toward the camera.
15.88 s: Same.
17.56 s: Two figures on the stair seen from behind.
19.23 s: Same.
Intent vs result: The sampled frames hold the wide for five samples (about 8 s); the picture reads as a darker, painted set than the sibling run with the shorter prompt.
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
{
"run_at": "2026-08-31T08:26:51Z",
"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-only prompt (no linked inputs recorded in the job metadata), a long structured prompt with one scene in four parts (a wide of about 8 s, a close-up of each of two characters of about 4 s requesting spoken lines, and a closing two-shot) and a stated look target (a wet-stroke test (newer clause)), 20 s, 16:9, audio requested, no seed set. One of a set of sequence runs on 31 August 2026 (UTC). Whether the requested lines were spoken was not checked (audio not listened to). Sampled inspection: 12 timestamped frames from 0.84 s to 19.21 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."
],
"artifact_ids": [
"ast_01M64XPE3Y2Y6EZZ6SJN37X7TA"
]
}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] Black water that climbs the steps is shown in one splash and a crouch.
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. |