Seedance 2.5 live-action test: 8 s low view over a woman's shoulder, a man in an orange tank top walks up and stops
A low camera over a woman's blurred shoulder at the right, looking down a paved path where a man in an orange tank top and grey shorts walks toward the camera, stops with his arms held out from his body, then lowers them and looks to the side while the woman's shoulder crosses in front of him.
Task: Stage a low view over a woman's shoulder in which a man in an orange tank top walks up, stops and looks off to the side as one continuous live-action take of 8 s.
Outcome: succeeded
0.34 s: Low, over a woman's blurred shoulder at the right: a man in an orange tank top and grey shorts on a paved path, a lawn and a brick-and-glass building behind.
1.01 s: He walks toward the camera.
1.68 s: He walks closer, arms loose.
2.35 s: He stops, arms slightly out.
3.02 s: He stands with his arms out from his sides, looking to the right.
3.69 s: Same; arms spread wide.
4.36 s: Same.
5.03 s: Same; his arms are lowering.
5.70 s: The woman's shoulder crosses the frame; he is small behind her.
6.37 s: He stands with his arms lowered, facing the camera, small and far.
7.04 s: He turns his head to the left.
7.71 s: He stands with his arms lowered, looking left.
Intent vs result: The sampled frames show the walk-up, a stop and a look to the side; no disc appears, as the prompt asks. The prompt asks that he stop with his arms at his sides, but the sampled frames at about 3 to 5 s show his arms held out from his body before they lower. 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": "11 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": "2026-09-25T07:04:34Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 8.042
},
{
"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, 8 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 0.34 s to 7.71 s of a 8.04 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": 8
},
"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.",
"Request vs picture (H01's judgement at this size): the prompt asks that he stop with his arms at his sides; the sampled frames at about 3 to 5 s show his arms held out from his body before they lower."
],
"artifact_ids": [
"ast_01M64XWTR1Y907WCYA7MR8KAKW"
]
}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 low angle over a shoulder keeps a lone arrival tied to a second person who is mostly out of 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. |