Seedance

Seedance is ByteDance Seed's AI video-generation model family. The latest version, Seedance 2.5, builds on Seedance 2.0's unified audio-video architecture and supports multimodal references using text, images, videos and audio. It can generate up to 30-second audio-video clips in a single generation, supports multi-round video extension, and provides stronger control over storytelling, characters, camera movement, editing and multimodal references. Seedance 2.0 supported up to 15-second audio-video generation and multiple reference inputs, while Seedance 1.0 focused on text/image-to-video and multi-shot storytelling.

Availability depends on the particular ByteDance product/API through which the model is accessed; no specific country-wide ban is stated on the official Seedance model pages reviewed.