Seedance Lab is our benchmark programme: eight repeatable tests, each with a fixed prompt, fixed settings, a stated reference policy and a scoring rubric, run against every Seedance version we offer. Results are published per run with the generation date, exact settings and the output file. Nothing on this page is a placeholder result; where a test has no published run yet, it says so.
Why a lab instead of a claims table
Most model comparisons on the web repeat vendor claims or cherry-pick one striking clip. Neither tells you what the model does with your prompt on an ordinary day. The Lab exists to produce first-hand, dated evidence that anyone can reproduce: same inputs, same settings, all runs published, including the bad ones.
Methodology
01
Fixed inputs
Each test has a canonical prompt and a reference policy. Runs never reword the prompt per model. Reference assets are Seedancee-owned originals (a Lab character, a Lab product) hosted on our media domain. Runs are generated from Seedancee staff accounts; generations made by site users are never published as Lab runs.
02
Fixed settings
Duration, resolution, aspect ratio and audio are held constant for every run of a test so outputs are comparable across models and dates.
03
Multiple runs
Where the protocol says three runs, all three are published. We report medians and ranges rather than best-of.
04
Human scoring
Every output is watched by a person and scored against the rubric. Where two reviewers disagree, both scores are shown.
05
Dated and versioned
Each run records the model id, provider, submit time and time-to-output. When a model version changes, old runs stay published and new runs are added, so you can see drift.
06
Known limitations
Each run lists what went wrong, because the failure modes are more useful to a prompt writer than the successes.
The eight tests
Test 01
Same prompt across versions
One unchanged text prompt run on every Seedance version to see what actually improved between releases.
Aucun essai publié pour l'instant
Ce qui est mesuré
Visual fidelity and lighting realism at the same resolution.
Whether the model follows the shot description or substitutes a generic one.
Protocole
Use the canonical prompt verbatim; no per-model rewording.
Text-to-video only, no references.
Run each model three times; publish all three, not the best one.
Record submit time and time-to-output for every job.
Prompt de référence
A lighthouse keeper in a wool coat climbs a spiral iron staircase at dusk, lantern in hand. Slow handheld follow shot from behind, warm lantern light against cold blue window light, gentle film grain. The keeper reaches the top and pushes open a heavy door as wind hits the frame.
Médias de référence: None. This test isolates text understanding.
Adherence (0–3): staircase, lantern, dusk, door, wind all present.
Camera (0–2): handheld follow from behind, no unmotivated cuts.
Stability (0–3): no face morphing, no object popping, consistent geometry.
Look (0–2): warm/cold contrast and grain as described.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 02
Same image across models
A single first-frame image animated by each model to compare how faithfully the source is preserved while motion is added.
Aucun essai publié pour l'instant
Ce qui est mesuré
Identity and composition preservation of the source frame.
Plausibility of inferred motion and depth.
Colour and exposure drift over the clip.
Protocole
One Seedancee-owned photograph (a still life on a wooden table, 1536×864) used as the first frame for every run.
Prompt describes only the motion, never the scene content.
Image-to-video mode; no other references.
Compare the first output frame against the source with a side-by-side crop.
Prompt de référence
Slow push-in. A breeze lifts the edge of the linen cloth and the candle flame leans, then steadies. Nothing else in the scene changes.
Médias de référence: Exactly one first-frame image, identical for every run, hosted on our media domain.
Source fidelity (0–4): first frame matches the input in layout, colour and detail.
Motion restraint (0–3): only the described elements move.
Drift (0–3): last frame still matches the source in tone and geometry.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 03
Camera-motion vocabulary
Six named camera moves, one per clip, to learn which terms each model reliably understands.
Aucun essai publié pour l'instant
Ce qui est mesuré
Recognition of dolly-in, dolly-out, pan, tilt, orbit and crane terms.
Whether the move is smooth and completes within the clip.
Whether the subject stays framed during the move.
Protocole
Same static scene description for all six clips; only the camera sentence changes.
Each move is requested with one plain-English sentence, no numeric parameters.
Scored by two reviewers independently; disagreements are noted, not averaged away.
Prompt de référence
A ceramic teapot on a slate counter in a sunlit kitchen, steam rising. [CAMERA SENTENCE]. No people, no cuts.
Per move: correct (2), partially correct (1), wrong or static (0).
Bonus (0–1): the move is smooth without speed ramps the prompt did not ask for.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 04
Character consistency
The same original character, defined by reference images, across three different scenes to measure identity drift.
Aucun essai publié pour l'instant
Ce qui est mesuré
Face and costume consistency across separate generations.
Consistency within a single clip as the character turns and moves.
How many reference images are needed before identity stabilises.
Protocole
Character is an original design created for the Lab (no likeness of a real person, no existing IP).
Three reference images: front, three-quarter, full body. Same set for every run.
Three scene prompts: a market street, a rainy bus stop, a rooftop at night.
Reference-to-video mode on models that support reference images.
Prompt de référence
The character from the reference images walks through [SCENE], looks over their shoulder toward the camera, then continues walking. Medium shot, natural light, no cuts.
Médias de référence: Three reference images of the Lab character, identical for every run.
Paramètres fixes
Durée
6s
Résolution
720p
Format d'image
9:16
Audio
Désactivé
Modèles
Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini
Grille de notation
Identity across scenes (0–4): a reviewer can recognise the same character in all three clips.
Identity within clip (0–3): no face morphing during the head turn.
Costume (0–3): outfit details preserved.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 05
Product and logo consistency
A product with a simple wordmark, rotated and lit, to see whether text and shape survive motion.
Aucun essai publié pour l'instant
Ce qui est mesuré
Legibility of a short wordmark throughout the clip.
Shape and proportion preservation during rotation.
Material and reflection plausibility.
Protocole
Product is a Lab-made bottle with the fictional wordmark 'NORTHFALL'. No real brand is used.
Two reference images: front view and 45° view.
Same rotation prompt for every model.
Frames sampled every 0.5 s and checked for text corruption.
Prompt de référence
The product from the reference images rotates slowly on a matte white turntable, 180 degrees, under soft studio light with a single specular highlight. The label stays sharp and readable. Plain background, no cuts.
Médias de référence: Two reference images of the Lab product, identical for every run.
Paramètres fixes
Durée
5s
Résolution
1080p
Format d'image
1:1
Audio
Désactivé
Modèles
Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini
Grille de notation
Wordmark legibility (0–4): count of sampled frames in which every letter is correct.
Shape (0–3): silhouette matches the reference through the rotation.
Lighting (0–3): highlight behaves like a real specular.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 06
Native audio and lip sync
A short spoken line and an ambient cue to evaluate generated audio quality and mouth synchronisation.
Aucun essai publié pour l'instant
Ce qui est mesuré
Whether the requested line is spoken at all, and in the requested tone.
Lip-sync accuracy on a front-facing speaker.
Presence and plausibility of ambient sound described in the prompt.
Protocole
Speaker is the Lab character (original design).
Audio generation enabled; no reference audio in the baseline run.
A second run supplies a Lab-recorded reference voice clip on models that accept reference audio.
Reviewers watch muted first, then with audio, and log timing offsets.
Prompt de référence
Close-up of the character from the reference images, facing camera in a quiet workshop. They say, clearly and calmly: "We tested it three times. The third one worked." Faint rain on the roof, a clock ticking. No music.
Médias de référence: Three character reference images; optional one reference audio clip (Lab-recorded).
Paramètres fixes
Durée
6s
Résolution
720p
Format d'image
16:9
Audio
Activé
Modèles
Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini
Grille de notation
Line delivered (0–3): exact words, correct tone.
Lip sync (0–4): offset under roughly 100 ms, no dropped syllables.
Ambience (0–3): rain and clock present, no music.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 07
Complex motion
A multi-part physical action to expose where motion coherence breaks down.
Aucun essai publié pour l'instant
Ce qui est mesuré
Limb and object coherence during fast, multi-stage motion.
Cause-and-effect ordering (throw, then catch, not both at once).
Cloth, hair and liquid behaviour under motion.
Protocole
Text-to-video, no references, so every model faces the same problem.
Same prompt, three runs per model.
Reviewers list each failure with a timestamp rather than a single overall impression.
Prompt de référence
A skateboarder in a loose grey hoodie pushes off, ollies over a low curb, lands, and coasts to a stop while pulling their hood down. Side tracking shot at chest height, overcast daylight, wet asphalt.
Sequence (0–3): push, ollie, land, coast, hood in order.
Body coherence (0–4): no extra limbs, no board passing through feet.
Secondary motion (0–3): hoodie and reflections behave plausibly.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
Test 08
Prompt adherence
A dense prompt with ten checkable details to measure how much of a specific brief each model honours.
Aucun essai publié pour l'instant
Ce qui est mesuré
Count of explicitly requested details present in the output.
Whether negative instructions ('no text', 'no people') are respected.
Whether colour and count constraints are followed.
Protocole
The prompt lists exactly ten verifiable details; reviewers tick each one.
No references; text-to-video only.
Three runs per model; report the median and the range.
Prompt de référence
A red bicycle with a wicker basket leans against a yellow door. Three potted ferns on the step. A grey cat sits on the windowsill and yawns once. Morning light from the left, long shadows. The door has a brass number 17. No people, no text overlays, no music. Static camera, slight film grain.
One point per detail (0–10): red bicycle, wicker basket, yellow door, three ferns, grey cat, yawn, left-side light, brass 17, no people, static camera.
Penalty (−1 each): text overlays, added people, music.
Essais publiés
Aucun essai publié pour l'instant
Un essai n'apparaît ici qu'une fois le clip généré, la sortie stockée sur notre propre hébergement média, la vidéo visionnée et les notes rédigées. Chaque essai affichera les champs ci-dessous, avec la date de génération, afin de pouvoir comparer les résultats dans le temps.
Prompt
Médias de référence
Modèle
Paramètres exacts
Date de génération
Temps de génération
Résultat
Notes
Limites connues
How results feed the rest of the site
Comparison pages (Seedance 2.5 vs 2.0, Seedance vs other models) link to the relevant tests and quote results only from published runs. Model pages show capability facts from the registry; the Lab shows behaviour. When a run reveals a reliable prompting pattern, it is added to the prompt guide with a link back to the run.
Reproducing a test yourself
Copy the canonical prompt from the test card.
Open the workspace, select the model, and set duration, resolution, aspect ratio and audio to the fixed settings.
Add the reference assets if the test uses them (Lab assets are downloadable from published runs).
Generate three times and score with the rubric.
If your results differ materially from ours, tell us; we re-run and, if needed, correct the published run.
Run a test in the workspace
Use the canonical prompt and fixed settings from any test card.
Because we only publish runs we have actually performed, stored and reviewed. The methodology is published first so it cannot be adjusted after seeing results. A run appears under its test only once the output is on our media host, a person has watched it and written the notes and known limitations, and the generation followed the test's fixed prompt, references and settings. Tests without such a run say so.
Which models does the Lab cover?+
Every Seedance model offered on Seedancee: 2.5, 2.0, 2.0 Fast, 2.0 Mini and 1.5 Pro. Reference-based tests skip 1.5 Pro because it does not accept reference inputs.
Will the Lab compare Seedance to other companies' models?+
Where we can run the same prompt and settings on another hosted model, yes, and those runs will be published on the relevant comparison page with dates. We do not quote competitor benchmarks we did not run.
Are the reference assets real people or brands?+
No. The Lab character and the Lab product are original designs created for these tests. No real person's likeness and no existing brand is used.
Can I submit a test?+
Suggest one through the contact page. Good candidates are repeatable, use original assets, and measure something the current eight tests miss.
How often are tests re-run?+
When a model version changes, when the provider reports a capability change, or on a monthly cadence for the flagship model. Each run carries its date.