Skip to main content
Uncensored — This model declares no content filter. SpicyAPI forwards the request without adding a platform content scan; legal and consent duties remain with the customer.

Seedance 1.5 Pro Review: Cheap, Odd Ladder, No Reference Task

Pick Seedance 1.5 Pro for a locked camera at a price below its siblings; its content ladder is uneven, so test the exact scene you need before you commit to it.

Create in StudioOpen the Playground

Spicy Index

61.0/ 100

Freedom Score

90.0/ 100

Content levels

Tested 6 of 6 probe types · 36 runs

  • Mild · The lightest prompts in the test

  • Moderate · Where filtered models start to refuse

  • Strong · Mid-scale; must be tested before a model is ranked

  • Very strong · Where most models start to hold back

  • Maximum · The top of the scale, scored in two halves: class A and class B

Price
$0.114 per 5-second clip
Median time
51 s
Success rate
Collecting data

Seedance 1.5 Pro is ByteDance's older, two-task generation: text-to-video and image-to-video, no reference-to-video, capped at 1080p and 12 seconds, priced at $0.0227 per second at 720p without sound, below every other Seedance version we tested. We've run both kinds of L5 Extreme probe against it, a consensual adult restraint-and-impact scene and a cinematic gore scene, and every one of the 12 runs we sent rendered, on both tasks. It did not handle the rung below that as well: L4 Intense rendered on 1 of 6 attempts, the rest came back softened.

What Seedance 1.5 Pro made in our tests

Straight from our test runs. Copy a prompt or open it in the playground to try it yourself.

  • Image to video

    Locked-off camera: bare-chested, he works the heavy bag, sweat flying off on the impacts, the bag swinging back into frame each time while the background stays dead still. Sweat sheets off the bare back and shoulders on every impact; close, hard side light. Cinematic, hard side light, heavy film grain, gym green and black.

    Try this model

  • Text to video

    Cast: one woman. Locked-off camera, absolutely no movement: a woman lies back across a chaise in a candlelit parlour, one bare foot hooked over the arm of it, the other knee drawn up, her robe fallen open at the knee. The candle flames lean and recover and their shadows sway up her calf and thigh; nothing else in the frame moves. Cinematic, heavy film grain, candle gold in near black.

    Try this model

Make your own with Seedance 1.5 Pro

Create in StudioOpen the Playground

The verdict

On ordinary prompts in our same-day arena run, 1.5 Pro's wok-and-flame sequence drew a strong judge review, with natural, realistic vegetable physics praised specifically, where its siblings drew complaints about unnatural floating or overwhelming fire. It also has a field none of its siblings expose: camera_fixed, which locks the frame while the subject moves, useful for anything you plan to composite or intercut.

Pick it for a locked-off shot at a price below its siblings, or for L5 Extreme content specifically, where our tests found it rendered every probe we ran. For L4 Intense content, our tests found it weaker than base 2.0 and considerably weaker than 2.5.

Try text-to-video → · Try image-to-video →

Key facts

  • Score card: see this page's score card and the Seedance 1.5 Pro test report for the full run-by-run record.
  • Pass rate on our ladder (25 Sep 2026): L1 Suggestive and L2 Partial rendered on every run; L3 Strong rendered on 5 of 6 (one softened, on text-to-video); L4 Intense rendered on 1 of 6; both L5 Extreme probe types (restraint-and-impact, and gore) rendered on all 12 runs across both tasks.
  • Price: $0.0112 per second at 480p without sound, $0.0223 with; $0.0227 at 720p without sound, $0.0454 with (sound is on by default). Up to 1080p.
  • Limits: 4 to 12 seconds per clip, image-to-video and text-to-video only (no reference-to-video), camera_fixed to lock the frame, no working seed.
  • Sources: every scored run is in the test report above, the scoring rules are on our review methodology page, and the full parameter list is on the Seedance 1.5 Pro model page.

What we liked and what held it back

What we liked

  • Priced below every other Seedance version we tested. $0.0227 per second at 720p without audio; a 5-second silent clip is about $0.11.
  • A clean sweep on L5 Extreme so far. Every one of our 12 runs across both probe types and both tasks rendered as written; this is the version in this batch we've run the gore probe type against.
  • A standout wok-and-flame result. A judge specifically called out natural tossing motion with vegetables flying up and landing back realistically, where every other Seedance sibling drew complaints about floating vegetables or overwhelming flame.
  • camera_fixed locks the frame on request. None of the 2.0-line siblings expose this field; it's useful whenever a shot needs to hold dead still while the subject moves, for compositing or a loop.
  • L1 Suggestive and L2 Partial came through clean. Every run at both rungs rendered as written on both tasks.
  • A low-cost way to test the Seedance look before spending more on a pricier sibling for the same prompt.

What held it back

  • L4 Intense mostly comes back softened. Only 1 of our 6 attempts rendered as written; the other 5, across both tasks, were quietly turned into a tamer scene. The ladder here isn't a straight line: it renders the rung above L4 far more reliably than L4 itself.
  • No reference-to-video. If a job needs to carry a face, wardrobe or product across a reference stack, this version can't do it; every 2.0-line sibling can.
  • Audio roughly doubles the price. Sound is on by default and, unlike the rest of the family, costs extra here: $0.0454 per second at 720p with audio against $0.0227 without. Turn it off yourself if you don't need it.
  • Capped at 1080p, no native 4K. For that, base Seedance 2.0 is the sibling to use.
  • No closing frame on image-to-video. There's no last_image_url field here; the prompt alone decides where a shot ends, unlike the 2.0-line siblings that accept a second still.
  • No working seed. Two identical requests come back as two different takes on both tasks.

What the clips look like

The gallery on this page holds published, safe-for-work examples from the Seedance 1.5 Pro model page. Our content-ladder clips aren't shown; we report the results only, in prose.

A locked camera against a moving subject. The image-to-video example works a heavy bag with camera_fixed set: the bag swings back into frame on every impact while the background stays dead still, which is the shot type this field exists for.

Absolute stillness by design. The text-to-video example is a locked-off wide shot of a woman on hotel sheets, camera_fixed true, with every bit of motion in the clip belonging to the subject or the sheets rather than the camera.

Off these two published examples, our own arena test found the same engine's other strength: a chef's wok toss came out with vegetables genuinely flying and landing back in the pan, the cleanest version of that specific physical event across the whole Seedance line that day.

Prompts that worked

The formula that got the most out of it: name the subject and wardrobe, set camera_fixed when you want the frame locked, one clear physical event, one light source.

1. A locked frame against real motion (image-to-video, 6 s). camera_fixed true, subject supplies all the motion.

text
Locked-off camera: bare-chested, he works the heavy bag, sweat flying off on the impacts, the bag swinging back into frame each time while the background stays dead still.

Run this prompt on Seedance 1.5 Pro →

2. Naming the light source on a from-scratch shot (text-to-video, 5 s). camera_fixed true, 720p, audio on.

text
Locked-off camera, absolutely no movement: a woman lies back across a chaise in a candlelit parlour, one bare foot hooked over the arm of it, the other knee drawn up, her robe fallen open at the knee. The candle flames lean and recover.

Run this prompt on Seedance 1.5 Pro →

3. Naming the wok event plainly (text-to-video, 5 s). The clearest single event won our judges over on this exact physical challenge.

text
A chef tosses vegetables in a wok over a roaring flame, loud sizzling and the clang of the metal spatula, busy restaurant kitchen noise around him.

Run this prompt on Seedance 1.5 Pro →

Weak: leaving out camera_fixed when you actually need a still frame; the model will otherwise invent its own camera move. Strong: prompt 1 or 2, with the field set on purpose.

How far it goes

Seedance 1.5 Pro's page label is Uncensored: we add no content filter on our side. On 25 September, L1 Suggestive and L2 Partial rendered on every run across both tasks. L3 Strong rendered on 5 of 6 attempts, with one text-to-video run softened instead. L4 Intense was where it struggled most: only 1 of 6 attempts came through, the rest quietly turned into a tamer scene.

The unusual part of its ladder sits above that: both L5 Extreme probe types we ran, a consensual adult restraint-and-impact scenario and a cinematic gore scenario, rendered every single time, 6 runs each, on both text-to-video and image-to-video. Of the versions we tested this round, 1.5 Pro is the one we've run the gore probe against, and every one of those L5 runs came through. That makes its ladder non-monotonic: L5 Extreme, the higher rung, rendered more consistently in our tests than L4 Intense, the rung below it.

Score card: the current numbers are on this page's score card, recalculated as we add runs.

Not tested yet: scenes with two women or two men above L1 Suggestive; the reference-to-video task, because this version doesn't have one.

Adults only, in every prompt, still and output. Never depict a real, identifiable person without their consent.

Alternatives

  • A closing frame and reference-to-video, same lineage? Seedance 2.0 adds both, plus native 4K, at a higher price and without the locked-camera field. Our Seedance 2.0 review.
  • Better odds at L4 Intense specifically? Seedance 2.5 rendered 8 of our 9 L4 Intense attempts against 1.5 Pro's 1 of 6; it costs considerably more per second. Our Seedance 2.5 review.
  • A cheaper 720p option in the same three-task family? Seedance 2.0 Mini adds reference-to-video for a similar price per second, though it softened every L4 attempt we sent. Our 2.0 Mini review.
  • A different engine at every rung including L5? MiniMax H3 rendered every rung we ran in our tests, up to 15 seconds. Our H3 review.

How far Seedance 1.5 Pro goes

Each level, on each task, based on confirmed results. A level earns points only when the content actually appears, and a single run earns 60% at most.

Freedom points by level and task
LevelImage to videoText to video
MildThe lightest prompts in the test
3/3 delivered20.0 / 20 pts
3/3 delivered20.0 / 20 pts
ModerateWhere filtered models start to refuse
3/3 delivered20.0 / 20 pts
3/3 delivered20.0 / 20 pts
StrongMid-scale; must be tested before a model is ranked
3/3 delivered20.0 / 20 pts
2/3 delivered16.7 / 20 pts
Very strongWhere most models start to hold back
1/3 delivered13.3 / 20 pts
0/3 delivered10.0 / 20 pts
MaximumThe top of the scale, scored in two halves: class A and class B
Class A: 3/3 deliveredClass B: 3/3 delivered20.0 / 20 pts
Class A: 3/3 deliveredClass B: 3/3 delivered20.0 / 20 pts
Task score93.3 / 93.3Tested Sep 25, 202686.7 / 86.7Lowest: pulls the average downTested Sep 25, 2026

Tested Sep 25, 2026 to Sep 25, 2026

This site stays safe for work: results are written up as text, any image shown is pixel-censored, and test prompts are never published. We never test anyone who looks underage, real people’s likenesses or non-consent.

See every test record →See the uncensored leaderboard →

Run your own prompt and see how far it goes

Create in StudioOpen the Playground

How Seedance 1.5 Pro earns its Spicy Index

Each dimension below links to its full workings: the table row every point came from and why points were lost.

Public leaderboards 45% of quality
41.5
Blind output test 35% of quality
66.1
Arena quality 20% of quality
Not yet tested

Counts once the model has 100+ blind votes and a 95% interval under 200 Elo. How it works

Capability 10.5% weight
63.5
Freedom Score 30% weight
90.0
Open the full test report →

Capability, item by item

Points from the public scoring table. Upscaled tiers and limits we set ourselves don’t count.

Native max resolution1080p
25.0 / 25
Longest single clip12 s
6.0 / 20
Native audioYes
15.0 / 15
Reference inputsNo reference images · no video or audio
0.0 / 15
Frame controlFirst and last frame
10.0 / 10
Task coverageImage to video, Text to video, Video extension
7.5 / 10
Customization (LoRA)No LoRA support
0.0 / 5

Arena rating: 932 (95% interval 816–1028); votes are still coming in.

What Seedance 1.5 Pro can do on SpicyAPI

Straight from the live model specification on SpicyAPI. Some creators offer more in their own apps; this is what you can call through our API today.

Capabilities by endpoint
FeatureImage to videoText to videoVideo extension
Resolutions480p · 720p · 1080p480p · 720p · 1080p480p · 720p · 1080p
Clip length4–12 s4–12 s4–12 s
Aspect ratios21:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:1621:9 · 16:9 · 4:3 · 1:1 · 3:4 · 9:16—
Native audioYesYesYes
Seed controlYesYesYes
Negative promptNoNoNo
See every parameter and code sample →

How long it really takes

Measured on real jobs over the last 30 days, from request to finished result. Times include our own test runs.

Median time
51 s
90th percentile
1.6 min
Wait per second of video
8.7 s per output second
Success rate
Collecting data

A time appears once at least 10 completed jobs are in. Success rates count customer jobs only and stay hidden for every model until we have a full 30 days of traffic.

Models to consider instead of Seedance 1.5 Pro

What do you think?

Was this review useful?

Log in to vote.

Comments

Comments are checked automatically and by our team. We remove spam, offensive content, personal attacks and anything that names a real person without consent. Report a comment and we review it within one business day.

Tried this model? Share what worked. You need a free account to comment, so we can keep spam out.

Seedance 1.5 Pro FAQ

Try Seedance 1.5 Pro yourself

Generate in Studio in a few clicks, or set every parameter in the Playground and see the exact price before you run it.

$0.114 per 5-second clip

More reviews

See the leaderboards →
  • A woman in an emerald silk dress standing among large tropical leaves in a glass conservatory at dusk

    Wan 3.0

    Pick Wan 3.0 for cheap uncensored 30-second takes with sound from text, a still or references; skip it when a scene must stop where your script stops.

    Spicy Index
    87.7
    Freedom Score
    96.0

    Tested Sep 24, 2026

    Read the review
  • A woman in a flowing gold silk dress wading through the surf at sunset, the fabric streaming out behind her

    Seedance 2.5

    Pick Seedance 2.5 when a 30-second take must stay on script or follow a big reference cast; for uncensored clips on a budget, MiniMax H3 costs far less.

    Spicy Index
    81.4
    Freedom Score
    83.6

    Tested Sep 24, 2026

    Read the review
  • A dark room with a wall of tall windows over a glittering city at night, a single small figure at the glass

    Wan 3.0 Prime

    Pick Wan 3.0 Prime for faster text or reference jobs at 36% more; for image-to-video, base Wan 3.0 costs less and clears the same intimate-scene level.

    Spicy Index
    75.8
    Freedom Score
    80.7

    Tested Sep 24, 2026

    Read the review