runway

Runway has released GWM Worlds 2, an interactive world model with real-time control capabilities, enabling the generation of 720p/24fps video and 48kHz audio on the fly. It allows users to manipulate the environment via text commands and integrate agents for task execution.

Runway announces that its enterprise business has more than doubled over the past year, with net revenue retention exceeding 300%, and discusses the commoditization of generative video models while emphasizing enterprise-focused features.

Runway shares a video highlighting the capabilities of current state-of-the-art image generation models and tooling.

Runway launched Media Router, a preference-optimized router that automatically selects the best video, image, or audio model based on user-defined criteria for cost, quality, or latency, eliminating manual model picking. It is live now in Runway Dev.

Runway launched the Media Router, a tool that automatically selects the best generative media model for a given request based on quality, speed, or cost preferences. It aims to simplify integration for developers amid a crowded generative media landscape.

A 21-year-old used AI tools like Claude, Midjourney, Runway, ElevenLabs, and Suno to produce one episode of animation for only $124 and 1 hour, earning $12,345, showcasing the high-return, low-cost potential of AI content creation.

User tested character consistency across five AI video generation models (Kling 3.0, Runway Gen-4.5, Veo 3.1, Seedance 2.0, Pika) using same prompt and reference image, finding Seedance 2.0 best (8/10) and Pika worst (3/10).

Users discuss their preferred alternatives to OpenAI's Sora after its shutdown, with Seedance 2.0 emerging as a popular replacement.

Runway, originally focused on AI tools for filmmakers, is now pivoting to building world models from video data, aiming to rival Google and other AI leaders. The company believes video-based intelligence will surpass language models as the next frontier of AI.

Runway Agent allows users to generate edited, sound-designed videos via chat, streamlining video production through natural language interaction.