Seedance 2.5 text-only test: 20 s fallen soldier in a bracken field with an extreme eye close-up
Autumn bracken: a figure lying on the ground, a wide view of oaks, an eye in extreme macro with detail in the iris, the eyelid closing and a pull-out to the lying figure.
Task: An extreme macro of a weathered man's eye cut against a real landscape, in afternoon light through trees.
Outcome: succeeded
0.84 s: A figure in field kit lies in orange bracken.
2.51 s: Wide: oaks beyond a field, the lying figure small.
4.18 s: Extreme close-up of a blue-grey eye with weathered skin.
7.52 s: The eye looks up.
9.20 s: Iris detail and a visible pupil.
12.54 s: The eyelid closing.
14.21 s: The eye closed.
15.88 s: The lying figure in bracken.
17.56 s: A more distant view.
19.23 s: The figure small in a wide field.
Intent vs result: The sampled frames hold a consistent macro eye with iris detail and a clean pull-out to a wide; the macro-to-wide cut links an eye to the lying figure.
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": "2026-08-11T02:29:41Z",
"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": 1
},
{
"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 asks for a large-format anamorphic-cinema look, 20 s, 16:9, audio requested, no seed set. One of a run of tests on 10-11 August 2026 (UTC) that vary subject and mood. 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_01M64WP8X2SY4ZM9T02Z3ASQ32"
]
}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] An extreme macro cut against a wide gives scale contrast, and the eye's detail holds at the sampled size.
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. |