Pika Launches Enact: Real-Time Directable AI Video Generation

nikola_mr64990 · x · 2026-11-19

Pika announced a research preview of Pika Enact, built on Pika H3 Flex. It generates video and sound in sub-second chunks while carrying scene context forward, letting creators direct as if on a film set.

Three interaction modes: Live Staging (place/reposition actors and objects mid-generation with the mouse), Live Actor Direction (talk to actors, whose performances remember your notes and deliver a fresh continuous take on "Action"), and Live Camera Control (steer camera movement live).

Related event: Pika Launches Enact, a Research Preview for Directing AI Video in Real Time(7 posts)→

Original post →

More from Multimodal

Multimodal channel →