Denoised

An AI-generated "behind-the-scenes" disaster video hit 750 million views in four days — and most viewers had no idea it was fake. Addy and Joey dig into why it went viral, what it reveals about audience appetite for movie magic, and why the filmmaking ...

Addy and Joey recap SIGGRAPH — covering EVRN's image-to-3D tool, ComfyCode.ai's metadata-driven JSON prompting, and Beeble's SwitchX 2.0 push toward pro-grade outputs. Neill Blomkamp releases a fully AI-generated short film, Flux 3 enters the video mod...

Joey tests OpenAI Codex + Blender MCP to reconstruct a real building in 3D from phone photos — and the results have real implications for production workflows. Plus: what to expect at SIGGRAPH and a free AI Workflows Summit in LA.Also: Nuke's SmartRoto...

A hidden brain spontaneously developed inside an AI neural network — and that's just one of the stories this week. Addy and Joey break down Seedream 5.0 Pro's new precise image editing, Meta's Muse model and its controversial opt-out Instagram remix fe...

Google DeepMind puts $70M into A24. Anthropic's Fable model launched — then got pulled within days. Krea 2 goes open weight, and LTX Trainer brings video LoRAs to the open-source world. Adobe acquires Topaz Labs. -- The views and opinions expressed in ...

Addy and Joey recap AI on the Lot's biggest announcements: Amazon MGM's Gen AI Creators Fund, their new AI production platform Project Nara, and the backlash that drove Jorge Gutierrez out of the program. Plus, new agentic tools from Drumina and Luma. ...

Joey returns from Google I/O with hands-on tests of Omni, Google's new video world model, comparing it head-to-head with Runway Aleph 2 on the same shots. Plus: Demis Hassabis puts AGI three years out, Google Flow gets agentic workflows, and Google Pic...

Google I/O is around the corner, and Addy and Joey unpack what's expected — from a potential Veo HDR upgrade to DeepMind's new storywriting AI tool, Fabula, built alongside working screenwriters. They also cover Image-Blaster, an open-source tool conve...

Lightcraft's browser-based virtual camera, Claude integrating with Blender and Adobe, Kling AI hitting 4K — here's what shifted in film tech while we were on the road. Joey returns from NAB with a roundup of under-the-radar tools worth paying attention...

Blackmagic just loaded DaVinci Resolve with AI tools that can clone voices, reshape actor performances, remove motion blur, and simulate cinematic depth of field — and it's all built in. In this pre-NAB episode, Joey and Addy break down the most notabl...

Netflix just open-sourced an AI model that removes objects from video and corrects the physics — and that's only one of several AI updates worth tracking this week. Addy and Joey break down Netflix's VOID model, early leaks of what looks like GPT-Image...

New AI image and video models are dropping fast — but which ones are worth your time? Addy and Joey break down PhotaLabs, a new image model built for human likeness and character consistency, plus Fotello, a practical tool streamlining real estate phot...

OpenAI has officially shut down Sora — and the story behind its collapse reveals a lot about where AI video is headed. Addy and Joey break down why Sora never found its footing despite early buzz, what the dead Disney-OpenAI deal reveals about strategi...

Val Kilmer is starring in a new film via AI — years after his passing and without ever filming a scene. Addy & Joey dig into what that means for actor estates, film marketing, and storytelling. Plus: an AI company paying improv actors $74/hr to capture...

ComfyUI is reshaping how studios create AI-generated content, with 50,000 downloads per day and adoption across Netflix, intelligence agencies, and major VFX houses. In this episode, Yoland Yan, CEO of ComfyUI, shares the origin story of the open-sourc...

Netflix acquires Ben Affleck's AI company InterPositive, which builds custom models for film productions. We also cover Corridor Crew's open-source chroma key model that's making VFX keying significantly easier, and LTX's new desktop editor that integr...

Google's Nano Banana 2 delivers Pro-level features at half the cost, with web search capabilities that can generate current event imagery in real-time. Addy and Joey test the model across multiple scenarios and discuss Perplexity and Claude's rapid fea...

Addy and Joey break down the latest batch of open-source AI image models: FireRed's specialized editing capabilities, Recraft V4's enterprise-grade output with SVG support, and ByteDance's newest open-source offering. They also cover Foundry's acquisit...

Beeble's SwitchX transforms video backgrounds and relighting without destroying faces—potentially the most practical AI filmmaking tool yet. Joey and Addy test it live, debate LED volumes versus AI workflows, and break down Seedance 2.0's official rele...

Google's Genie world generation model is now public, OpenClaw AI agents are running wild across the internet, and Kling 3.0 just merged the best features from multiple video models. Addy and Joey take a closer look. -- The views and opinions expressed ...