Seedance
Seedance is ByteDance's video lineage — cinematic motion, native audio, multimodal reference inputs. The family row is wired to Seedance 2.0 Video Edit today; the sibling Seedance 2.0 Text-to-Video model is in the catalog but its family_id isn't set yet (admin can pin it to this family to make the lineage discoverable on the family page).
Seedance 2.0 Pro is ByteDance's flagship text-to-video model — strong prompt adherence, natural motion, and optional multimodal references (images, videos, audio) to lock identity, style, and rhythm. This is the native ByteDance ModelArk endpoint; the WaveSpeed-routed siblings stay in the catalogue for users that already point at them.
Seedance 2.0 (Text-to-Video) is ByteDance's cinematic text-to-video generator on WaveSpeed. Produces 4–15 s clips at 480p, 720p, or 1080p with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Optional reference images, videos, and audio guide visual style, identity, and atmosphere.
Seedance 2.5 Text to Video is ByteDance's next-generation video model, turning a written brief into a single continuous take of up to 30 seconds — with dialogue, effects and ambience generated in the same pass. It renders up to native 4K and, when you need it, follows up to 30 reference images plus video and audio references for characters, products and motion.