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

Los Angeles-based AI startup Moonvalley has released a video generator purpose-built for entertainment and advertising. Called Marey, its creators say it was designed with the “specifications and tastes” of filmmakers and studios in mind and trained exclusively on owned or fully licensed source data to protect users from lawsuits. Asteria, a partner in the venture, owns a large documentary library through its subsidiary XTR. Its founders say Marey aims to usher in “a new era of GenAI video built to empower — not replace — the creative forces behind modern motion pictures.” Continue reading Moonvalley and Asteria Unveil Cinematic GenVid Model Marey

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

Microsoft has unveiled a new AI model called Muse that can generate game visuals and controller actions and understands 3D space. The new model can create complex gameplay sequences with accurate physics and character behaviors. Classified by Microsoft as the first World and Human Action Model (WHAM), Muse was trained from over seven years’ worth of human gameplay data from the Xbox game “Bleeding Edge,” published by UK-based Microsoft Games subsidiary Ninja Theory. Muse can, in addition to game goals, provide research insights to support all sorts of creative use of generative AI, Microsoft says. Continue reading Muse Could Be a Gamechanger for Xbox Players, Developers

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

The National Hockey League is testing an animated recap show aimed at drawing young viewers. “NHL Hockeyverse Matchup of the Week” uses NHL Edge Positional Data to turn NHL player into avatars, creating “a visualization of the on-ice action with stunning realism and dynamic movements,” the league says. The half-hour show premiered February 1 featuring a recap of a January 25 game between the Vancouver Canucks and Washington Capitals. Episodes air on the NHL Network and on the NHL YouTube channel in the U.S. and on Sportsnet in Canada and are expected to continue in the Saturday slot. Continue reading NHL Is Turning Players into Avatars in Game Recaps for Kids

Sony has debuted a full-body Mocopi mobile motion capture system as part of the ecosystem to support its new extended reality brand XYN (pronounced “zin”), also launched at CES 2025 in Las Vegas. The Mocopi Pro Kit for the new professional mode of Mocopi is available as a PC app and as the XYN Motion Studio app. The apps provide capture and editing functions, while each Pro Kit includes two sets of six lightweight Mocopi sensors, two newly announced Sensor data receivers and an additional set of Sensor bands. The new professional mode expands coverage by connecting 12 Mocopi sensors. Continue reading CES: Sony Mocopi Adds Full-Body Pro Kits for PC, XR Mocap

World Labs, the AI startup co-founded by Stanford AI pioneer Fei-Fei Li, has debuted a “spatial intelligence” system that can generate 3D worlds from a single image. Although the output is not photorealistic, the tech could be a breakthrough for animation companies and video game developers. Deploying what it calls Large World Models (LWMs), World Labs is focused on transforming 2D images into turnkey 3D environments with which users can interact. Observers say that reciprocity is what sets World Labs’ technology apart from offerings by other AI companies that transform 2D to 3D. Continue reading World Labs AI Lets Users Create 3D Worlds from Single Photo

Wonder Animation is the latest tool from Wonder Dynamics, the AI startup founded by actor Tye Sheridan and VFX artist Nikola Todorovic in 2017 that Autodesk purchased in May. Now in beta, Wonder Animation can automatically transpose live-action footage into stylized 3D animation. Creators can shoot using any camera, on any set or location, and easily convert to 3D CGI. Matching the camera position and movement to the characters and environment, Wonder Animation lets you film using any camera system and lenses, edit those shots using Maya, Blender or Unreal, and then reconstruct the result as 3D animation using AI. Continue reading Autodesk’s AI Tool Turns Live-Action Video into 3D Animation

Runway is launching Act-One motion capture system that uses video and voice recordings to map human facial expressions onto characters using the company’s latest model, Gen-3 Alpha. Runway calls it “a significant step forward in using generative models for expressive live action and animated content.” Compared to past facial capture techniques — which typically require complex rigging — Act-One is driven directly and only by the performance of an actor, requiring “no extra equipment,” making it more likely to capture and preserve an authentic, nuanced performance, according to the company. Continue reading Runway’s Act-One Facial Capture Could Be a ‘Game Changer’

Adobe has launched a public beta of its Generate Video app, part of the Firefly Video model, which users can try for free on a dedicated website. Login is required, and there is still a waitlist for unfettered access, but the Web app facilitates up to five seconds of video generation using text and image prompts. It can turn 2D pictures into 3D animation and is also capable of producing video with dynamic text.  The company has also added an AI feature called “Extend Video” to Premiere Pro to lengthen existing footage by two seconds. The news has the media lauding Adobe for beating OpenAI’s Sora and Google’s Veo to market. Continue reading Adobe Promos AI in Premiere Pro, ‘Generate Video’ and More

Meta is rolling out new generative AI advertising tools for video creation on Facebook and Instagram. The expansion to the Advantage+ creative ad suite will become widely available to advertisers in early 2025. The announcement, made at Advertising Week in New York last week, was positioned as a way for marketers to improve campaign performance on Meta’s social platforms. The new tools will allow brands to convert static images into video ads. The company also announced a new full screen video tab for Facebook that feeds short-form Reels with long-form and live-stream content. Continue reading Meta Announces New GenAI Video Tools at Advertising Week

A newly redesigned Snapchat experience is built around a three-tab user interface called Simple Snapchat. As part of that effort, the social platform is launching more generative video features, including text-to-video as part of the app’s Lens Studio AR authoring tool. Easy Lens allows the quick generation of Lenses by typing text prompts, making it possible to do things like experiment with Halloween costumes or explore looks for back to school. Launching in beta for select creators, Snap says the new features are designed for all ability levels. The company is also updating its GenAI Suite and adding an Animation Library of “hundreds of high-quality movements.” Continue reading Snapchat Is Getting a Redesign and Generative Text-to-Video

Canadian generative video startup Viggle AI, which specializes in character motion, has raised $19 million in Series A funding. Viggle was founded in 2022 on the premise of providing a simplified process “to create lifelike animations using simple text-to-video or image-to-video prompts.” The result has been robust adoption among meme creators, with many viral videos circulating among social media platforms powered by Viggle, including one featuring Joaquin Phoenix as the Joker mimicking the movements of rapper Lil Yachty. Viggle’s Discord community has four million members including “both novice and experienced animators,” according to the company. Continue reading Viggle AI Raises $19 Million on the Power of Memes and More

The world’s first AI-powered movie camera has surfaced. Still in development, it aims to enable filmmakers to turn footage into AI imagery in real time while shooting. Called the CMR-M1, for camera model 1, it is the product of creative tech agency SpecialGuestX and media firm 1stAveMachine, with the goal of providing creatives with a familiar interface for AI imagemaking. It was inspired by the Cine-Kodak device, the first portable 16mm camera. “We designed a camera that serves as a physical interface to AI models,” said Miguel Espada, co-founder and executive creative technologist at SpecialGuestX, a company that does not think directors will use AI sitting at a keyboard. Continue reading New Prototype Is the World’s First AI-Powered Movie Camera