gen‑ai.news
← Back
Multimodal

Introducing Runway Media Router

Introducing Runway Media Router

Runway has launched Media Router, a new layer within its Runway Dev platform designed to automatically select the best generative model for a given media task. The system draws on preference optimization - a technique that aligns model selection with quality and suitability signals - to route requests rather than leaving that decision to the developer or end user.

The core idea behind a router in this context is that no single generative model consistently outperforms others across every type of task. Different models have different strengths depending on the content, style, or format being generated. By sitting between the application layer and the underlying models, Media Router aims to improve output quality without requiring developers to manually manage which model handles which request.

Runway Dev is the company's developer-facing platform, providing API access to Runway's suite of generative video and image tools. Media Router extends that infrastructure by adding an intelligent dispatch layer, which means teams building on top of Runway can potentially benefit from better results across varied prompts and use cases without restructuring their integrations.

The introduction of preference-optimized routing to generative media reflects a broader pattern seen in large language model infrastructure, where similar routing approaches have been used to balance cost, speed, and quality. Applying that concept to visual media generation is a notable step, given the added complexity of evaluating image and video outputs. How well the system performs across diverse real-world production workloads will be something developers on the platform will be watching closely.

Enjoy this story? Get the next one in your inbox.

Twice a week: the most important stories in generative image and video AI, distilled into a 2-minute read.

Free. Unsubscribe any time. No spam, ever.

Your next read

What Is MAX Sneaks? Your First Look at Tools That Don’t Exist Yet
Multimodal

What Is MAX Sneaks? Your First Look at Tools That Don’t Exist Yet

Adobe MAX Sneaks is an annual event where Adobe researchers demo experimental technology that has not yet made it into any product. Some of these demos eventually become familiar tools in Premiere, After Effects, or Photoshop - others never ship at all. This year's Sneaks airs Wednesday, November 11, and is free to watch online.

Adobe’s AI experiments let you walk around in photos and interview your characters
Multimodal

Adobe’s AI experiments let you walk around in photos and interview your characters

Adobe's annual Max conference has brought a fresh batch of experimental features, including tools that convert flat photos into navigable 3D scenes, let creators shape AI characters through conversation, and simplify photo editing to a copy-and-paste workflow. These "Sneaks" projects offer a glimpse into where Adobe's generative AI research is heading. None are shipping products yet, but they reflect the direction of the company's broader creative toolset.

Tom Hanks Played Five Characters in This 2004 Christmas Movie
Multimodal

Tom Hanks Played Five Characters in This 2004 Christmas Movie

The Polar Express, Robert Zemeckis's 2004 performance-capture film, is back in seasonal rotation - and it remains one of the more technically unusual productions of its era. Tom Hanks played five distinct characters across 38 days of work, a casting choice that was rooted in story logic as much as technical curiosity. Here is a closer look at how that decision came together and what it meant for the actors involved.