Seedance 2.5 volcanic couture fashion film with a white-and-black flash at 15 s (20 s)
Silver-grey editorial sequence of a lone model on a volcanic plain; a white frame and a 0.9 s black gap at 14.85-15.92 s split the clip into two halves.
Task: High-fashion editorial: black gravel dunes, charcoal fog, a model holding the garment's line against rising wind.
Outcome: partial
0.63 s: Tiny standing figure on a black dune under steel cloud.
4.39 s: Profile close-up of a shaved-head model in black couture with rigid shoulders.
5.64 s: Macro of pleated black fabric over gravel and water.
9.40 s: Wind drags the cape sideways on the dune against fog.
11.91 s: The garment spreads into a wide wing-like silhouette with the model's head at the centre.
14.85 s: Full white frame.
15.05 s: Black frame; black until 15.92 s with a speck at the lower right.
16.93 s: Front-facing model in the shoulder couture on lava rock; end returns to the dune wide at 18.18 s.
Intent vs result: Detector fires five times between 14.83 and 15.0 s (flash flicker) and blackdetect flags 15.00-15.92 s: a white-then-black transition at the clip midpoint, plausibly an intentional flash cut but not confirmed from the prompt summary.
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": "1 linked image input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-08-09T07:52:53Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 20.064
},
{
"name": "resolution",
"value": "1280x720"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 10
},
{
"name": "black_intervals",
"value": "15.00-15.92 s"
}
],
"procedure": "Seedance 2.5, one style reference still, structured prompt with one person in sculptural couture on a volcanic plain, 20 s, 16:9, 720p, audio requested. Sampled inspection: 20 timestamped frames from 0.63 s to 19.44 s of a 20.06 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.",
"White flash plus 0.9 s black gap at 14.85-15.92 s."
],
"artifact_ids": [
"ast_01M64VJXW8GS2T8G50VTJ9N818"
]
}Evidence claims
- [sourced_fact] Timestamped observations above come from viewing 20 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 strobing white-black beat near 15 s is a recognizable transition artefact; the first and last shots mirror each other (tiny figure on the dune), which gives the clip a clear shape.
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. |