Seedance 2.5 live-action test: 11 s follow from behind onto a school landing, the man turns, goes back in and the woman walks away
A camera inside a school doorway that follows a man in a red tee out through the glass doors onto a sunlit landing with a woman in a dark top; he extends an arm toward her, turns to the camera and leaves the frame, and she walks away along a brick wall with a lawn beyond.
Task: Stage a follow from behind through a school doorway onto a landing where a man turns to a woman and goes back in while she walks away along a brick wall as one continuous live-action take of 11 s.
Outcome: succeeded
0.46 s: From inside a doorway: a man in a red tee, seen from behind, walks toward a bright glass door with a lawn beyond.
1.38 s: He walks out; a woman in a dark top stands at the right beyond the door.
2.30 s: His back fills the left of the frame; she stands beyond the doorway at the right.
3.22 s: They stand on the landing, he at the left, she at the right with a ponytail.
4.14 s: He holds an arm out toward her.
5.06 s: He extends his arm to the right.
5.98 s: He stands with his hands at his sides; she faces him.
6.90 s: Same; she stands at the right looking at him.
7.82 s: He turns toward the camera at the left; she stands at the right.
8.74 s: He is gone; she walks away along the brick wall.
9.66 s: She walks toward the right, small, with the lawn behind.
10.58 s: She is small at the right edge.
Intent vs result: The sampled frames follow the plan: a follow from behind onto the landing, an arm gesture, the man's exit from frame and the woman's walk-away along a brick wall. 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 video input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-09-25T07:06:07Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 11.042
},
{
"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, 11 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 0.46 s to 10.58 s of a 11.04 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": 11
},
"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_01M64XWWREWKGW7Q4FHQTM518M"
]
}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] Leaving one person's exit off screen lets the second person own the end of the take.
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. |