ByteDance launches Seedance 2.0, an AI video model combining text, image, video, and audio prompts
AI video model releases
ByteDance launches Seedance 2.0, an AI video model combining text, image, video, and audio prompts
ByteDance launched Seedance 2.0, which can generate video clips from prompts combining text, images, video, and audio.
Users can feed the model up to 9 images, 3 video clips, and 3 audio clips to refine text prompts, and it generates clips up to 15 seconds long with audio.
ByteDance says the model accounts for camera movement, visual effects, and motion, and can reference text-based storyboards.
In a demo example, ByteDance claims the model rendered two figure skaters performing synchronized takeoffs, mid-air spins, and ice landings while following real-world physics.
Early social media tests show the model generating a cinematic fight scene using the likenesses of Brad Pitt and Tom Cruise, anime-style clips, and content resembling copyrighted characters like Dragon Ball Z, raising unresolved copyright questions.
cho.sh