Seedance 2.5 reference-anchored test: 20 s vertical night-market street food
Lantern-lit street: skewers on coals, a sauce brush, dumplings in syrup, a stall holder with a flatbread stack and a sold-out sign, a held flatbread wedge and bokeh lights.
Task: Vertical phone-camera footage of a night-market street-food scene.
Outcome: succeeded
0.84 s: Lantern-lit street with a crowd in the foreground.
2.51 s: An older man grills a row of skewers over coals.
4.18 s: A sauce brush over glazed skewers.
5.85 s: Glazed skewers on coals.
7.52 s: Out-of-focus lantern bokeh.
9.20 s: A ladle pours syrup over purple and yellow dumplings in a pot.
10.87 s: Smoke and a lit sign above a crowd.
12.54 s: A woman in a headscarf behind a stall; a red sign reading SOLD is partly in frame.
14.21 s: She faces the camera.
15.88 s: She lifts a flatbread from a stack.
17.56 s: A hand holds a scallion flatbread wedge to camera.
19.23 s: Bokeh lights.
Intent vs result: The sampled frames show a vertical handheld-style montage with food close-ups, stall faces and bokeh; short sign text (SOLD) is legible at this size. Speech and sound were not assessed.
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": "2026-08-09T06:50:38Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 20.064
},
{
"name": "resolution",
"value": "720x1280"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 7
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5, one reference still used as the look-and-world anchor, a long structured prompt (one subject, a setting and a shot-by-shot format), 20 s, 9:16, audio requested, no seed set. One of a run of tests on 9 August 2026 (UTC) that each pair the same kind of reference still with a different subject, genre and visual style. Sampled inspection: 12 timestamped frames from 0.84 s to 19.23 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": "9:16",
"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_01M64W2E97F20RRTBAPYK13DV4"
]
}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] Vertical 9:16 food montage works as a sequence of short stall vignettes in the sampled frames.
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. |