Seedance 2.5 live-action test: 7 s throw on a lawn, a camera whip down to a yellow disc on a step, a hand lifts it
A woman in a grey tank top on a lawn before a brick-and-glass entrance draws a yellow disc across her waist and throws it, then the camera whips down to the disc on a concrete step where a hand reaches in beside a white sneaker and lifts it.
Task: Stage a woman on a lawn who throws a yellow disc, a quick whip down to the disc on a concrete step and a hand and shoe that take it as one continuous live-action take of 7 s.
Outcome: succeeded
0.29 s: A woman in a grey tank top stands on a lawn before a brick-and-glass entrance, a yellow disc at her waist.
0.88 s: She steps and twists, the disc low at her side.
1.47 s: She extends her arm in a throw, one foot forward.
2.05 s: She stands with her arm lowered, weight on the front foot.
2.64 s: She stands, small in the frame; a blurred yellow shape crosses the lower left.
3.23 s: The camera whips down to a yellow disc lying on a concrete step.
3.81 s: Same; the disc lies still.
4.40 s: A black-trousered leg and a white sneaker enter at the right.
4.99 s: Same; a hand reaches in from the top right.
5.57 s: The hand touches the rim of the disc beside the sneaker.
6.16 s: The hand lifts the disc's edge.
6.75 s: The hand and disc are gone; the sneaker remains.
Intent vs result: The sampled frames follow the plan: a throw, a camera whip down to the disc and a hand and shoe taking it. The throw itself is seen as a posed arm extension. 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": "9 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": "2026-09-25T03:35:31Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 7.042
},
{
"name": "resolution",
"value": "854x480"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 0
},
{
"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, 7 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 0.29 s to 6.75 s of a 7.04 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": 7
},
"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_01M64XWMVH8P1TET44DTVFMSP8"
]
}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 whip from a throw to the landing spot connects two beats with one camera move.
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. |