Pika Enact research preview: direct AI actors and camera in live-streamed video generation
techNmak · x · 2026-11-19
Pika launched Pika Enact, a research preview built on Pika H3 Flex: an experimental live-streaming environment that generates video and audio in sub-second chunks, carrying scene context forward while folding in new direction—mimicking directing on a real film set.
Three new interaction modes:
- Live Staging: place and reposition actors or objects with your mouse inside a running video while the scene keeps generating.
- Live Actor Direction: speak directly to actors to shape performances; they remember your notes and deliver a fresh continuous take when you call "Action."
- Live Camera Control: steer camera movement with your mouse around the live scene.
It signals a shift from the prompt box toward on-set directing as the AI video creation paradigm.
Related event: Pika Launches Enact, a Research Preview for Directing AI Video in Real Time(7 posts)→
More from Multimodal
- Building a Claude-controlled video editor over MCP: lessons from ~200 tools, approvals and context bloat — MrxAnomynous · 2026-11-20
- OpenMontage: a self-hosted pipeline for consistent AI short dramas — Direct_Grab7063 · 2026-11-20
- CapCut launches ChatGPT video plugin: generate and edit timeline-based videos in chat — alifcoder · 2026-11-20
- I gave Claude a video editor — it made a 21-shot short I can fix shot-by-shot — MrxAnomynous · 2026-11-20
- Demi Guo previews real-time AI video model for directing films like a set — ying11231 · 2026-11-20
- Full automated GTA 6 content pipeline: Apify + ElevenLabs + Claude + Codex — eptwts · 2026-11-20