What Happened
ByteDance published its official Seedance 2.0 introduction on February 12, 2026. This entry dates the public announcement: the post says the model had launched recently without specifying the first user-access date.
Why It Matters
The release broadens video generation from a single prompt or starting image into a workflow guided by multiple audiovisual references, with editing and continuation capabilities.
Technical Details
The announced model jointly generates audio and video. Inputs can combine text with up to nine images, three video clips, and three audio clips. ByteDance describes multi-shot output up to 15 seconds, stereo audio, targeted editing, and video extension. Its performance comparisons are developer evaluations, and the announcement acknowledges remaining artifacts and consistency limitations.