Seedance 2.5 style variant with one linked image: 20 s tilted pillared hall, a lantern handed between two kneeling figures in dark red robes
A tilted dark pillared hall with a long-haired figure in red holding a lantern and a man, a lantern floating and a tumbling figure, a close of a long-black-haired person looking down, a close of a pale dark-haired man in profile beside a lantern, and two kneeling figures in dark red robes with a lantern between them.
Task: Render two adults in a flooded ruined hall who pass a small hand-lamp, as a wide, two close-ups and a closing two-shot as a guofeng ink-cloud look, at 20 s.
Outcome: succeeded
0.84 s: A tilted dark pillared hall: a long-haired figure in red holds a lantern, a man near.
2.51 s: The lantern floats, a figure tumbles.
4.18 s: Two figures at a lantern on a tilted floor.
5.85 s: Same.
7.52 s: Same.
9.19 s: Close: a long-black-haired person looking down, in a red robe.
10.86 s: Same.
12.53 s: Close: a pale dark-haired man in profile, a lantern at the right.
14.20 s: Same.
15.87 s: Two kneeling figures in dark red robes, a lantern between them, in a grey-white misty hall.
17.54 s: Same.
19.21 s: Same.
Intent vs result: The sampled frames follow a wide of about 8 s with a splash handover, a woman's close-up at about 9.2 to 10.9 s, a man's close-up at about 12.5 to 15.9 s and a closing two-shot with the lamp in joined hands. One linked image input is recorded; its disclosure and rights basis are unconfirmed.
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": "2026-08-30T09:06:19Z",
"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": 3
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5, one linked image input (a style reference; the prompt asks to take only its medium, palette and light), a long structured prompt that fixes one scene in three parts (a wide of about 8 s, two close-ups and a closing two-shot) and states the look target (guofeng ink-cloud), 20 s, 16:9, audio requested, no seed set. One of a set of style variants of the same scene on 30 August 2026 (UTC). 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.",
"Request vs picture: the prompt asks for an ink-cloud medium; at this size the frames read as a misty grey hall with flat anime-style figures and no ink-cloud forms are seen."
],
"artifact_ids": [
"ast_01M64XHWV20EAK8HBKSVSH1G3P"
]
}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 tilted frame adds instability to the handover.
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. |