Model · Video

Seedance

ByteDance's video model family. It makes clips from a description, images or reference videos, with sound, up to 30 seconds per go. Not downloadable: you use it through ByteDance's own apps and business API or apps built on it.

Go to Seedance’s website

At a glance

Open or closed
Closed
Only usable through the maker's app or API
Only API and app access offered; no weights or licence file found.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Licence
BytePlus ModelArk terms and GenAI Acceptable Use Policy (The maker's own terms)
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Can I sell what I make?
The terms don't say clearly
BytePlus targets advertising and e-commerce use but the pages read give no output licence terms; depends on the app or API you use it through.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Cost
No free plan.
Plans below.
How you use it
Maker's own API, In your browser, Through another service
Seed pages link to the BytePlus Playground, an API and Dola. Model id names it 'Dreamina Seedance'.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by
ByteDance Seed
Footer: 'Copyright 2026 Bytedance Seed'. Business API sold by BytePlus Pte Ltd; no company location stated on pages read.
source · checked 12 Oct 2026 · checked on the maker's own page
Status
Available
Seedance 2.5 on BytePlus ModelArk announced 6 Aug 2026; earlier 1.0 and 2.0 pages still online.
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

text to videoimage to videovideo to videoaudio to video

2.5 page: joint audio-video generation, up to 30 s with two extensions, more dependable edits; 1.0 page: text and image to video, multi-shot.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

No paid plans listed.

Pricing page not read (fetch budget ran out). Not offered by BytePlus in the US.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review

Rights and safety

Watermark
Visible watermark, Content credentials (C2PA)
Via BytePlus: visible watermark plus C2PA Content Credentials.
source · checked 12 Oct 2026 · checked on the maker's own page
Real faces and voices
Copies a real face (real-person likeness via ModelArk API), checks the person's consent
Real faces in input are blocked unless vetted clients complete real-person verification and likeness authorisation.
source · checked 12 Oct 2026 · checked on the maker's own page
Limits
max video seconds: 30; note: Per generation; can be extended twice.
source · checked 12 Oct 2026 · checked on the maker's own page

Other options for “A video, from a description”

Adobe Express, Adobe Firefly, Adobe Premiere, Akool, Animoto, Arcads, Canva AI (Magic Studio), CapCut, Civitai, CogVideoX, ComfyUI, Creatify, DeeVid AI, DomoAI, Dreamina, Dzine, fal, Filmora, FlexClip, Fliki, Fotor, Genmo, getimg.ai, Google Flow

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.