ByteDance's Seedance 2.5 breaks the 30-second barrier for AI video generation

Ad

Skip to content

The Decoder

AI, Menschen, Wirtschaft

-->

Sign In

Register

Subscribe Now

The Decoder

Opens discord in a new tab<br>Opens LinkedIn in a new tab

ByteDance's Seedance 2.5 breaks the 30-second barrier for AI video generation

Maximilian Schreiner

View the LinkedIn Profile of Maximilian Schreiner

Jun 23, 2026

ByteDance introduced five new AI models at Volcano Engine's FORCE conference. The centerpiece is Seedance 2.5, a video model set to launch in early July.

Volcano Engine is ByteDance's cloud business, which offers the company's AI models as services for enterprises. The new model generates single video clips up to 30 seconds long without any post-stitching, complete with scene changes and tempo shifts. It can process up to 50 additional inputs at once - reference images, audio, and more - useful for film scenes with multiple characters. Users can also edit generated videos after the fact while keeping the visual style and look intact.

Seedance 2.0 gets 4K, and four more models join the lineup

Meanwhile, Seedance 2.0 now supports native 4K with 10-bit color depth. Volcano Engine also announced the Doubao 2.1 Pro language model, the Seedream 5.0 Pro image model, and the Seed-Audio 1.0 audio model. According to the company, Doubao 2.1 Pro costs about 80 percent less than Claude Opus 4.6.Ad<br>DEC_D_Incontent-1

Ad

AI News Without the Hype – Curated by Humans

Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.

Subscribe now

Source: Weixin

Ask about this article…

Search

Top<br>Stories

Sam Altman says a whole generation of researchers held AI back by underestimating what scaling could do

Microsoft researcher builds a working neural network out of goats in Age of Empires II to critique AI science

Vibecoding is becoming a deal-breaker test for software acquisitions

Sakana AI's Fugu orchestrates multiple LLMs to match Anthropic's Fable and Mythos benchmarks

OpenAI's Codex can now watch you work once and repeat the task forever

Don't Miss<br>What Matters

Stay in the loop on AI. Clear, useful, no fluff.

Your email address

Subscribe to our Newsletter

Most<br>Popular

Landmark German ruling declares Google's AI Overviews are Google's own words and makes it liable for false answers

For $1.3 million a month, OpenClaw founder Peter Steinberger runs 100 AI agents that code, review PRs, and find bugs

Google launches a tiny board that runs Gemma 3 locally

Fields Medalist says ChatGPT 5.5 Pro delivered "PhD-level" math research in under two hours with zero human help

Researchers let Claude Code discover AI scaling algorithms that humans probably wouldn't have designed

Sam Altman says a whole generation of researchers held AI back by underestimating what scaling could do

AI Community<br>& Insights

The Decoder

Follow The Decoder for AI news, background stories and expert analyses.

Opens LinkedIn in a new tab

Opens Discord in a new tab

BETA-TEST

&times;

Start new search

&times;

Send

wpDiscuz

Insert

BETA-TEST

&times;

Start new search

&times;

Send

wpDiscuz

Insert