ByteDance is preparing to release Seedance 2.5, its latest AI video generation model. The tool can produce 30-second 4K videos from a single prompt and accepts up to 50 reference files.
The Chinese company unveiled the model at a conference in Beijing last month. Reports indicate a possible launch as early as this week, with a July 9 date mentioned by Testing Catalog.
Users can input images, videos or audio as references, a significant increase from the 12 allowed in Seedance 2.0. An official landing page is already live on the Dreamina website, and CapCut posted about the release on July 4.
ByteDance plans to make the model available first in China next month. The previous version faced delays in the United States over copyright concerns raised by Hollywood.
