Seedance 2.5 live-action test: 12 s aerial swoop over a school campus to a doorway two-shot, the man walks back inside
A high aerial view over a red-brick school and a sports court that descends to glass doors at the top of a ramp, where a woman in a dark top and a man in a red tee step out; they stand in a doorway two-shot before the man steps back toward the doors and walks into the bright hallway.
Task: Stage a high aerial swoop over a school campus that descends to the doorway where a woman and a man stand, ending with the man walking back inside as one continuous live-action take of 12 s.
Outcome: succeeded
0.50 s: High over a school campus: a red-brick building, a sports court and lawns.
1.51 s: The camera descends over a lawn and a paved path toward the school.
2.51 s: It descends toward glass doors at the top of a ramp and steps.
3.51 s: A woman in a dark top and a man in a red tee step out of the doors onto the landing.
4.52 s: Two-shot at the doorway: the woman at the left, the man at the right, both facing the camera.
5.52 s: Same; the man looks off to the right.
6.52 s: Same.
7.53 s: The man turns his head and glances aside.
8.53 s: He leans toward her, his weight on one leg.
9.53 s: He steps back toward the doors; the woman is out of frame at the left.
10.54 s: He walks toward the open glass doors, his back to us.
11.54 s: He is small in the doorway.
Intent vs result: The sampled frames follow the plan: an aerial descent, a doorway two-shot and a man who turns back in. The descent takes about 3 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": "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": "2026-09-25T03:18:29Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 12.042
},
{
"name": "resolution",
"value": "1280x720"
},
{
"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, 12 s, 16:9, 720p 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 0.50 s to 11.54 s of a 12.04 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": "720p",
"requested_duration_s": 12
},
"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_01M64XWHRK24GAWE4VXY392N0R"
]
}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] An aerial descent that ends on a two-shot is a compact way to introduce a place and two people.
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. |