OpenAI’s Generative Video Tech Is Described as ‘Eye-Popping’

OpenAI has debuted a generative video model called Sora that could be a game changer. In OpenAI’s demonstration clips, Sora depicts both fantasy and natural scenes with photorealistic intensity that makes the images appear to be photographed. Although Sora is said to be currently limited to one-minute clips, it is only a matter of time until that expands, which suggests the technology could have a significant impact on all aspects of production — from entertainment to advertising to education. Concerned about Sora’s disinformation potential, OpenAI is proceeding cautiously, and initially making it available only to a select group to help it troubleshoot. Continue reading OpenAI’s Generative Video Tech Is Described as ‘Eye-Popping’

Apple’s Keyframer AI Tool Uses LLMs to Prototype Animation

Apple has taken a novel approach to animation with Keyframer, using large language models to add motion to static images through natural language prompts. “The application of LLMs to animation is underexplored,” Apple researchers say in a paper that describes Keyframer as an “animation prototyping tool.” Based on input from animators and engineers, Keyframer lets users refine their work through “a combination of prompting and direct editing,” the paper explains. The LLM can generate CSS animation code. Users can also use natural language to request design variations. Continue reading Apple’s Keyframer AI Tool Uses LLMs to Prototype Animation

CES: Voiseed Upgrades Its Platform for Expressive AI Voices

Milano-based Voiseed demonstrated its web-based Revoiceit platform at CES, pitched as the best way to manage synthetic voice actors, particularly ensuring that synthetic voices present realistic emotions. The company describes it as a cloud-based solution that uses “generative AI to infuse virtual voices with human emotions and prosody, creating highly expressive, lifelike audio experiences.” While Revoiceit’s most obvious feature is its Studio (imagine Adobe Audition devoted to second-by-second management of voices), it may well be the product’s forthcoming API that provides real value to developers of entertaining technology products. Continue reading CES: Voiseed Upgrades Its Platform for Expressive AI Voices

Meta Touts Its Emu Foundational Model for Video and Editing

Having made the leap from image generation to video generation over the course of a few months in 2022, Meta Platforms introduces Emu, its first visual foundational model, along with Emu Video and Emu Edit, positioned as milestones in the trek to AI moviemaking. Emu uses just two diffusion models to generate 512×512 four-second long videos at 16 frames per second, Meta said, comparing that to 2022’s Make-A-Video, which requires a “cascade” of five models. Internal research found Emu video generations were “strongly preferred” over the Make-A-Video model based on quality (96 percent) and prompt fidelity (85 percent). Continue reading Meta Touts Its Emu Foundational Model for Video and Editing

Nielsen: June Marks a New All-Time Record for TV Streaming

Streaming accounted for 37.7 percent of overall U.S. TV usage in June, a record share for the digital format. Cable TV accounted for 30.6 percent and broadcast 20.8 percent, according to Nielsen’s monthly snapshot The Gauge. TV viewing was up 2.2 percent in June, the first monthly increase since January. The uptick was principally attributed to young viewers and the summer break. Notably, TV consumption among the 2-11 and 12-17 age groups was up 16.3 percent and 24.1 percent, respectively, compared with May. Alternative viewing options — including streaming and video gaming — accounted for 90 percent among those groups. Continue reading Nielsen: June Marks a New All-Time Record for TV Streaming

Netflix Shutters Cheapest Streaming Plan Without Advertising

Netflix is marshalling resources around its ad-supported Standard plan, pulling the plug on ad-free Basic in an effort to drive more eyeballs to the service’s sponsored tier. The $9.99 per month Basic plan is no longer available “for new or rejoining members” in the U.S. and UK and was dropped in Canada last month. Existing Basic subs can continue the plan until they decide to change tiers or cancel. Standard with Ads has since its November launch accrued more than 5 million subs, according to Netflix, which says 25 percent of new sign-ups have chosen that package. Continue reading Netflix Shutters Cheapest Streaming Plan Without Advertising

ETC Releases Section 3 of Its Virtual Production White Paper

The Entertainment Technology Center@USC has released the third installment of its case study, “Fathead: Virtual Production & Beyond.” Section 3 of the four-part white paper is “State of the Industry: Beyond Trends,” which discusses “where we’re at, and where we’re going” and features compelling interviews with thought leaders from companies including The Third Floor, Stargate Studios, Orbital Virtual Studios, Vū Technologies, Lux Machina, nDisplay, Epic Games and Unity Technologies. Click here to access Section 3 and we’ll post announcements when the final section — “Fathead: A Proof-of-Concept Short Film” — becomes available. Continue reading ETC Releases Section 3 of Its Virtual Production White Paper

Vimeo Says Its AI Makes Video as Easy to Edit as Word Docs

Vimeo is leveraging artificial intelligence to automate video editing, and says its new AI suite of tools enables the creation of “a fully produced video in minutes by generating scripts from text prompts, recording videos in one take, and editing content as easily as a Word doc,” the company claims. Features include recording using a built-in screen teleprompter and the ability to quickly delete unwanted filler words (“ums” and “uhs”) and long pauses. The video hosting and sharing platform is rolling out the AI tools in July as part of the $20 per month standard subscription. Continue reading Vimeo Says Its AI Makes Video as Easy to Edit as Word Docs

New Tool from Epic Simplifies High-Fidelity Facial Animation

Epic Games is releasing MetaHuman Animator, which lets developers create nuanced facial animation by capturing an actor’s performance using an iPhone or stereo head-mounted camera system and a PC. The system eliminates the need for manual touch-ups, according to Epic, capturing “every subtle expression, look, and emotion” and replicating it onto a digital character for a faster performance capture workflow that allows more creative control. The new feature set uses a 4D solver to combine video and depth data with a MetaHuman representation of the performer. The animation is produced locally using GPU hardware, providing final results in “minutes.” Continue reading New Tool from Epic Simplifies High-Fidelity Facial Animation

Thought Leaders Analyze AI at ETC Synthetic Media Summit

Entertainment and communications leaders explored the impact of artificial intelligence and anticipated the larger changes ahead at the inaugural Synthetic Media Summit, presented by the Entertainment Technology Center at USC in partnership with NAB Amplify, SMPTE and sponsor Wizeline, in conjunction with the USC School of Cinematic Arts and USC Annenberg School for Communication and Journalism. Speakers addressed how new technology will make VFX cheaper and faster for studios, while for indies it will open new frontiers. Teaming AI with tools such as Unreal Engine is expected to level the playing field and launch a new era of virtual production. Continue reading Thought Leaders Analyze AI at ETC Synthetic Media Summit

Runway Makes Next Advance in Consumer Text-to-Video AI

Google-backed AI startup Runway has released Gen-2, an early entry among commercially available text-to-video models. Previously waitlisted in limited release, the commercial availability is impactful, since text-to-video is predicted as the next big bump in artificial intelligence, following the explosion of AI use generating text and images. While Runway’s solution may not be ready to serve as a professional video tool, this is the next step in development of tech expected to impact media and entertainment. Filmmaker Joe Russo recently predicted that within the next two years, AI may have the ability to create feature films. Continue reading Runway Makes Next Advance in Consumer Text-to-Video AI

Roll Uses Generative AI to Simulate Jibs, Dollies, Much More

Roll, a new app for web and iOS, puts an AI spin on timeworn video capture and editing techniques, delivering virtual bokeh, motion graphics and multicam shots, as well as sliders, cranes, dollies and jibs. As the latest consumer artificial intelligence entry, Roll professes to empower anyone to create professional-quality remote video quickly using just an iPhone and Roll’s proprietary software. The Roll app is free to use, with the whole platform offered as a free trial with a paid subscription option. Roll lets users record broadcast-quality remote video calls, add generative AI special effects, and publish quickly. Continue reading Roll Uses Generative AI to Simulate Jibs, Dollies, Much More

HUSSLUP Aims to Become Entertainment Industry’s LinkedIn

Hollywood talent discovery platform HUSSLUP debuted its desktop app this week, staking its claim as the LinkedIn of the entertainment community. With backing from Comcast NBCUniversal’s LIFT Labs accelerator and various venture funds, the job search and networking hub aims to help young professionals who want to break into the world of production for film, television and games. The company launched as a mobile app in December, when it announced a $2.5 million seed round and 4,000 job-seeking members. HUSSLUP has separate logins for creative professionals and entertainment companies, offering functionality catering to each. Continue reading HUSSLUP Aims to Become Entertainment Industry’s LinkedIn

Netflix-Approved Camera List Has Expanded to 51 Models

Netflix has the largest global audience of any paid streaming service and produces the most original content, optimum position to recommend camera specs and photographic best practices. Netflix requires that at least 90 percent of a program’s content be captured using hardware from its “approved camera list,” which currently includes 51 models from seven manufacturers. There are some exceptions, mainly for documentaries. But the care the company takes in vetting the list — with input from creatives, camera manufacturers and global experts — makes the five-year-old tradition respected guidance for video professionals. Continue reading Netflix-Approved Camera List Has Expanded to 51 Models

AMPAS Diversifies with a Production and Technology Branch

The Academy of Motion Picture Arts and Sciences has formed a Production and Technology Branch to include about 400 individuals previously classified as members-at-large. The branch “represents members working in key technical and production positions in all phases of filmmaking, from pre- to post-production,” AMPAS says, listing chief technology officers, senior department heads in tech and creative services, and preservation and restoration specialists as among the inductees. In addition, credited production roles — including stunt coordinators, script supervisors, choreographers, music supervisors, colorists, line producers and associate producers — will be part of the branch. Continue reading AMPAS Diversifies with a Production and Technology Branch