Seedance 2.5 live-action test: 30 s low tracking master on a soccer field, a conversation, a rolling ball, a kick and a woman with her arms raised
A 30 s low tracking master on a soccer field in which a woman in a dark top runs in and talks with a woman in a blue bib and a goalkeeper in a green top, a ball rolls on the grass toward her, she kicks at a goal where the goalkeeper waits and ends standing behind the ball with both arms raised before bleachers.
Task: Stage a 30 s low tracking master on a soccer field that follows a woman into a conversation with a goalkeeper and a woman in a bib, tracks a rolling ball to her and ends with her arms raised as one continuous live-action take of 30 s.
Outcome: succeeded
1.25 s: A soccer field: a woman in a dark top runs at the right near a goal post; two figures far behind a goal.
3.76 s: Three women in conversation: one in a blue bib, one in a green goalkeeper top, one in a dark top with a ponytail.
6.26 s: Closer; the woman in the dark top has a hand on her hip, facing the others.
8.76 s: Same; the goalkeeper in green speaks.
11.27 s: The woman in the blue bib at the left looks toward the others; bleachers behind.
13.77 s: The women turn away; a ball rolls on the grass at the right.
16.27 s: A woman in a blue bib walks toward the bleachers at the left, a ball on the grass.
18.78 s: A ball on the grass at low level; a leg in dark trousers enters at the right.
21.28 s: Low: a dark-trousered leg steps over a ball; a goal and a goalkeeper in green beyond.
23.78 s: Same; she stands at the ball, the goal behind.
26.29 s: A woman in a dark top stands behind the ball with both arms raised.
28.79 s: She stands with an arm up beside the ball, bleachers behind.
Intent vs result: The sampled frames follow the plan's order: a run in, an arc into a conversation, a walk toward the bleachers, a low track to a ball, a goal-facing stance and a closing celebration pose. The kick itself falls between samples. 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": "14 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": "2026-09-25T07:30:12Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 30.042
},
{
"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, 30 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 1.25 s to 28.79 s of a 30.04 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": 30
},
"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_01M64XXAAGKAM6MPVC452SQVTK"
]
}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 low camera that stays at ball height ties a talk, a roll and a kick into one connected piece of field.
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. |