Seedance 2.5 live-action test: 15 s handheld take of a young woman with a flying disc, an arm sweep, then a leg and sneaker over a railing
A handheld take of a young woman with a ponytail and a large yellow disc at the lower centre; her body tilts with an arm raised before a white-framed window, then she looks up and to the side, and the take ends on a dark leg and white-soled sneaker over a railing.
Task: Stage a young woman on school steps with a flying disc, a head-down sweep and a sneaker cresting a railing at the end as one continuous live-action take of 15 s.
Outcome: succeeded
0.63 s: Close: a large yellow disc at the lower centre, her face looking down at the left, red brick behind.
1.88 s: Her face looks down and left, brow tight.
3.14 s: Same; she looks to the right.
4.39 s: Her body tilts, an arm raised at the top right, before a white-framed window.
5.64 s: Close: her face lowered, an arm sweeping across the lower left.
6.90 s: Her face tilts up, brow furrowed.
8.15 s: Her face looks up and right, trees behind.
9.41 s: Medium: upper body, mouth parted, brick and bushes behind.
10.66 s: Medium: she looks left, a lawn and railing behind.
11.91 s: Same; she faces the camera.
13.17 s: Same.
14.42 s: A dark leg and a white-soled sneaker curve over a railing.
Intent vs result: The sampled frames show the disc only in the first sample, one person throughout, and a closing frame of a leg over a railing. 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": "4 linked image input(s) recorded in the generation metadata (details withheld)."
},
{
"description": "1 linked start_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": "2026-09-23T17:18:50Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 15.05
},
{
"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, 15 s, 16:9, 480p label, audio requested, no seed set. One of a set of live-action school-scene runs on 23 September 2026 (UTC). Sampled inspection: 12 timestamped frames from 0.63 s to 14.42 s of a 15.05 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": 15
},
"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_01M64XVTPCFDJ5K5Y4EWZD7NNY"
]
}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 closing detail of a single sneaker is enough to say the character has left the frame.
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. |