Runway has introduced a new video generation model, launching a next phase of competition that could transform film production. Notably, its Gen-4 system improves the consistency of characters, locations and objects across multiple scenes, an elusive prospect for most AI video generators. The New York-based startup calls its new development “a step towards Universal Generative Models that understand the world.” The key, Runway says, is to provide a single reference image of the character, item or environment as part of the model’s project material. Runway Gen-4 can generate 5- and 10-second clips at 720p resolution. Continue reading Runway Gen-4 Tackles AI’s Elusive Video Scene Consistency

During Nvidia’s GTC AI Conference in San Jose earlier this month, VP and GM of Media & Entertainment Richard Kerris presented the Nvidia Media2 initiative that builds on the company’s Blackwell GPU foundation to enable real-time AI solutions for all aspects of media production workflows. His talk showcased a broad range of generative AI breakthroughs in real-time ray tracing and VFX, video search and summarization, and musically-based sound effects (SFX). Kerris also shared insights on the media industry’s reception to AI thus far and humbly implored the audience to consider using such technology as an effective new tool for storytelling. Continue reading Nvidia Forges AI Initiative to Streamline Production Workflows

Netflix revealed plans to boost its 2025 original programming expenditure to $18 billion, a more than 10 percent increase over 2024, which could place pressure on other streaming services. Additionally, the company notes that this spending plan does not represent its cap by any means. In the wake of this news, Netflix co-CEO Ted Sarandos joined Mexican President Claudia Sheinbaum to unveil a plan to spend $1 billion producing content over the next four years south of the border. The company will also invest $2 million upgrading Mexico City’s Churubusco Studios, its new home base there. Continue reading Netflix Spending $18B on Originals, Commits $1B to Mexico

Staircase Studios AI — the film, television and gaming studio launched by “Divergent” franchise producer Pouya Shahbazian — has announced its investors and shared plans to produce more than 30 projects at budgets under $500,000 over the next 3-4 years. The company will be using a proprietary AI workflow it invented called ForwardMotion that the company says will revolutionize film and television production. The company has acquired multiple pieces of IP, including more than 20 scripts that have appeared on the Black List, which tallies the most popular unproduced scripts. Continue reading Staircase Studios AI Plans 30 Projects Over Next 3 to 4 Years

ByteDance has developed a generative model that can use a single photo to generate photorealistic video of humans in motion. Called OmniHuman-1, the multimodal system supports various visual and audio styles and can generate people doing things like singing, dancing, speaking and moving in a natural fashion. ByteDance says its new technology clears hurdles that hinder existing human-generators — obstacles like short play times and over-reliance on high-quality training data. The diffusion transformer-based OmniHuman addressed those challenges by mixing motion-related conditions into the training phase, a solution ByteDance researchers claim is new. Continue reading ByteDance’s AI Model Can Generate Video from Single Image

Sony has launched XYN, a platform for the creation and display of spatial content. Pronounced “zin,” XYN is an integrated software and hardware solution that “accurately captures real-world objects, human motion, and backgrounds, recreating them in virtual environments for 3D computer graphics production,” according to Sony. In addition to the XYN Motion Studio, at CES 2025 this month the company shared prototypes for a XYN spatial capture solution and a XYN headset equipped with 4K OLED micro displays and video see-through function that Sony says is intended for production purposes. Continue reading CES: Sony Bows Production Tools for Metaverse, Digital Twins

The Canon Americas Lab exhibit at CES this year featured a demonstration of Canon USA’s Volumetric X Motion Capture system that creates videos viewable from any camera angle. The multi-camera system leverages 2D data, 3D volumetric data, and analytical tools for sports and entertainment applications. The basis of the system is the same as the Free Viewpoint video system — Canon’s CES 2023 headliner — which was used in an NBA pilot for Cleveland Cavaliers’ alternative game stream. We checked in with the project’s researchers for updates, including ESPN highlights on Meta’s Xtadium VR app, a new U.S. volumetric studio, and how AI was used in this technology. Continue reading CES: Canon Updates Its Volumetric X Motion Capture System

CES’s Eureka Park is a section of exhibits where startups and early-stage products from all over the world solicit feedback and explore opportunities. From this year’s Italian delegates at Eureka Park, our team found EYE2DRIVE, a semiconductor company that develops CMOS chips for digital imaging inspired by the human eye. Their image sensors use AI to mimic the human eye’s ability to adapt its response to changing environmental light conditions. As a result, quality and color of the captured image remains unaffected. While currently focusing on autonomous navigation applications, the tech has potential for media production as well. Continue reading CES: Image Sensors Adapt to Light Changes Like Human Eye

6P Color, the color science technology company that innovated the multi-primary color system, recently pivoted its focus to provide color management tools for display manufacturers to reproduce colors the way they are intended at the source. The new C-suite leadership brought in four months ago is transitioning the company to this new direction. During CES, the ETC team met with 6P Color CTO Matthew Brantley; Board Member Steven Poster, ASC; and Lead Product Manager Kennen Dietz. They explained their tech could deliver immediate improvements by addressing the shortcoming in current displays of not fully representing the color space of an image source in the displays’ native gamuts. Continue reading CES: 6P Color Pivots to Provide New Color Management Tools

Fitting for a trade show long associated with the latest and greatest television sets, this year’s CES featured a panel titled “The Future of Immersive TV.” The panelists, led by moderator Rick Kowalski, senior director of business intelligence for the Consumer Technology Association (CTA), underscored the biggest current challenge for home entertainment is the fragmentation of platforms on which consumers view content. Multimodal content delivery is impacting production workflows and advertising services. From trends in consumer behavior to emerging technologies, the panel speculated about interactive TV, shoppable TV, and the need for consistent experiences. Continue reading CES: TV Industry Adapts to Expansion of Platforms and Devices

When walking through the Japanese exhibits at CES 2025, it was difficult to miss the huge black spherical drone aircraft HAGAMOSphere that was prominently positioned as if demanding the passerby’s respect. And respect it deserved, for this drone prototype was one of this year’s CES Innovation Award recipients recognized for outstanding design and engineering in consumer technology. HAGAMOSphere’s innovation is its distinct ability to move both horizontally and vertically without tilting the aircraft. If the HAGAMOSphere is outfitted with a suitable camera, jerky movements in captured drone footage could potentially be eliminated or mitigated. Continue reading CES: Spherical Drone Design Could Benefit Media Production

In the never-ending smorgasbord of AI hype, “agents” represent practical and worthwhile potential. AI agents are autonomous AI programs that can understand some context and take action in that context. Agents can autonomously perform a task that involves mapping a goal to its context and parameters (even if they’re not explicitly laid out), process data across multiple formats and ontologies to understand the goal and work through the task, call multiple functions across multiple apps, and take some action to achieve the goal. Unfortunately, however, while many are talking about AI agents, few are promoting actual products at CES. Continue reading CES: Show Features a Surprisingly Small Number of AI Agents

The Eureka Park section at CES 2025 in Las Vegas is an exhibition area dedicated to thousands of startups and early-stage products from across the globe. Our reporting team visited the space organized specifically for Japanese startups and discovered a few that are developing innovative technologies that could potentially be applied to 3D computer graphics modeling, XR, and gaming. Among the standouts were Tokyo-based CalTa that developed the digital twin platform Trancity — and Japanese telecom giant NTT Docomo’s exhibit of its ongoing Feel Tech system. Continue reading CES: Japanese Startups Showcase 3D Modeling, XR, Gaming

CES 2025 kicked off appropriately with a high-powered panel on AI’s impact in entertainment. Under the expert moderation of our friend, and former president of the Hollywood Professional Association, Seth Hallen, three of the industry’s most senior leaders spoke candidly about what the technology means to the industry: Samira Panah Bakhtiar (GM of Media and Entertainment, Games, and Sports at Amazon Web Services), Academy Award-winner Ed Ulbrich (Chief Content Officer and President of Production at Metaphysic), and Richard Kerris (GM of Media and Entertainment at Nvidia). Continue reading CES: Industry Leaders Highlight Transformative Potential of AI

Promise is a new entertainment studio launched around the potential of generative AI. The Los Angeles-based startup is developing a multiyear slate of films, TV shows and media in “new formats.” With funding led by Peter Chernin’s North Road Company and Andreessen Horowitz, Promise vows to set “a new standard for high-quality storytelling enabled by AI.” The firm is also working on new tools to optimize the generative workflow. The first product, MUSE, “integrates the latest GenAI technology throughout the creative process in a streamlined, collaborative, and secure production environment.” Continue reading Promise Is an Entertainment Studio Built Around Generative AI