Seedance 2.5 live-action test: 15 s science-room take, a seated woman rises and walks past the lens as a man in a red tee approaches
A sunlit science room with a window wall; a woman seated at a black table rises and walks toward the lens while a man in a red tee stands, approaches and smiles, ending with her back to camera and him in front of a filing cabinet.
Task: Stage a science-room exchange in which a seated woman rises and walks past the lens while a man approaches as one continuous live-action take of 15 s.
Outcome: succeeded
0.63 s: Wide: a sunlit science room with a window wall; a woman seated at a black table at the right, cheek on her hand; a man walking at the left.
1.88 s: Same; he stands with his back turned to her.
3.14 s: She rises and leans on the table edge; he stands at the left.
4.39 s: She walks toward the camera; a second figure stands behind her at the back.
5.64 s: Close: she passes near the lens, eyes lowered.
6.90 s: Over her shoulder (ponytail at the left), a man in a red tee walks toward her.
8.15 s: He stands smiling beside a filing cabinet; her ponytail fills the left foreground.
9.41 s: Same; he smiles toward her.
10.66 s: Same framing; he stands with loose arms.
11.91 s: Same.
13.17 s: Same.
14.42 s: She turns and walks away; he steps toward her.
Intent vs result: The sampled frames show the sequence the prompt describes: a seated woman rises, passes the lens, and a man in a red tee approaches and smiles. They hold one framing from about 8 to 13 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": "7 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)."
}
],
"run_at": "2026-09-23T09:08:07Z",
"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), 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_01M64XVFTVTJM2CW36X8R3KVBE"
]
}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 pass near the lens can hand the camera from a wide to an over-the-shoulder view without a cut.
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. |