Seedance

Seedance 2.5 is ByteDance's video generation model, launched 31 July 2026 inside Jimeng AI and Doubao Pro. It generates clips up to 30 seconds at 4K in a single run, producing video and audio together in one pass rather than dubbing audio afterwards, and supports multi-turn extension for longer sequences. Its distinguishing feature is an input system accepting up to 50 multimodal references at once, images, text descriptions, style frames, character references and scene direction, used to steer character and style consistency across a shot. It is served through Volcano Engine Ark and...

Seedance 2.0 is a massive leap in AI video generation, featuring native audio-video joint generation. It produces synchronized dialogue, sound effects, and background music as part of the core pipeline rather than post-processing. It supports up to 12 reference files simultaneously (up to 9 images, 3 video clips, and 3 audio clips) and generates 2K resolution video up to 15 seconds long.

Seedance 1.5 pro is ByteDance's next-generation audio-visual generation model, launched in December 2025. It generates synchronized video and audio in a single pass, supports text-to-video and image-to-video workflows, and offers cinematic camera control, multi-language and dialect lip-sync, and autonomous audio-visual scene direction.