Seedance: what the ByteDance video model family is, and which version to use

Seedance is ByteDance Seed’s AI video model family, from 1.0 in June 2025 to 2.5 on July 31, 2026, used through ByteDance apps and an API, with no public weights found; this site currently delivers images only, not video, and its photo editor, a different model, edits one photo in about 37 seconds for 10 credits. Free with sign-up: 10 credits = 1 image, then from $0.13.

Your edited photo appears here (this site’s editor)
Studio background edit made on this site: the same woman on a plain light-grey studio backdrop
Input photo (AI-generated, fictional): a smiling woman with curly brown hair in a green sweater, in a parkYour photo
Type your own change, or leave this empty and pick a one-tap edit below.0/400

Style changes (cartoon, 3D, anime) are not reliable yet. If the result looks unchanged, try again or describe the change more specifically.

One-tap edits

  • Images only: this site does not make video
  • Not affiliated with ByteDance
  • Free with sign-up: 10 credits = 1 image
versions on ByteDance Seed’s pages: 1.0, 1.5 pro, 2.0, 2.5
4
latest launch: Seedance 2.5 (Seed post)
Jul 31, 2026
longest single generation (2.5; 2.0 was 15 s)
30 s
models in ByteDance-Seed’s Hugging Face org named Seedance (our count)
0 of 63

What Seedance is

The family, from ByteDance Seed’s own posts

  • Seedance 1.0, post dated 2025-06-11: ByteDance Seed’s first public Seedance video model. It makes 1080p video from text and from an image, and the post gives a 10-second example with 2 to 3 shots. The post does not mention sound.Source: ByteDance Seed ·
  • Seedance 1.5 pro, post dated 2025-12-16: adds sound. It generates audio and video together from text or an image, with lip-sync in several languages and dialects. The post gives no clip length or resolution.Source: ByteDance Seed ·
  • Seedance 2.0, post dated 2026-02-12: takes text, image, audio and video as input (up to 9 images, 3 video clips and 3 audio clips) and makes up to 15 seconds of multi-shot video with two-channel sound.Source: ByteDance Seed ·
  • Seedance 2.5, post dated 2026-07-31: up to 30 seconds per generation, can be extended in more rounds, takes up to 30 images, 10 video clips and 10 audio clips as references, and edits at timestamp level. It has its own page here, linked below.Source: ByteDance Seed ·
  • The three product pages show the same buttons: Try now, Try Dola and Try in Playground, and Get API on the 1.0 and 2.0 pages. ByteDance Seed also makes other models, such as the Seedream image line.Source: ByteDance Seed, Seedance 2.0 page ·

Where each version can be used (what we read)

  • API: BytePlus’s Seedance page says the Dreamina Seedance 2.5 API is “fully available now”, with 480P and 720P options and 4 to 30 seconds per video. At launch ByteDance had said the API was “coming soon”, so this is newer. Its plan cards show approximate seconds of video but their prices did not load for us.Source: BytePlus ·
  • BytePlus’s documentation menu lists tutorials and prompt guides for both the Dreamina Seedance 2.5 series and the 2.0 series under video generation.Source: BytePlus docs ·
  • Apps: for 2.5, ByteDance named Jimeng AI and Doubao Pro (Video Generation, then choose Seedance 2.5). Dreamina’s site lists Dreamina Seedance 2.5, 2.0 and 2.0 Mini in its video model menu, next to models from other companies.Source: ByteDance Seed / Dreamina ·
  • The Try Dola button leads to dola.com, whose page title calls it an AI assistant. We could not confirm who runs it or which Seedance versions it offers. The Try in Playground button leads to BytePlus’s playground.Source: dola.com ·

Open or closed

  • We found no downloadable Seedance weights. Our own count on 2026-11-19: ByteDance-Seed’s Hugging Face organisation lists 63 models and none has Seedance or video in its name, although the same group does publish other open models. The official pages point to apps and an API, so it appears to be a closed model you use as a service. That is our reading, not a statement from ByteDance.Source: Hugging Face API, our count ·
  • By contrast, other video models do publish weights: LTX-2.5 (under a licence with a revenue limit) and LongCat Video (MIT). Both have pages on this site.Source: This site

How it compares with other video models

  • ByteDance’s own page says Seedance 1.0 ranked first for text-to-video and image-to-video on the Artificial Analysis arena, as of 2025-06-09. That is the maker quoting a ranking from over a year ago, so we do not use it as a current comparison.Source: ByteDance Seed ·
  • We read no current independent test of any Seedance version, and we ran none. So this page compares only sourced facts such as length, inputs, openness and where to use it, not which one looks better.Source: This page ·

Not confirmed

  • Prices: none read. BytePlus’s plan prices did not load for us, and we did not read Jimeng, Doubao or Dreamina prices. Dreamina’s Seedance 1.0 page says “free daily credits” without an amount; that is its claim, not tested.Source: Dreamina ·
  • Resolution: ByteDance’s 2.0 and 2.5 posts give no output resolution. BytePlus’s API page lists 480P and 720P for 2.5, so a higher resolution in apps is not confirmed either way.Source: BytePlus ·
  • Where it is available by country, and why the word “seedance” is searched more now: no page we read says. We do not guess.Source: ByteDance Seed ·

On this site: related pages

  • The Seedance 2.5 page: the newest version, with its reference limits and where ByteDance said you could try it.Source: This site: Seedance 2.5
  • Seedream 5.5, ByteDance Seed’s image model, which is the part of its line that makes still images.Source: This site: Seedream 5.5
  • LongCat Video, an open-source video model with a per-second price on fal.ai.Source: This site: LongCat Video
  • Edit your own photo with this site’s editor, for example a cleaner reference image.Source: This site: AI photo editor

Versions

Seedance versions side by side

Our table, built from ByteDance Seed’s four launch posts, read on 2026-11-19. These are ByteDance’s statements; we did not test any version.
-Seedance 1.0Seedance 1.5 proSeedance 2.0Seedance 2.5
Post date2025-06-112025-12-162026-02-122026-07-31
InputText and imageText and imageText, image, audio, videoText, image, audio, video
SoundNot mentioned in the postYes, made with the videoYes, two-channelYes
Length stated10-second exampleNot statedUp to 15 sUp to 30 s, extendable
References per requestNot statedNot stated9 images, 3 videos, 3 audio30 images, 10 videos, 10 audio
Downloadable weights foundNoNoNoNo

How to try it

How to try Seedance

  1. Start from the version’s own ByteDance Seed page

    Each version has a page with Try buttons: 1.0, 2.0 and 2.5. For the newest version, see our Seedance 2.5 page.

  2. Pick an app, and check price and country there

    ByteDance named Jimeng AI and Doubao Pro for 2.5. Dreamina and Dola also appear. We read no prices in any of them, so check the app before you pay.

  3. Developers: the BytePlus API

    BytePlus says the Seedance 2.5 API is fully available, with 480P and 720P and 4 to 30 seconds per video. Its playground is linked from ByteDance Seed’s pages.

  4. Need a still image or a clean reference photo? Use the editor here

    This site edits one photo at a time and does not make video. Upload a photo and write the change (up to 400 characters), or tap a ready-made edit.

Prompts

Photo edit prompts for this site’s editor

These are this site’s photo-editor prompts, for tidying a photo before you use it as a reference in a video tool. They are not Seedance prompts. We did not run them for this page, and we have not tested them in other tools. Results vary with the photo.

Not run for this page. For the newest Seedance version and its reference limits, read our Seedance 2.5 page.

  • Remove background clutter

    Edit my uploaded photo: remove distracting clutter from the background (stray objects, litter, bins, cables, signs and people in the background) and fill those areas naturally with what is around them. Keep the framing as it is. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Plain studio background

    Edit my uploaded photo: replace the background with a plain, softly lit light-grey studio backdrop with natural soft shadows. Keep the framing as it is. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Professional headshot

    Edit my uploaded photo into a clean professional headshot: a smooth neutral grey-blue background with a gentle gradient, soft even studio light on the face, the same crop or a slightly tighter head-and-shoulders crop. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

Not run for this page. ByteDance Seed’s image model is a different product, covered on our Seedream 5.5 page.

  • Fix the lighting

    Edit my uploaded photo: fix the lighting only. Balance the exposure, lift dark shadows on faces, tame blown-out highlights and correct the white balance so skin tones look natural. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Warm golden-hour light

    Edit my uploaded photo: change only the light to warm, low golden-hour sunlight from one side, with soft long shadows and a warm glow, as if taken shortly before sunset. Keep the scene and framing. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Classic black and white

    Edit my uploaded photo into a classic black and white photograph with rich contrast, deep blacks, clean whites and fine film grain. Keep the composition exactly as it is. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

  • Watercolor painting

    Repaint my uploaded photo as a soft watercolor painting on textured white paper, with loose washes and visible brush edges, keeping the same composition. Keep every person and pet recognizable, and do not add or remove anyone. No text, logos or watermarks.

  • Sharpen and clean up

    Edit my uploaded photo: gently sharpen it, reduce noise and compression artifacts, and recover fine detail in hair, fabric and edges, without a plastic or over-smoothed look. Keep every face, expression, pose and outfit exactly the same. No text, logos or watermarks.

Pricing on this site

Credit packs or a monthly plan.

Credits come in one-time packs ($4.99 for 50 credits, $9.99 for 120 credits, $19.99 for 300 credits); each image costs 10 credits. Or pick a plan from $9.90 a month (500 credits), cancel anytime.

  • Basic · $9.90/month500 credits a month · about 50 images · $0.20 per image
  • Pro · $19.90/month1500 credits a month · about 150 images · $0.13 per image

Billed every month and renews automatically. Cancel anytime in Settings; you keep the plan until the end of the month you paid for. Each month's credits are for that month; unused ones expire.

Refund policy

FAQ

Questions, answered

What is Seedance?

Seedance is ByteDance Seed’s family of AI video models. The first public version, 1.0, came out in June 2025 and the newest, 2.5, on July 31, 2026. They turn text, images and (from 2.0) audio and video references into video, and the later versions also make sound.

What are the Seedance versions and release dates (Seedance 1.0, 2.0, 2.5)?

By ByteDance Seed’s own posts: Seedance 1.0 on 2025-06-11, Seedance 1.5 pro on 2025-12-16, Seedance 2.0 on 2026-02-12 and Seedance 2.5 on 2026-07-31. Dreamina’s menu also lists a 2.0 Mini, which we could not read about.

What is the difference between Seedance 2.0 and Seedance 2.5?

Per ByteDance: 2.0 makes up to 15 seconds and takes up to 9 images, 3 videos and 3 audio clips; 2.5 makes up to 30 seconds per generation, can extend further, and takes up to 30 images, 10 videos and 10 audio clips. Our Seedance 2.5 page goes into detail.

Where can I use Seedance, and is there a Seedance API?

ByteDance named Jimeng AI and Doubao Pro for 2.5, and its pages link to Dola and to BytePlus’s playground. BytePlus says the Seedance 2.5 API is fully available, with 480P and 720P and 4 to 30 seconds per video. Check each app for your country.

How much does Seedance cost, and is Seedance free?

We did not read a price at the source: BytePlus’s plan prices did not load for us. Dreamina’s Seedance 1.0 page claims free daily credits, with no amount. On this site, which makes images only, Partly: new accounts get 10 free credits after signing in, enough for 1 free image (once per account, valid for 7 days, while the day's new-account gifts last). Each image costs 10 credits, from $0.13 on a monthly plan.

Is Seedance open source?

We found no downloadable Seedance weights. Of 63 models in ByteDance-Seed’s Hugging Face organisation on 2026-11-19, none is named Seedance, and the official pages offer apps and an API. So it appears to be closed; that is our reading, not ByteDance’s statement.

Is Seedance the same as Seedream?

No. Seedance is ByteDance Seed’s video line. Seedream is its image line, and this site has a page on Seedream 5.5. This site runs neither: its editor uses a different model, takes one photo and returns a still image.

Can I make a Seedance video on this site?

No. This site currently delivers images only, not video, and it is not affiliated with ByteDance. You can edit one photo in about 37 seconds (1024 × 1024), for example to prepare a clean reference image for a video tool.

Need a clean photo first?

Upload it, write the change, and download the result in about 37 seconds. Images only, not video.

Edit a photo here

Independent site. Not affiliated with ByteDance, ByteDance Seed, BytePlus, Dreamina, Jimeng, Doubao or Dola. This site does not run Seedance and does not make video. Seedance facts come from ByteDance Seed’s and BytePlus’s own pages, read on 2026-11-19; access, limits and prices may have changed.