ByteDance unveils AI model that can create 30-sec videos in one go

ByteDance has unveiled Seedance 2.5, an AI video generation model that can create 30-second videos in 4K resolution in a single go and from a single prompt. It can accept up to 50 simultaneous multimodal reference inputs, including images, videos, or audio files, up from 12 in Seedance 2.0. The model is expected to be launched in early July.