AI, virtual production, and creative technology — reported daily.
On the Denoised podcast, we weigh custom post-trained video models against general models that keep getting more capable, starting with Ben Affleck's account of how InterPositive built its models before Netflix bought…
Jeffrey Katzenberg wants Hollywood to stop resisting AI and start shaping it, and on the Denoised podcast we ask whether the executive behind Shrek should build a studio or sell tools. We also break down how Opus 5.5…
Runway Labs is testing responsive generative video interfaces that create a new scene composition when the viewing window changes size. The experiments show how real-time generation could let creative teams explore pr…
ChatGPT Images 2.5 launches with stronger reference preservation and iterative editing, alongside separate GPT-Image-2.5 Flare and Sunburst API models. Flare prioritizes speed and volume, while Sunburst trades longer…
Qwen Image 2.1 launched as an open-weight image model that combines image generation and editing with native RGBA output, subject extraction, and transparent-layer revisions. Native alpha channels could reduce the mas…
Filmmakers we met at TIFF often heard “AI” and pictured fully synthetic video with little creative control. We unpacked that disconnect, tested ChatGPT Image 2.5, explored TypeSafe’s Jev model, and examined generative…
Ruby takes a finished SDR clip and converts it up to 16-bit HDR, exporting ProRes files and EXR sequences instead of a flat 8-bit master. Runway says the model, announced on X, works on any uploaded video or generated…
Atlas turns footage from a few ordinary cameras into a space-time capture that can freeze action and generate new viewpoints after filming. In its Atlas launch post, World Labs says the model reconstructs spatial stru…
Adobe announced a generative media tool for Premiere that lets editors select a gap in the timeline, describe the video or audio they need, and generate a clip the company says fits the surrounding shots. The same ann…
Goldenrod launched a real-time financial platform that categorizes a production's qualified spend as it lands and packages the final rebate submission for state film commissions, with coverage live in Texas, Louisiana…
Universal Music Group has licensed its artist catalog to ElevenLabs to build an AI-powered music platform where fans can remix and mash up official tracks and generate new interpretations of them. The licensing agreem…
AFM's 2026 Market gains a dedicated 15,000-square-foot venue, The AFM House, that puts its AI and technology programming and a new theatrical-exhibition track under one roof for every registered badge holder. The indo…
The platform where AI filmmakers find, fine-tune, and deploy open image and video models is set to change hands. Nvidia has agreed to buy Hugging Face for $12.9 billion, according to The Information, and neither compa…
Matriarch, the self-funded Los Angeles studio from Verena Puhm, is developing its own audience-response technology alongside its film and series slate rather than adding it to a traditional studio later. Puhm told Dea…
Chris Nichols captured a crumbling, abandoned house in Northern California's Gold Rush country on an Alexa 35, rebuilt it as a relightable Gaussian splat, added a second story it never had, and set the whole thing on…
Volinga has added 4D Gaussian Splatting support to its Unreal Engine workflow, letting animated splat captures play back in real time inside the engine.
The American Society of Cinematographers is releasing StEM3-VP , a set of open reference assets built to evaluate and calibrate in-camera visual effects stages, and the material is joining the Ac
Orbital Studios has relocated its headquarters and research lab to Television City, the 73-year-old former CBS lot in the Fairfax District of Los Angeles. The virtual product
Epic Games has added native Model Context Protocol (MCP) support to Unreal Engine 5.8, letting external AI agents operate the Unreal Editor directly. According to Epic's documentation , the
NVIDIA is positioning DGX Station as the local hardware base for an open agent stack that can run large models, govern their behavior, and call simulation tools inside Blender. Announced at SIGGRAPH , the
Canon announced the EOS R6 V , the first full-frame body in its video-focused EOS V series. The camera pairs a 32.5MP sensor with 7K Open Gate capture, built-in ac
Sony announced the Alpha 7R VI , the sixth generation of its high-resolution full-frame mirrorless line. The camera moves the R series onto a 66.8MP fully-stacked back-illu
Arc Eye's Modular Mobile Stand Collapses the Dome Scanner Into a Flat-Pack Rig May 07, 2026 Arc Eye CEO Christian Cicerone walked us through the company's new modular mobile capture rig at NAB, a battery-powered alternative to the company's large dome scanner that bre
iodyne is building storage hardware designed to bring the security, performance, and reliability of data center infrastructure to fast-moving production environments. At NAB 2026, the com
DiffHDR, a research framework from Texas A&M University, Eyeline Labs, and Netflix, converts ordinary 8-bit low dynamic range video into HDR by generating plausible radiance in regions the original footage blew out or…
The Visual Effects Society held the first edition of its Women Who Lead Summit, a sold-out half-day program of two keynotes and two panels on leadership, equity, career advancement, and technology in visual effects. T…
Blackmagic Design released DaVinci Resolve 21.1, a free update that connects AI assistants including Claude, Claude Code, and ChatGPT Codex to the editing application so editors can direct post-production work with pl…
Maxon is showing a first look at features planned for October across its Maxon One lineup, led by AI-powered relighting in Red Giant and procedural fur in Redshift. The preview of upcoming updates sits alongside capab…
Beeble launched SwitchX 2.0, an update to its video-to-video model that generates at native 4K in 10-bit color and handles shots up to 20 seconds. That pushes the tool past its 1080p output to finishing-length sequenc…
We toured NantStudios' El Segundo campus to see the Dynamic Volume System, an LED volume that trades one fixed wall for modular "wall pods" that snap into different shapes. The stage can become a long arc, a tight cur…
A Yoruba-language sci-fi feature reached completion using AI for roughly 80% of its visuals, with human direction and live-action performance covering the rest. The result is a finished, more-than-three-hour hybrid-AI…
Michael Caine's Licensed AI Voice Narrates ElevenLabs' 13-Hour 'Odyssey' Audiobook June 23, 2026 ElevenLabs has released a roughly 13-hour AI-generated audiobook of Homer's The Odyssey through its ElevenReader app, narrated by a licensed AI replica of Michael
Inside Door G's Brand-First Virtual Production Pipeline: AI in Pre and Post, Not on the Wall May 13, 2026 A virtual production studio that doubles as an AI workflow shop is pitching brands on the idea that a shoot should leave behind a reusable digital asset, not a torn-down
Aronofsky-Produced AI Hybrid Short 'Goodnight, Lamby' Premieres at Cannes Classics May 16, 2026 Goodnight, Lamby , a live-action and animation hybrid short film produced by Darren Aronofsky's Primordial Soup and built in part with Google DeepMind's generative AI t
Ellenor Argyropoulos says she used to get death threats over her AI filmmaking. She says the reaction has flipped in the space of about a year and a half, and now studios and well-known directors are the ones who brin…
Caroline Ingeborn thinks the AI industry sold creatives the wrong idea when it pushed them to become prompt engineers. The chief operating officer of Luma argues that skilled filmmakers should talk to an agent the way…
Christy Anzelmo says AI has reversed the way visual effects artists work. Instead of building an image step by step and refining as they go, compositors now start from the result they want and trace back to the data o…
AI models can take an image, generate an audio track, cut it into a video, and lip-sync a character in one automated pass. What they still can't do, according to Justine Moore, is judge whether any of it is good.
Background animators become lead animators. First-year lawyers become partners. Production assistants become producers. But if AI eliminates those entry-leve
GPT-6 Astra can take a one-line goal and reconstruct a real city in Blender, building the street grid and individual structures without a single reference file handed to it. We pointed it at downtown Miami, let Codex…
World models had their biggest showing yet on this episode, and Atlas from World Labs is the one we kept rewinding. Feed it a few phones shooting ordinary video and it rebuilds the scene into a 3D space you can freeze…
On the Denoised podcast, we look at how far AI video has moved into live, interactive territory, and why audiences keep falling for synthetic movie magic. We put Lucy 2.5 through a live webcam test, debate how MiniMax…
