Seedance 2.5 sequence run with a linked image and video: 20 s dark space with a window of light, a descent toward a woman lying on the floor and a closed eye
A dark space with a pale window of light and a tiny pale spot below, a descent toward a woman lying on the floor with her hair spread and her arms out, a close of her face in profile with her eyes closed, a close of her neck and collarbone with a tiny red mark, and a close of a closed eye.
Task: Render a descent from a dark space with a window of light toward a woman lying on the floor, then her face, neck and a closed eye as a golden-hour wet-stroke painting look, at 20 s.
Outcome: succeeded
0.84 s: A dark space with a pale window of light above, a tiny pale spot below.
2.51 s: Same.
4.18 s: Same.
5.85 s: The spot is a tiny lying woman.
7.52 s: Same.
9.19 s: A woman lying on the floor with her arms out, seen from above.
10.86 s: Closer, hair spread.
12.53 s: Close: her face in profile, eyes closed.
14.20 s: Close: her neck and collarbone, a tiny red mark.
15.87 s: Same.
17.54 s: Close: a closed eye.
19.21 s: Same.
Intent vs result: The sampled frames follow a slow descent over about 10 s and then three close-ups that end on a closed eye. The mark is tiny and the picture is not graphic. One linked image and one linked video are recorded; their disclosure and rights basis are unconfirmed, and the prompt asks that they set the characters' faces and colouring, so likeness is a hold.
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)."
},
{
"description": "1 linked video input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-09-02T22:44:13Z",
"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, one linked image input and one linked video input (references that the prompt asks to set the medium and the characters' faces and colouring), a long structured prompt in a shot-by-shot format for one gothic scene of two adults in golden-hour light, with a stated look target (a golden-hour wet-stroke painting look); 20 s, 16:9, audio requested, no seed set, no spoken lines requested. One of a set of sequence runs on 2 September 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."
],
"artifact_ids": [
"ast_01M64XVM80MXK7KC6JWQ04T8MG"
]
}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 descent from a window of light to a face is a patient way to reveal a figure.
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. |