ByteDance Releases Seedance 2.5 Video Generation Model
ByteDance has introduced Seedance 2.5, the newest iteration of its Seed video-generation model. The model is capable of producing 30-second high-quality video clips in a single generation process.
ByteDance, the parent company of TikTok, has launched Seedance 2.5, the latest version of its Seed model for video generation. The updated model can produce high-quality, 30-second video clips from a single processing run. It also supports multi-turn extension, allowing for the creation of longer video sequences.
The model allows users to input up to 30 images, 10 video clips, and 10 audio clips as reference material in one go. This feature aims to provide greater flexibility and control in the video generation process.
Seedance 2.5 is being rolled out to ByteDance's Jimeng AI platform and the Pro version of its Doubao application. An API (Application Programming Interface) is also expected to become available soon on Volcano Engine's Ark platform, indicating plans for broader integration.
This release positions ByteDance to compete more directly in the growing market for AI-powered creative tools, offering enhanced capabilities for content creators and developers.