Runway: AI Video Models and Creative Controls

Runway develops Gen video models and controls for consistent subjects, directed motion and generated character performances, including Act-One.

kindCompany

Updated

Video models that can be directed

Runway develops generative video technology and creative tools around it. Its stated research direction includes models that simulate the visual world, while its released products give creators controls over subjects, shots and performances. Those product controls are concrete contributions distinct from the broader research goal.

Gen-4 used reference images with instructions to preserve a character, object or location across different shots. The company demonstrated consistent subjects across lighting and viewpoints, addressing the practical problem of keeping a sequence recognizable instead of treating every clip as a new cast and setting.

Performance and motion are separate controls

Act-One, released inside Gen-3 Alpha in October 2024, used a recorded actor's performance to animate a generated character. A simple camera recording supplied the driving performance, reducing the need for a traditional facial-animation capture and rigging pipeline.

Gen-4.5 followed in December 2025, emphasizing motion and prompt adherence. Its release described additional control modes as forthcoming, so a current feature list should not be projected onto that initial rollout. Selected demonstrations and leaderboard comparisons also do not establish that every generated scene obeys real-world physics.

Sources

  1. [1]
    About Runway AI Video Platform

    Runway · retrieved Oct 23, 2026

  2. [2]
  3. [3]
    Introducing Act-One

    Runway · Oct 22, 2024

  4. [4]

Runway history

2025

│
Runway ships Gen-4.5, its sharpest video model yet

A new flagship video generation model with tighter prompt adherence and better physics: human movement, camera dynamics, cause and effect. It topped the Artificial Analysis text-to-video leaderboard on release.

Runway
Model

2024

│
Runway introduces Act-One for AI character performances

A tool inside Gen-3 Alpha transfers an actor's facial performance, filmed on an ordinary camera, onto an animated or realistic character. It let one performer voice and animate multiple characters in a scene without motion capture equipment.

Runway
Product

2022

●
Stable Diffusion puts image generation on a home GPU

With Stability AI, CompVis

Stable Diffusion released downloadable weights for text-to-image generation, letting developers run and adapt the model themselves. It generated images through a compressed representation that reduced compute demands, with responsibilities and distribution requirements under its release license.

Stability AI
Model