Seedance turns your images, clips and words into stunning AI-generated videos — with true multi-modal reference control, right from your iPhone.
Every clip below was generated with Seedance — straight out of the app, untouched.
Loading the latest creations…
A truly controllable multi-modal AI video model — reference anything, edit anything, create anything.
Bring up to 9 images, 3 video clips (15s combined) and 3 audio tracks into one generation. Mix text, pictures, footage and sound however your idea demands.
Borrow motion, effects, camera moves, characters, scenes or sounds from any upload — point at it in plain language and the model gets it.
Faces, outfits, lettering, scenes and style stay locked from the first frame to the last — no character drift, no style wobble.
Hand the model a reference clip and it mirrors the choreography and cinematic camera work — no elaborate prompting required.
Extend a shot, stitch clips together, or rework a single segment — swap characters, add elements, change actions while the rest stays put.
Scene-aware sound effects and music, generated automatically — or sync your visuals to a track you upload.
From materials to motion in three steps.
Photos, video clips, even a soundtrack — everything becomes a reference.
Type @ to reference uploads precisely: “@Image1 as first frame, surfing on the sea…”
Cinematic video in minutes, with audio. Saved to your library, ready to share.
Start with free credits when you join. Pay only for what you generate — no subscription required.
Join free at launch