concept

Act-One (Runway)

Act-One is Runway's performance-capture feature that takes a webcam recording of a person's face and retargets the performance onto a generated character — making AI-generated characters convincingly act.

Launched by Runway in late 2024, Act-One was the first widely-used AI tool that solved character performance capture without motion-capture rigs. The user records a short video of themselves performing the lines + expressions, supplies a character reference image, and Act-One generates a clip of the character performing the same way. Quality is good enough for narrative work, ads, and short films. By 2026 Act-One has become a standard tool in AI-assisted filmmaking workflows alongside Gen-4. Major limitation: extreme angles and overlapping faces still struggle.

When to use act-one (runway)

AI-assisted filmmaking and animation.
Ads requiring character dialogue.
Performance capture without mocap rigs.

Common mistakes

Trying to retarget faces with extreme rotation — degrades quickly.
Cropping too tight — Act-One needs context to retarget convincingly.

FAQ

What is act-one (runway)?

When should I use act-one (runway)?

AI-assisted filmmaking and animation. Ads requiring character dialogue. Performance capture without mocap rigs.

What are the most common mistakes with act-one (runway)?

Trying to retarget faces with extreme rotation — degrades quickly. Cropping too tight — Act-One needs context to retarget convincingly.

Diffusion model — A diffusion model is a generative neural network that creates images, video, or audio by iteratively denoising random noise toward a learned target distribution.
Voice cloning — Voice cloning takes a sample of someone speaking — sometimes as little as 30 seconds — and produces a model that can synthesise new speech in that voice.

Last updated: 2026-06-01. Raw markdown: https://promtable.com/glossary/act-one.md.