Seedance 2.5 live-action test: 10 s wide shot, a woman walks down a ramp, picks up a yellow disc and ends in a close-up
A wide shot from a lawn in which a woman in a dark top walks down a white-railed ramp toward a yellow disc on the concrete, stops, crouches and picks it up, then the camera pushes in to a close-up of her face above the disc.
Task: Stage a woman who walks down a ramp, stops at a yellow disc on the concrete, crouches, picks it up and ends in a close-up above the disc as one continuous live-action take of 10 s.
Outcome: succeeded
0.42 s: Wide from a lawn: a woman in a dark top at the top of a ramp with white railings, a man in an orange tee at the left, a brick-and-glass building behind.
1.26 s: She walks down the ramp; a yellow disc lies on the concrete ahead of her.
2.09 s: She walks; the disc is ahead of her feet.
2.93 s: She stops above the disc and looks down.
3.77 s: Same; she stands over the disc.
4.60 s: She crouches with bent knees, her hands toward the disc.
5.44 s: She bends and picks up the disc.
6.28 s: She stands holding the disc at waist level.
7.11 s: She holds the disc at her chest, the camera closer.
7.95 s: She tilts the disc in her hands, looking at it.
8.79 s: Close: her face above the disc, which fills the bottom of the frame.
9.62 s: Closer: her face and a large yellow disc at the bottom.
Intent vs result: The sampled frames follow the plan: a descent, a crouch and pickup, and a push-in to a face above the disc. One yellow disc is seen at a time. The linked inputs are recorded by count only; their disclosure and rights basis are unconfirmed, and the prompt asks that they set the faces and wardrobe of the people shown, so likeness is a hold. Spoken lines were requested and not heard.
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": "2026-09-25T05:36:25Z",
"metrics": [
{
"name": "output_duration",
"unit": "s",
"value": 10.042
},
{
"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, linked reference inputs recorded in the job metadata (images that set the place, light, wardrobe and the people and one blocking video), a long structured prompt in a shot-by-shot format for one continuous live-action take with spoken lines requested, 10 s, 16:9, 480p label, audio requested, no seed set. One of a set of live-action school-scene runs on 25 September 2026 (UTC). Sampled inspection: 12 timestamped frames from 0.42 s to 9.62 s of a 10.04 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": 10
},
"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_01M64XWP0X4C9DK47GZERNQ5J6"
]
}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 push-in that ends on a face behind a foreground object turns a practical beat into a portrait.
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. |