ByteDance AI video models
TikTok parent; its Seed team builds the Seedream/Seedance image and video models, plus Dreamina and OmniHuman.
Omnihuman 1.5Creates vivid, emotional character videos driven entirely by your audio.Seedance 1.5 ProKeyframe-driven video with native audio, from a start frame, an end frame, or both.Seedance 2.0Reference-driven video up to 4K with native audio — hold a look across shots with reference images, clips, or audio.Seedance 2.0 MiniThe lightest Seedance tier — short reference-driven clips at 480p and 720p.Seedance 2.5Reference-driven video up to 30 seconds at 1080p, with native audio.