Seedance 2.5 text-only look test: 20 s gold-lit gothic plaza with drawn-looking figures in a rendered setting
A gold-lit gothic arcade at night: a polished shoe, a tall black-coated man behind a smaller red-haired armoured figure in front of a gold-curtain wall, a flat-shaded red-haired close-up and a two-shot.
Task: Render a red-haired armoured figure and a long-coated man facing each other in a gothic plaza as a split look of drawn figures in a rendered setting, at 20 s.
Outcome: succeeded
0.84 s: Wide: a gold-lit gothic arcade at night with lamps along the arcades.
2.51 s: Same.
4.18 s: Same.
5.85 s: A polished black shoe on marble.
7.52 s: A tall black-coated man stands behind a smaller red-haired armoured figure, a gold-curtain wall behind.
9.20 s: Same.
10.87 s: Close: red hair, a grey eye, a triangle of light on the cheek, flat shading.
12.54 s: Same.
14.21 s: Same.
15.88 s: The black-coated man with a red head and a gloved hand at the bottom edge.
17.56 s: Same.
19.23 s: The man, red hair at the right edge.
Intent vs result: The sampled frames follow wide facade, coat or boot insert, two figures, hair close-up, two-shot and the man alone. The first three or more sampled frames show nearly the same picture. The red-haired close-up reads as flat-shaded drawn art against a modelled set, which is the split the prompt describes.
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
{
"run_at": "2026-08-27T05:31:23Z",
"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": 4
},
{
"name": "black_intervals",
"value": "none"
}
],
"procedure": "Seedance 2.5, text-only prompt (no linked image inputs recorded in the job metadata), a long structured prompt that fixes a look target (a split look in which the figures are drawn as flat ink-outline art and the setting is rendered, kept as two unblended languages) and a scene with a shot-by-shot format, 20 s, 16:9, audio requested, no seed set. One of a set of look-target runs on 27 August 2026 (UTC). 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_01M64XAJ5ETTQBX39BXT0K0Q9X"
]
}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 flat close-up in a lit set is the clearest case of the split look 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. |