Four reference modalities
Combine text, images, video, and audio to guide composition, motion, camera language, and sound.
Built for production work that needs multimodal references, complex motion, and director-level control.
Combine text, images, video, and audio to guide composition, motion, camera language, and sound.
Handles multi-subject interaction, sports, combat, and collisions with more stable motion and believable weight.
Edit specified clips, characters, and actions, or extend a video while preserving story and subject consistency.