Video Models

Seedance 2.5

ByteDance's long-sequence video model — native 30-second single-shot clips, native 4K, up to 50 multimodal reference assets, phoneme-level lip-sync and one-pass synced audio.

Seedance 2.5, unveiled by ByteDance’s cloud arm Volcano Engine on June 23, 2026 at its summer FORCE conference, pushes AI video into the long-sequence era: a native 30-second single-shot clip generated in one pass, at 4K, with synchronized audio. Where most models — and ByteDance’s own Seedance 2.0 — stop around 5–15 seconds, 2.5 roughly doubles the ceiling, which is the difference between stitching a montage and directing one continuous scene.

Editorial illustration: multiple reference thumbnails (portrait, landscape, product, audio) merging along a 30-second timeline into a single 4K video frame with a synced soundwave.

Original illustration by Heyaiwiki — Seedance 2.5 turns many reference inputs into one long, audio-synced 4K shot.

What’s new in Seedance 2.5

According to ByteDance and conference reporting, the headline upgrades are:

  • Native 30-second output. A complete half-minute clip in a single generation, rather than short segments you splice together — aimed squarely at directors, agencies and e-commerce creators.
  • Up to 50 multimodal reference assets. Feed it images, video, audio and brand/style guides (up from ~12 on Seedance 2.0) so a long timeline stays on-model and on-brand.
  • Native 4K. Production-grade resolution baked into the pipeline; the older Seedance 2.0 base was upgraded to 4K at the same event.
  • Phoneme-level lip-sync and one-pass audio. Context-aware background music plus environmental sound effects are generated and matched to the action in the same rendering pass.
  • Localized scene editing. Adjust one detail — a prop, a movement, a line — without re-rolling the entire video, which attacks the “dice-roll” regeneration problem head-on.

Volcano Engine president Tan Dai framed long-form, controllable video generation as a step toward world models, not just a content tool.

Community reaction

Filmmaker and AI creator el.cine (@EHuanglu) shared the launch with the wider creative community:

Post on X

Seedance 2.5 vs Seedance 2.0

CapabilitySeedance 2.0Seedance 2.5
Native clip length~15s30s single-shot
Reference assets~1250
Resolutionup to 1080p (now upgraded to 4K)native 4K
Editingclip/subject editinglocalized scene editing
Audiodual-channel synced audioone-pass synced audio + ambient design
Status (Jun 2026)generally availableenterprise beta → GA early July

Seedance 2.0 remains the reference-driven workhorse and now outputs 4K too; 2.5 is the longer-form, higher-control successor built for full scenes.

Availability and pricing

At announcement Seedance 2.5 is in global enterprise beta, with a broader rollout expected in early July 2026 through Volcano Engine. Public per-second pricing and API details had not been published as of the announcement, so treat any cost figures as provisional until ByteDance ships the GA tier. For a model you can use today, Seedance 2.0 covers most reference-driven and short-form jobs.

Who it’s for

Seedance 2.5 is built for teams that need one long, coherent take rather than a cut-up montage: 30-second ads and explainers, brand-consistent product films assembled from many references, and iterative workflows where editing a single shot shouldn’t break the rest of the clip. If your work is short-form or you need it in production right now, start with Seedance 2.0 and migrate when 2.5 reaches general availability.

Best for

  • Long-form ads, explainers and product films that need 30s in one take
  • Reference-heavy, brand-consistent e-commerce and catalog video
  • Iterative editing where you fix one shot without re-rolling the whole clip

Pros & cons

Strengths

  • Native 30-second single-shot output — well beyond the 5–15s industry norm
  • Up to 50 multimodal reference assets (images, video, audio, brand guides)
  • Native 4K resolution with synced audio generated in a single pass
  • Localized scene editing keeps the rest of the clip stable when you tweak one detail

Limitations

  • Enterprise beta at announcement; general availability not until early July 2026
  • Public pricing and API details not yet released
  • Real-world quality vs Veo / Kling / Sora awaits independent, hands-on testing

Frequently asked questions

When is Seedance 2.5 available?

ByteDance unveiled Seedance 2.5 on June 23, 2026 at the Volcano Engine FORCE conference. It is in global enterprise beta now, with a general rollout slated for early July 2026.

How long can a Seedance 2.5 video be?

It generates a native 30-second single-shot clip in one pass — roughly double Seedance 2.0's 15 seconds and well ahead of the 5–15s most rivals cap at.

What resolution does Seedance 2.5 output?

Native 4K. At the same event ByteDance also upgraded the existing Seedance 2.0 base model to native 4K output.

How many reference assets can it take?

Up to 50 multimodal reference materials — images, video clips, audio and brand/style guides — versus about 12 on Seedance 2.0.

Sources

Last updated: 2026-06-23 · Specs and pricing change fast — verify on the vendor's site before relying on them.