Seedance 2.5 grey-peg test: table-tennis rally, third take with a sitting player and a bystander exit (15 s)
Table-tennis scene where the player in the blue cap drops out of view at about 8 s, the girl walks away across the lawn and the camera rises to the table.
Task: Over-the-shoulder view of a rally with a bystander and a rising camera reveal.
Outcome: succeeded
0.75 s: Foreground boy in white tee; girl and blue-cap player behind a blue table.
5.27 s: Player lifts a red paddle.
6.77 s: Player steps left.
8.28 s: Player crouches or sits lower in frame.
9.78 s: The girl walks away across the lawn.
11.29 s: Girl is a small figure; boy's glasses visible.
14.30 s: High view of the table with the boy in profile.
Intent vs result: Third take of the table-tennis scene: the bystander persists (like 10c9b5b4) but the player drops out. The grey-peg input for this take was 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": "9 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)."
},
{
"description": "1 linked video input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-09-23T18:00:23Z",
"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 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: 10 timestamped frames from 0.75 s to 14.30 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_01M64VPQEMYYYPXFDAF073R7N3"
]
}Evidence claims
- [sourced_fact] Timestamped observations above come from viewing 10 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] Across three takes, background-character persistence differs; the rising reveal repeats each time.
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. |