AI Usage at a Glance
Jan 1, 2024
ModerationPractice documented: Runway uses an in-house AI visual moderation system that automatically detects and blocks attempts to generate harmful or inappropriate content, including depictions of public figures without consent, and adds invisible C2PA-standard watermarks to every generated output to label it as AI-made.
Practice DocumentedView practice →Jan 1, 2024
Creative GenPractice documented: Runway offers a Generative Audio suite that converts written text into spoken audio using selectable AI voices, allows users to train custom voice models from their own recordings, and can synchronize generated speech to animate the mouth movements of characters in photos or videos (Lip Sync).
Practice DocumentedView practice →Jun 17, 2024
ModerationNew evidence: Runway Research | Runway Gen-3 Alpha: Next-Generation AI Video Generation
Evidence AddedView practice →Jun 17, 2024
Creative GenPractice documented: Runway offers an AI video generation platform that takes text prompts, images, or existing video clips as input and produces short synthetic video clips. The platform's current flagship model, Gen-4.5, is available to all paid subscribers worldwide.
Practice DocumentedView practice →Sep 1, 2024
Creative GenPractice documented: Runway announced a partnership with Lionsgate Entertainment in September 2024 to develop a custom AI video generation model trained on Lionsgate's proprietary catalog of over 20,000 film and television titles, available exclusively to Lionsgate filmmakers and creative talent.
Practice DocumentedView practice →Oct 7, 2024
ModerationNew evidence: Runway Research | Foundations for Safe Generative Media
Evidence AddedView practice →Oct 22, 2024
Creative GenPractice documented: Runway offers Act-One and Act-Two, AI tools that transfer a human actor's facial expressions, mouth movements, and gestures from a simple driving video onto a generated or user-supplied character image. These tools are available to users on Standard plan and higher.
Practice DocumentedView practice →Oct 23, 2024
Creative GenNew evidence: 'This is a game changer': Runway releases new AI facial expression motion capture feature Act-One
Evidence AddedView practice →Nov 21, 2024
ProductivityPractice documented: Runway offers Workflows, a node-based tool that lets users chain together multiple AI models and processing steps — including video generation, audio generation, video upscaling, and image editing — into reusable automated pipelines that can be converted into shareable apps.
Practice DocumentedView practice →Jan 1, 2025
ProductivityNew evidence: Runway | AI Image and Video Generator
Evidence AddedView practice →Mar 31, 2025
Creative GenNew evidence: Runway Research | Runway Gen-4: AI Video Generation with World Consistency
Evidence AddedView practice →Dec 1, 2025
Creative GenNew evidence: Runway Research | Introducing Runway Gen-4.5
Evidence AddedView practice →Dec 11, 2025
OtherPractice documented: Runway announced GWM Robotics in December 2025, an AI model that generates synthetic video training data for robot policy development and enables simulation-based testing of robotic systems, available to robotics firms and enterprises via a Python SDK by request.
Practice DocumentedView practice →Dec 18, 2025
Creative GenNew evidence: Adobe and Runway Partner to Deliver the Next Generation of AI Video for Creators, Studios and Brands
Evidence AddedView practice →Mar 9, 2026
Creative GenPractice documented: Runway deployed Characters in March 2026, a real-time AI system that generates a fully expressive, conversational video avatar from a single reference image, with synchronized lip movements, facial expressions, and gestures, available via the Runway API and web app.
Practice DocumentedView practice →Mar 12, 2026
Creative GenNew evidence: Runway News | Building Interactive AI Characters Responsibly
Evidence AddedView practice →Mar 31, 2026
Creative GenNew evidence: Exclusive: Runway launches $10M fund, Builders program to support early-stage AI startups
Evidence AddedView practice →Runway uses an in-house AI visual moderation system that automatically detects and blocks attempts to generate harmful or inappropriate content, including depictions of public figures without consent, and adds invisible C2PA-standard watermarks to every generated output to label it as AI-made.
Runway's safety page and research publications confirm an in-house visual moderation system trained to classify both AI-generated and real-world images and videos. The system automatically suspends users who repeatedly trigger moderation filters or upload unlawful content. All outputs receive invisible C2PA (Coalition for Content Provenance and Authenticity) watermarks embedded in metadata, enabling downstream platforms to identify the content as AI-generated. Runway also applies bias-mitigation measures to reduce demographic skew in generated content.
Runway offers Act-One and Act-Two, AI tools that transfer a human actor's facial expressions, mouth movements, and gestures from a simple driving video onto a generated or user-supplied character image. These tools are available to users on Standard plan and higher.
Runway offers an AI video generation platform that takes text prompts, images, or existing video clips as input and produces short synthetic video clips. The platform's current flagship model, Gen-4.5, is available to all paid subscribers worldwide.
Runway announced a partnership with Lionsgate Entertainment in September 2024 to develop a custom AI video generation model trained on Lionsgate's proprietary catalog of over 20,000 film and television titles, available exclusively to Lionsgate filmmakers and creative talent.
Runway deployed Characters in March 2026, a real-time AI system that generates a fully expressive, conversational video avatar from a single reference image, with synchronized lip movements, facial expressions, and gestures, available via the Runway API and web app.
Runway offers a Generative Audio suite that converts written text into spoken audio using selectable AI voices, allows users to train custom voice models from their own recordings, and can synchronize generated speech to animate the mouth movements of characters in photos or videos (Lip Sync).
Have evidence about Runway's AI practices? Submit a report.
Submit a report →AI Trace is free and nonprofit. Support our work
Runway offers Act-One and Act-Two, AI tools that transfer a human actor's facial expressions, mouth movements, and gestures from a simple driving video onto a generated or user-supplied character image. These tools are available to users on Standard plan and higher.
Act-One was launched in October 2024 as part of the Gen-3 Alpha platform. It takes a short video of a person performing as input — recorded on any consumer camera — and maps that performance onto a still character image or video, generating an animated clip. Act-Two, the successor, extends this capability to include body gestures and environmental motion. Runway describes the prior industry approach as requiring 'complex, multi-step workflows' including motion capture equipment, multiple footage references, and manual face rigging — but does not explicitly confirm that Runway itself previously employed such a process for its own users.
Runway offers an AI video generation platform that takes text prompts, images, or existing video clips as input and produces short synthetic video clips. The platform's current flagship model, Gen-4.5, is available to all paid subscribers worldwide.
Runway's generative video models have progressed through several generations: Gen-2 (June 2023), Gen-3 Alpha (June 2024), Gen-4 (March 2025), and Gen-4.5 (December 2025). Gen-4.5 supports text-to-video, image-to-video, and video-to-video generation modes, producing clips at up to 720p resolution at 24 fps with optional 4K upscaling on higher-tier plans. The model is also integrated into Adobe Firefly via a multi-year partnership announced in December 2025.
