Shotcraft
Video generation

ByteDance Seedance 2.0

Seedance 2.0 is ByteDance Seed's unified multimodal audio-video model: a single generation pass accepts text plus mixed references (up to 9 images, 3 video clips and 3 audio files, addressed in the prompt as [Image1], [Video1], [Audio1]) and returns video with synchronised native audio, including lip-synced dialogue when speech is quoted in the prompt.

A video generation model by ByteDance · read 2026-08-14 · sourcing low

Resolution
disputed — 720p per ByteDance's own Replicate listing, 4K per Higgsfield's model schema (see disagreements)
Aspect ratios
16:9, 4:3, 1:1, 3:4
Weights
Not released
API
Yes
Commercial use
Not established

It also supports first/last frame conditioning, prompt-driven video editing (replace an object in a reference clip while keeping the original motion) and an intelligent-duration mode where the model chooses clip length. It reaches consumers through Jimeng/Dreamina and developers through Volcengine, BytePlus ModelArk, Replicate and resellers.

Commercial use — Not established

The research notes for this model record other terms but do not state a commercial-use position, and no licence page was retrieved, so it is not established here. Check the vendor's own terms.

The licence notes recorded during research were read for a commercial-use position and did not state one. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from ByteDance's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is thin. Treat it as a starting point and verify before relying on any figure. Check the vendor's current documentation

What it takes in
text, image, video, audio
What it makes
video, audio
Maximum duration
not established
Maximum resolution
disputed — 720p per ByteDance's own Replicate listing, 4K per Higgsfield's model schema (see disagreements)
Aspect ratios
16:9, 4:3, 1:1, 3:4, 9:16, 21:9
Controls
image-to-video, start-end-frame, reference-character-consistency, inpainting, lipsync
Weights
Not released
API
Yes
Pricing
Not verified. BytePlus ModelArk's video pricing page is client-rendered and returned no rate table; no first-party per-second price could be confirmed.
Released or updated
Seedance 2.0 page live on seed.bytedance.com as of 2026-08-14; the Replicate listing reports the model was created roughly four months earlier and last updated roughly two months earlier. A Seedance 2.5 tier is separately marketed by Higgsfield.
Prompt limit
not published by the vendorVendor figure, checked 2026-08-16Collected from the vendor's own documentation on 16 August 2026. Vendors change these between model versions without announcing it, so check the vendor's current API reference before you rely on it. Check the vendor's documentation

Maximum duration is not established here. That means no page we could retrieve stated it, not that the model lacks one.

Strengths

  • Genuinely unified multimodal input: images, video and audio references combined in one pass
  • Native audio generated jointly with picture, including dialogue with matching lip movement
  • Prompt-driven video editing that preserves original motion
  • Intelligent duration (set duration to -1 and let the model choose)
  • Very widely resold, including exclusive higher-resolution tiers on some platforms

Weaknesses

  • Specs vary sharply by host, which makes 'the' max resolution and duration unanswerable from first-party sources
  • ByteDance publishes no fetchable spec or price table on its own docs surface
  • Audio references require at least one image or video reference
  • No published maximum duration

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

How to prompt it

Written for ByteDance Seedance 2.0. See prompt craft for the full vocabulary and cinematic language for the lens, light and mood tables.

MCP servers that front ByteDance

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

2 further servers name ByteDance with lower confidence and are not listed, because a server naming a vendor may be using it for text rather than media.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Seedance 1.0 Pro (closed weights)

ByteDance's commercial video generation model, available in Pro, Pro Fast and Lite tiers via API. It supports text-to-video and image-to-video at 480p

Video generation

Adobe Firefly Video Model

The Adobe Firefly Video Model generates video from a text prompt, optionally guided by an image used as the first or final frame. Adobe's Firefly Serv

Video generation

Allegro

A small text-to-video model comprising a 2.8B VideoDiT and a 175M VideoVAE, released under Apache-2.0 in October 2024. It generates 88-frame clips at

Video generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.