Seedance 2.5 grey-peg test: wide disc pick-up, jump and railing hop with a drifting camera (17 s)
Wide, almost static vantage on a brick building's steps: the girl picks up a yellow disc, throws it up, jumps, walks along a white railing and hops over it; identity is steady.
Task: Wide continuous take of a disc pick-up, a throw and jump, a walk along the railing and a hop over it.
Outcome: partial
0.61 s: Girl stands at the top of concrete steps; a yellow disc lies on the ground at right.
1.83 s: She crouches to pick the disc up.
3.04 s: Standing with the disc raised; white railing diagonals at the right.
6.69 s: Mid-air with a leg bent.
7.91 s: Disc visible high in the frame upper right as she lands.
9.13 s: Arm raised; camera has drifted so the railing is now at the left.
12.78 s: Walking toward the railing; ponytail visible.
15.22 s: Hand on the railing.
16.43 s: Hopping over the railing.
Intent vs result: The camera drifts around the girl so the railing geometry changes from right-side diagonal to left-side straight run between 6.69 and 9.13 s. Peg video not separately viewed.
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": "5 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": "2026-09-25T05:35:27Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 17.042
},
{
"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 text-and-reference video generation with a grey-peg motion video (a rendered blocking pre-visualisation that fixes camera path and positions), several approved scene stills and per-character face/front/back reference photos, plus a long structured prompt (look statement, reference-use rules, cast, camera, ordered choreography, continuity, sound). Historical founder test period using an older mannequin-based blocking pipeline. Sampled inspection: 14 timestamped frames from 0.61 s to 16.43 s of a 17.04 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": 17
},
"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.",
"Railing geometry changes between 6.69 and 9.13 s."
],
"artifact_ids": [
"ast_01M64VM18D5Y83JQRYG3XMZXV2"
]
}Evidence claims
- [sourced_fact] Timestamped observations above come from viewing 14 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] Wide framing keeps identity and costume steady for 17 s, but the staging geometry shifts unless the peg video pins it.
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. |