Seedance 2.5 live-action test: 24 s run and spin, a long close-up by a hedge, then a fence two-shot with a man hanging from a hoop
A woman in a dark top who runs along a path and spins, a long close-up of her face before hedges and a stone wall, a turn and track to a fence two-shot in which a man in a dark tank top and blue shorts hangs from a hoop, and her departure toward the camera.
Task: Stage a run and spin by a woman, a long hedge-side close-up, a turn to a fence two-shot with a man hanging from a hoop and her departure as one continuous live-action take of 24 s.
Outcome: succeeded
1.00 s: A woman in a dark top runs along a path before a brick-and-glass building.
3.01 s: She spins; her legs and the lawn fill a blurred frame.
5.01 s: Close: she stands on a lawn before hedges, looking off to the left.
7.01 s: Close: her face, brow raised, hedges and a stone wall behind.
9.02 s: Closer: she looks up to the left.
11.02 s: Close: she looks off to the right, a bench and a brick wall behind.
13.02 s: She walks toward the camera across the grass; a blue table at the right and a court at the left.
15.03 s: She stands at the left; through a fence a man in a dark tank top and blue shorts hangs from a hoop.
17.03 s: She stands at the left; the hanging man at the right behind the fence.
19.03 s: Same.
21.04 s: She walks away from the fence toward the right; the man still hangs.
23.04 s: Close: she walks toward the camera, a court at the right and a lawn behind.
Intent vs result: The sampled frames follow the plan's order: a run and whip, a sustained close at a hedge, a fence two-shot and a departure. A fall by the hanging man is not seen at the sampled times, and he is still hanging at about 21 s. The linked inputs are recorded by count only; their disclosure and rights basis are unconfirmed, and the prompt asks that they set the faces and wardrobe of the people shown, so likeness is a hold. Spoken lines were requested and not heard.
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": "15 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": "2026-09-25T07:25:28Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 24.042
},
{
"name": "resolution",
"value": "854x480"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 1
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5, linked reference inputs recorded in the job metadata (images that set the place, light, wardrobe and the people and one blocking video), a long structured prompt in a shot-by-shot format for one continuous live-action take with spoken lines requested, 24 s, 16:9, 480p label, audio requested, no seed set. One of a set of live-action school-scene runs on 25 September 2026 (UTC). Sampled inspection: 12 timestamped frames from 1.00 s to 23.04 s of a 24.04 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": "480p",
"requested_duration_s": 24
},
"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_01M64XX7WYAKVYV18WR84M2DPS"
]
}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 long close-up held beside a hedge lets a single face carry about a third of a 24 s take.
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. |