Companies GUIDE
Runway
Runway develops generative video tools and research systems.
Listen to this guideAI-narrated · ~1 min
On this page1 min read
Overview
Its Gen-1 and Gen-2 products are historical model generations; Runway’s current research also describes general world models for interactive environment simulation.
Deep Dive
Runway introduced Gen-1 for video-to-video and Gen-2 for text-to-video/image-to-video tasks. Its archived Motion Brush feature gave localized motion control but was specific to Gen-2, which Runway deprecated in 2025. Runway’s general world-model research describes a distinct goal: represent environments and simulate future events, with GWM Worlds 2 conditioned on prompts, current controls and prior frames. Research claims are scoped to the methods and evaluations described by Runway.
Real-World Implementation
Gen-1 was described as video-to-video transformation using text or image guidance.
Gen-2 was introduced for text-to-video and image-to-video generation; its legacy Motion Brush feature is now deprecated.
Motion Brush historically let users indicate regions and directions for motion in Gen-2 clips.
Runway’s GWM research studies interactive world simulation, including autoregressive frame generation with contextual inputs.
The Future of Runway
When describing Runway, date product generations and check current support status. Distinguish creative video generation from interactive world-model research, and assess any real-world simulation claims against published evaluation. The cited research does not establish that generated environments are physically faithful in every setting.
Putting it into practice
Why it matters
- Vendor strategy. Vendor roadmaps influence what features your team can build next.
- Cost and budget. Commercial terms and deployment options affect long-term cost and risk.
- Risk and safety. Company incentives shape product defaults, safety posture, and openness.
Watch out for
- Launch announcements may outpace stability in real production workflows.
- API pricing or policy shifts can break assumptions overnight.
- Single-vendor dependency increases lock-in and migration costs.
Next steps
- Evaluate providers using your own tasks and datasets.
- Review privacy, security, and legal terms before integration.
- Maintain a fallback plan across models or vendors.
- Monitor release notes so roadmap changes do not surprise teams.
Keep Exploring
Free newsletter
Get the daily AI briefing
Three verified AI stories every weekday morning, written in plain English. Free forever, no ads.
One email each weekday. Unsubscribe in one click. We never sell or share your address.
Test yourself
Take the Runway quiz
Instant feedback on every answer, and a shareable certificate with a verifiable ID once you pass a course.
Support free AI education. AI Understanding is a 501(c)(3) nonprofit — no ads, no paywall, ever. Make a donation
Frequently asked questions
What is Runway?
Runway develops generative video tools and research systems. Its Gen-1 and Gen-2 products are historical model generations; Runway’s current research also describes general world models for interactive environment simulation.
What category of AI tool is Runway primarily known for?
Runway builds generative video tools, including its Gen-series text-to-video and video-to-video models.
Which Runway model first introduced text-to-video generation in its Gen series?
Gen-1 handled video-to-video, while Gen-2 introduced generating video directly from text prompts in 2023.
What is the core technical challenge unique to AI video versus AI images?
Video models must make frames consistent over time so objects move smoothly instead of flickering, a problem images do not have.
What does Runway’s current Gen-2 deprecation page say about Motion Brush?
Runway’s support page says Motion Brush was a Gen-2-specific feature and is not available on newer models; the page describes product status, not the feature’s historical behavior.
What did Gen-2 Motion Brush let a user control in a generated clip?
Runway described Motion Brush as a way to paint regions and specify movement for those areas in Gen-2 image-to-video generation.
Keep learning
Related guides
More guides picked for this topic