Seedance 2.5 style test: 20 s rooftop sparring in low-key sakuga with purple sparks
Rooftop at night with a lamp: a silhouette, a close grip, purple sparks at the grip, a throw in a spark cloud, a kneeling pin and both lying on the mat.
Task: Re-tell a short sparring story in a low-key sakuga shonen anime on a rooftop at dusk, at 20 s.
Outcome: succeeded
0.84 s: A dark rooftop with a lamp and a silhouette.
4.18 s: Close grip: a white-gi student and a larger blue-gi rival, stars above.
9.20 s: Purple sparks at the grip.
10.87 s: Sparks scatter around a throw.
12.54 s: The rival's back fills the frame in a spark cloud.
14.21 s: The student kneels on the downed rival.
15.88 s: The student over him, hands at his collar.
17.56 s: Both lie on the mat.
19.23 s: Same.
Intent vs result: The sampled frames keep the spark effect on the throw and the same cast across shots.
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": "1 linked image input(s) recorded in the generation metadata (details withheld)."
}
],
"run_at": "2026-08-10T16:26:08Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 20.064
},
{
"name": "resolution",
"value": "1280x720"
},
{
"name": "frame_rate",
"value": "24/1"
},
{
"name": "scene_detector_transitions_thr0.30",
"value": 2
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5, one reference still that defines art style and character-design language only, a long structured prompt (one scene, a fixed cast and a shot-by-shot format), 20 s, 16:9, audio requested, no seed set. One of a matrix of runs on 10 August 2026 (UTC) that re-tell a sparring story in different art-style and character-design languages. Sampled inspection: 12 timestamped frames from 0.84 s to 19.23 s of a 20.06 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": 20
},
"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_01M64W8MR38RW877AP2W8SABQ9"
]
}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] Spark clouds are a compact way to signal impact in the sampled frames.
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. |