ByteDance Launches Next-Generation AI Video Generation Model Waver 1.0

ByteDance has launched its next-generation AI video generation model, Waver 1.0, built on the Rectified Flow Transformer architecture. It supports text-to-video, image-to-video, and text-to-image generation without the need to switch models. The model enables outputs of up to 1080p resolution with flexible video lengths ranging from 2 to 10 seconds. It excels at capturing complex motions, producing videos with impressive motion dynamics and strong temporal consistency.