Skip to content
Seedancee

Change language

Independent AI video creation platform

Seedance AI Video Generator for Cinematic Video Creation

Seedance 2.5 is here. Create longer, reference-driven video with native audio.

Turn text, images, video, and audio references into polished AI video in one professional workspace.

Create a videoExplore examples

Configure a shot

Describe the shot and let the model build it from scratch.

FastLowest-cost drafts and social clips with strong visual consistency.

0 / 20000
Settings
5s

ProClips up to 10 seconds without Pro.

Native audio

Estimated cost 50 credits

5s at 720p. Confirmed before the job is submitted.

You will be asked to create an account (or sign in) and choose a plan. Your settings and files are kept, and once your subscription is active the video starts and the credits shown are spent.

Capabilities verified 2026-09-29

Matte-black headphones on wet slate

Now playing

Matte-black headphones on wet slate

Prompt: Studio product film. A pair of matte-black over-ear headphones rests on a slab of wet dark slate. The camera begins on a tight macro of the ear cushion stitching, then pulls back on a slow motorized slider to reveal the full silhouette. A single hard key light from the upper left throws a crisp rim highlight along the headband; soft fill from a large overhead diffuser. Fine mist drifts through the beam. In the final second, a bead of water slides off the cup and lands with a soft, clean drip sound. Sound design: low room tone, subtle hum of the light, the single drip. No text, no logo.

Remix this

Model: Seedance 2.5Duration: 8sAspect ratio: 16:9Resolution: 1080PAudio: AudioGenerated: Sep 29, 2026

Clip 1 of 6

  • Prompt: Abstract music visual, vivid color. Drops of magenta, cyan and gold ink fall into clear water inside a glass tank against a deep black backdrop, each color blooming and mixing into violet and teal clouds. Each drop lands on a slow 70 bpm pulse, tendrils unfolding in macro detail. The camera slowly rotates around the tank. Add a faint iridescent shimmer at the edges of the ink. High contrast, saturated, no text. Sound: a deep sub-bass pulse on each drop with soft reverb tails.

    Remix this

  • Prompt: Fashion film, 35mm anamorphic look, rich saturated color. A model in a floor-length emerald-green silk coat stands in a sunlit terracotta courtyard, late-afternoon golden light raking across ochre walls and a cobalt-blue door. A wind machine off-screen lifts the coat in slow waves. The camera orbits a quarter turn at hip height, shallow depth of field, soft warm lens flares. Palette: emerald, gold, terracotta, cobalt. Motion is unhurried; fabric moves in slow motion while the model holds a steady gaze into the lens. Sound: fabric rustle, distant wind, no music.

    Remix this
  • 5 Seedance models available
  • Up to 30s per generation
  • Native audio on 5 models
  • Up to 30 reference images, 10 clips and 10 audio tracks
  • Output up to 4K

Start with a shot

Six shots to open the generator with

Original prompts written for this site. Load one, change anything, generate.

  • Product commercial

    Matte-black headphones on wet slate

    Studio product film. A pair of matte-black over-ear headphones rests on a slab of wet dark slate. The camera begins on a tight macro of the ear cushion stitching, then pulls back on a slow motorized slider to reveal the full silhouette. A single hard key light from the upper left throws a crisp rim highlight along the headband; soft fill from a large overhead diffuser. Fine mist drifts through the beam. In the final second, a bead of water slides off the cup and lands with a soft, clean drip sound. Sound design: low room tone, subtle hum of the light, the single drip. No text, no logo.

    Aspect ratio
    16:9
    Duration
    8s
    Audio
    Audio

  • Fashion film

    Silk coat in a wind tunnel

    Fashion film, 35mm anamorphic look, rich saturated color. A model in a floor-length emerald-green silk coat stands in a sunlit terracotta courtyard, late-afternoon golden light raking across ochre walls and a cobalt-blue door. A wind machine off-screen lifts the coat in slow waves. The camera orbits a quarter turn at hip height, shallow depth of field, soft warm lens flares. Palette: emerald, gold, terracotta, cobalt. Motion is unhurried; fabric moves in slow motion while the model holds a steady gaze into the lens. Sound: fabric rustle, distant wind, no music.

    Aspect ratio
    9:16
    Duration
    8s
    Audio
    Audio

  • Short cinematic scene

    Night train, rain on the window

    Cinematic scene. Interior of an overnight train at 2 a.m. A woman in a wool coat rests her forehead against the window; rain streaks the glass and the passing sodium lamps paint moving orange bars across her face. The camera is locked off on the seat opposite, slight handheld drift. Rich color: amber lamp glow against cool teal-blue night outside the window, deep shadows, subtle film grain, warm practical light from a reading lamp above. Halfway through she exhales and closes her eyes. Sound: steady rail rhythm, rain against glass, the lamp buzzing faintly.

    Aspect ratio
    21:9
    Duration
    10s
    Audio
    Audio

  • Character scene

    Old lighthouse keeper, first line of dialogue

    Character close-up. An elderly lighthouse keeper with a white beard, weathered ruddy skin and a faded red wool sweater sits in a stone room, a kerosene lamp throwing warm amber light on the table while deep blue dusk fills the small window behind him. Medium close-up, 50mm, camera slowly pushing in. He looks just off lens, half-smiles, and says in a low gravelly voice: "They said the light would never fail. I never asked who they were." Lip movement matches the line. Lamp flicker, wind pressing on the shutters, a slow foghorn far away.

    Aspect ratio
    16:9
    Duration
    8s
    Audio
    Audio

  • Social ad

    Cold brew pour, vertical and fast

    Vertical social ad, bright and punchy. A tall glass of ice sits on a sunlit white marble counter beside a bowl of bright oranges and a sprig of fresh mint, a coral-pink wall behind. Cold brew coffee pours in from above in slow motion, dark ribbons swirling through the ice, then a splash of oat milk clouds the glass from the bottom up. Quick whip-pan to a top-down shot as the milk blooms. High-key daylight, crisp highlights, very shallow focus. Energetic pacing with two fast cuts. Sound: ice cracking, liquid pour, one satisfying clink.

    Aspect ratio
    9:16
    Duration
    6s
    Audio
    Audio

  • Music visual

    Ink clouds pulsing to a slow beat

    Abstract music visual, vivid color. Drops of magenta, cyan and gold ink fall into clear water inside a glass tank against a deep black backdrop, each color blooming and mixing into violet and teal clouds. Each drop lands on a slow 70 bpm pulse, tendrils unfolding in macro detail. The camera slowly rotates around the tank. Add a faint iridescent shimmer at the edges of the ink. High contrast, saturated, no text. Sound: a deep sub-bass pulse on each drop with soft reverb tails.

    Aspect ratio
    1:1
    Duration
    10s
    Audio
    Audio

Original examples

Cinematic showcase

Every clip below was generated on Seedancee. The prompt, model, duration, ratio and resolution are shown exactly as used. Remix loads all of them into the generator.

Matte-black headphones on wet slate

Matte-black headphones on wet slate

Prompt: Studio product film. A pair of matte-black over-ear headphones rests on a slab of wet dark slate. The camera begins on a tight macro of the ear cushion stitching, then pulls back on a slow motorized slider to reveal the full silhouette. A single hard key light from the upper left throws a crisp rim highlight along the headband; soft fill from a large overhead diffuser. Fine mist drifts through the beam. In the final second, a bead of water slides off the cup and lands with a soft, clean drip sound. Sound design: low room tone, subtle hum of the light, the single drip. No text, no logo.

Remix this
Model
Seedance 2.5
Duration
8s
Aspect ratio
16:9
Resolution
1080P
Audio
Audio
Generated
Silk coat in a wind tunnel

Silk coat in a wind tunnel

Prompt: Fashion film, 35mm anamorphic look, rich saturated color. A model in a floor-length emerald-green silk coat stands in a sunlit terracotta courtyard, late-afternoon golden light raking across ochre walls and a cobalt-blue door. A wind machine off-screen lifts the coat in slow waves. The camera orbits a quarter turn at hip height, shallow depth of field, soft warm lens flares. Palette: emerald, gold, terracotta, cobalt. Motion is unhurried; fabric moves in slow motion while the model holds a steady gaze into the lens. Sound: fabric rustle, distant wind, no music.

Remix this
Model
Seedance 2.5
Duration
8s
Aspect ratio
9:16
Resolution
1080P
Audio
Audio
Generated
Night train, rain on the window

Night train, rain on the window

Prompt: Cinematic scene. Interior of an overnight train at 2 a.m. A woman in a wool coat rests her forehead against the window; rain streaks the glass and the passing sodium lamps paint moving orange bars across her face. The camera is locked off on the seat opposite, slight handheld drift. Rich color: amber lamp glow against cool teal-blue night outside the window, deep shadows, subtle film grain, warm practical light from a reading lamp above. Halfway through she exhales and closes her eyes. Sound: steady rail rhythm, rain against glass, the lamp buzzing faintly.

Remix this
Model
Seedance 2.5
Duration
10s
Aspect ratio
21:9
Resolution
1080P
Audio
Audio
Generated
Old lighthouse keeper, first line of dialogue

Old lighthouse keeper, first line of dialogue

Prompt: Character close-up. An elderly lighthouse keeper with a white beard, weathered ruddy skin and a faded red wool sweater sits in a stone room, a kerosene lamp throwing warm amber light on the table while deep blue dusk fills the small window behind him. Medium close-up, 50mm, camera slowly pushing in. He looks just off lens, half-smiles, and says in a low gravelly voice: "They said the light would never fail. I never asked who they were." Lip movement matches the line. Lamp flicker, wind pressing on the shutters, a slow foghorn far away.

Remix this
Model
Seedance 2.5
Duration
8s
Aspect ratio
16:9
Resolution
1080P
Audio
Audio
Generated
Cold brew pour, vertical and fast

Cold brew pour, vertical and fast

Prompt: Vertical social ad, bright and punchy. A tall glass of ice sits on a sunlit white marble counter beside a bowl of bright oranges and a sprig of fresh mint, a coral-pink wall behind. Cold brew coffee pours in from above in slow motion, dark ribbons swirling through the ice, then a splash of oat milk clouds the glass from the bottom up. Quick whip-pan to a top-down shot as the milk blooms. High-key daylight, crisp highlights, very shallow focus. Energetic pacing with two fast cuts. Sound: ice cracking, liquid pour, one satisfying clink.

Remix this
Model
Seedance 2.5
Duration
6s
Aspect ratio
9:16
Resolution
1080P
Audio
Audio
Generated
Ink clouds pulsing to a slow beat

Ink clouds pulsing to a slow beat

Prompt: Abstract music visual, vivid color. Drops of magenta, cyan and gold ink fall into clear water inside a glass tank against a deep black backdrop, each color blooming and mixing into violet and teal clouds. Each drop lands on a slow 70 bpm pulse, tendrils unfolding in macro detail. The camera slowly rotates around the tank. Add a faint iridescent shimmer at the edges of the ink. High contrast, saturated, no text. Sound: a deep sub-bass pulse on each drop with soft reverb tails.

Remix this
Model
Seedance 2.5
Duration
10s
Aspect ratio
1:1
Resolution
1080P
Audio
Audio
Generated

One workspace, five workflows

Every way to get from idea to shot

The same prompt, model and credit system across all of them. Pick the input you have.

Seedance 2.5

The current generation, in a workspace built around it

Released by ByteDance Seed on July 31, 2026. On Seedancee it is the default model for every workflow.

About Seedance 2.5Compare 2.5 and 2.0
  • Up to 30s per generation
  • Native audio and dialogue
  • 30 images, 10 clips, 10 audio tracks as references
  • Edit and extend existing clips
  • Output up to 1080P
  • Seedance 2.5 · 2026-09-29

Made on Seedancee with Seedance 2.5

  • Matte-black headphones on wet slate

    Matte-black headphones on wet slate

    Seedance 2.5 · 8s · 16:9 · Staff

    Prompt

    Studio product film. A pair of matte-black over-ear headphones rests on a slab of wet dark slate. The camera begins on a tight macro of the ear cushion stitching, then pulls back on a slow motorized slider to reveal the full silhouette. A single hard key light from the upper left throws a crisp rim highlight along the headband; soft fill from a large overhead diffuser. Fine mist drifts through the beam. In the final second, a bead of water slides off the cup and lands with a soft, clean drip sound. Sound design: low room tone, subtle hum of the light, the single drip. No text, no logo.

    Watch and remix
  • Silk coat in a wind tunnel

    Silk coat in a wind tunnel

    Seedance 2.5 · 8s · 9:16 · Staff

    Prompt

    Fashion film, 35mm anamorphic look, rich saturated color. A model in a floor-length emerald-green silk coat stands in a sunlit terracotta courtyard, late-afternoon golden light raking across ochre walls and a cobalt-blue door. A wind machine off-screen lifts the coat in slow waves. The camera orbits a quarter turn at hip height, shallow depth of field, soft warm lens flares. Palette: emerald, gold, terracotta, cobalt. Motion is unhurried; fabric moves in slow motion while the model holds a steady gaze into the lens. Sound: fabric rustle, distant wind, no music.

    Watch and remix
  • Night train, rain on the window

    Night train, rain on the window

    Seedance 2.5 · 10s · 21:9 · Staff

    Prompt

    Cinematic scene. Interior of an overnight train at 2 a.m. A woman in a wool coat rests her forehead against the window; rain streaks the glass and the passing sodium lamps paint moving orange bars across her face. The camera is locked off on the seat opposite, slight handheld drift. Rich color: amber lamp glow against cool teal-blue night outside the window, deep shadows, subtle film grain, warm practical light from a reading lamp above. Halfway through she exhales and closes her eyes. Sound: steady rail rhythm, rain against glass, the lamp buzzing faintly.

    Watch and remix

Model chooser

Pick the right Seedance model for the shot

Capabilities and credit ranges come from the same registry the generator uses. Nothing here is hand-written.

Comparison of active Seedance models on Seedancee
Seedance 2.5DefaultSeedance 2.0Seedance 2.0 FastSeedance 2.0 MiniSeedance 1.5 Pro
Ideal forLonger reference-driven scenes up to 30s with native audio and editing workflows.High-quality 4–15s shots with up to 4K output and multimodal references.Quicker iterations at 480p/720p with the same reference inputs as 2.0.Lowest-cost drafts and social clips with strong visual consistency.Previous-generation text and image-to-video with a fixed-lens option.
Duration4–30s4–15s4–15s4–15s4–12s
Resolutions480p, 720p, 1080p480p, 720p, 1080p, 4k480p, 720p480p, 720p480p, 720p, 1080p
Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4, 21:916:9, 9:16, 1:1, 4:3, 3:4, 21:916:9, 9:16, 1:1, 4:3, 3:4, 21:916:9, 9:16, 1:1, 4:3, 3:4, 21:916:9, 9:16, 1:1, 4:3, 3:4, 21:9
Reference inputsFirst/last frame · 30 images · 10 videos · 10 audioFirst/last frame · 9 images · 3 videos · 3 audioFirst/last frame · 9 images · 3 videos · 3 audioFirst/last frame · 9 images · 3 videos · 3 audioFirst/last frame
Native audioYesYesYesYesYes
Edit / extendYesNoNoNoNo
Relative speedStandardSlower, higher qualityFastFastStandard
Estimated credits300–5647 per generation200–3726 per generation120–450 per generation40–150 per generation20–257 per generation
Capabilities verified2026-09-292026-09-292026-09-292026-09-292026-09-29
Read the full comparison

Comparisons

How Seedance compares

Version-to-version and head-to-head pages with verified Seedance capabilities and a last-verified date. Side-by-side test outputs are added as Seedance Lab publishes them.

Prompt Lab

Write prompts like shot lists

Prompt Lab is the set of writing tools inside the Seedancee workspace. Here is what each one does to a prompt; the public prompt guide covers the same techniques.

Prompt enhancerExample

Your idea

old lighthouse keeper at dusk says "They said the light would never fail."

Enhanced prompt

An elderly lighthouse keeper with a white beard and a faded red wool sweater sits at a wooden table, looks just off lens and half-smiles before he speaks. A small stone room at the top of the lighthouse at dusk, a kerosene lamp on the table and deep blue sky in the window behind him. Slow push-in from a medium shot to a medium close-up, keeping him centered. Warm amber key light from the lamp, cool blue fill from the window, soft film grain. He says in a low, gravelly voice: "They said the light would never fail." Wind presses on the shutters, a foghorn sounds far away, no music. No cuts, no text on screen.

What the enhancer changed

  • Added subject details and one clear action
  • Set the room, time of day and two set details
  • Chose one camera move with start and end framing
  • Described key light, fill and the look
  • Kept the line word for word; added delivery, ambience and constraints

Written by the Seedancee team to show the structure the enhancer returns. It is not a live result: real output depends on your idea and the target model.

  1. 02Shot builder

    Assembles a prompt from structured fields so nothing important is left out.

    Shot size:
    medium close-up
    Lens:
    portrait lens feel with shallow depth of field
    Camera:
    slow push-in (dolly in) toward the subject

  2. 03Camera controls

    Vocabulary for moves, lenses and framing that the models respond to reliably.

    • slow push-in (dolly in) toward the subject
    • slow half-orbit around the subject, keeping it centred
    • side tracking shot moving with the subject
    • crane up rising above the scene

  3. 04Negative instructions

    Phrasing for what to avoid, applied only where the provider accepts it.

    No cuts, no text on screen, no logos.

  4. 05Dialogue formatting

    How to write spoken lines so native audio and lip movement follow them.

    The keeper says, low and gravelly: "They said the light would never fail."

Open the prompt guide

Use cases

Made for the work that needs a finished shot

  • Ads

    Product films and campaign cutdowns without a set.

  • E-commerce

    Turn product stills into motion for listings and paid social.

  • Social

    Vertical clips with sound, produced in minutes.

  • Short films

    Blocked scenes, consistent characters, dialogue.

  • Storyboards

    Animatics and previs before a real shoot.

  • Music visuals

    Loops and abstract sequences timed to a beat.

  • Creator content

    B-roll, intros and visual explainers on demand.

Pricing

Starter and Pro, weekly, monthly or yearly

Each plan adds credits every billing period. A generation's cost depends on model, duration, resolution and audio, the generator shows it before you submit, and credits are only charged when a job succeeds.

Prices are in US dollars and exclude tax. VAT or sales tax is added at checkout where it applies.

Credit packs are available to subscribers.

Generating a video needs a subscription; plans start at $4.99 per week. Configuring a shot and seeing its cost is free, no account needed.

See all plans

FAQ

Questions people ask about Seedance

What is Seedance?

Seedance is a family of AI video generation models developed by ByteDance Seed. The versions available on Seedancee (Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini, and Seedance 1.5 Pro) generate short video from text prompts, images, reference video clips, and reference audio. All of them can generate native audio. Seedancee is an independent workspace for creating video with these models through a third-party API provider.

Who makes Seedance?

Seedance is developed by ByteDance's Seed team. Seedancee is not affiliated with, endorsed by or sponsored by ByteDance; it is an independent platform that adds a workspace, prompt tools, projects and a credit system around compatible Seedance models.

Is Seedance free?

ByteDance and other platforms offer Seedance access on their own terms. On Seedancee you can configure any shot and see its cost for free, but generating a video needs a subscription. Every generation costs credits that depend on the model, duration, resolution and audio, and the estimate is shown before you submit.

How do I use Seedance?

Pick a mode (text, image, reference, edit, or extend), choose a model, write a shot-style prompt that covers subject, camera, light and sound, then set aspect ratio, duration and resolution. On Seedancee you can configure everything before creating an account; your draft is restored right after sign-up. The step-by-step guide walks through each setting.

Is Seedance open source?

As of September 29, 2026, ByteDance has not publicly released Seedance model weights. The models are available through hosted APIs and partner platforms. Seedancee uses a hosted provider and does not distribute any weights.

Can Seedance run locally?

Not in a supported way. Because the weights are not publicly released as of September 29, 2026, there is no official option to run Seedance on your own hardware. Seedancee runs generation in the cloud, so a browser is all you need.

Does Seedance generate audio?

Yes, on models that support native audio (Seedance 2.5, Seedance 2.0, Seedance 2.0 Fast, Seedance 2.0 Mini, and Seedance 1.5 Pro). Native audio covers ambient sound, effects and dialogue when you describe them in the prompt, and you can turn it off per generation.

What is the difference between Seedance 2.5 and 2.0?

Seedance 2.5 (released July 31, 2026) generates up to 30 seconds per job, adds edit and extend workflows, and accepts up to 30 reference images, 10 reference clips and 10 audio tracks. Seedance 2.0 (released February 12, 2026) tops out at 15 seconds but offers output up to 4K. Both support native audio and first/last-frame control. Full details are on the comparison page.

How does Seedance pricing work on Seedancee?

Seedancee uses credits. Each generation is quoted from its duration, resolution, audio setting and reference video before you submit; credits are reserved when the job starts and released if it fails. Generating needs a subscription: Starter and Pro are sold weekly, monthly or yearly, from $4.99 per week, and subscribers can add one-time credit packs. Current plans are on the pricing page.

Where can I access Seedance?

Through ByteDance's own products and a number of third-party platforms. Seedancee gives you browser access with a full workspace, projects and reusable assets; the developer API is in early access. Our guide on where to use Seedance compares the options.

Your next shot starts here.

Configure it above, or open the full workspace.

Create with Seedance