ByteDance announced five new AI models at Volcano Engine’s FORCE conference. The highlight is Seedance 2.5, a video model scheduled for release in early July.
Volcano Engine is ByteDance’s cloud business, offering its AI models as a service to enterprises. The new model produces a single video clip up to 30 seconds long, complete with scene changes and tempo shifts, without post-stitching. It can process up to 50 additional inputs at once, such as reference images, audio, etc., useful for movie scenes with multiple characters. Users can also post-edit the generated videos while preserving their visual style and appearance.
Seedance 2.0 now supports 4K and adds four more models to 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, Seedream 5.0 Pro image model, and Seed-Audio 1.0 audio model. The company says Doubao 2.1 Pro is about 80% cheaper than Claude Opus 4.6.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, exclusive six-a-year “AI Radar” frontier reports, full archive access, and access to the comments section.
Subscribe now
