Seedance 2.5 is a new-generation video creation model that enhances user expectations from simple clip generation to complete creative work. It utilizes a unified multimodal audio-video joint-generation architecture.

Seedance 2.5 can generate native 30-second video clips in a single pass. The API release is now targeted for July 16, following delays due to negotiations with rights holders.

Seedance 2.0 is an image-to-video and text-to-video AI model developed by ByteDance, launched on February 14. Its hyperrealistic capabilities have generated significant attention and concern within the Hollywood industry.