Today in Generative Media

Mixed decision in Meta, Getty cases; You sound like ChatGPT; PJ Ace's AI studio

News and Opinion

• Meta wins AI copyright case, but judge says others could bring lawsuits (CNBC)

• Don't Believe The Tech Bro Hype: Copyright Owners Are The Real Winners In Kadrey v. Meta (Peter Csathy on Substack)

• Getty drops key copyright claims against Stability AI, but UK lawsuit continues (TechCrunch)

• You sound like ChatGPT (The Verge)

• The filmmaker behind the AI-generated Kalshi ad built an AI studio. It didn't kick off until Veo 3 launched. (Business Insider)

• Sketched Out: An Illustrator Shares His Fears About A.I. Art (New York Times)

• Image generation: Still crazy after all these years (Gary Marcus on Substack)

• The rise of the personal AI advisers (Fast Company)

• 5 Ways AI-Powered Creatives Are Stealing All The Best Clients (Forbes)

• How AI infiltrated perfume (The Verge)

• The résumé is dying, and AI is holding the smoking gun (Ars Technica)

• The Global A.I. Divide (New York Times)

• Takeaways From Hard Fork’s Interview With OpenAI’s Sam Altman (New York Times)

Software

• Adobe's New Firefly AI App Lets You Try AI Image and Video Generation for Free (CNET)

• Adobe is Now Tracking Generative Credit Use: What You Need to Know (PetaPixel)

• Bria 3.2 is the next-generation commercial-ready text-to-image model. With just 4 billion parameters, it provides exceptional aesthetics and text rendering, evaluated to provide on par results to leading open-source models, and outperforming other licensed models. (HuggingFace)

• Imagen 4 is now available in the Gemini API and Google AI Studio (Google Developers Blog)

• VideoPrism: A Foundational Visual Encoder for Video Understanding (GitHub)

• A memory-efficient implementation for upscaling videos in ComfyUI using non-diffusion upscaling models. This custom node is designed to handle large video frame sequences without memory bottlenecks. (GitHub)

• Gemini CLI: your open-source AI agent (Google Keyword Blog)

Research

• Dynamic Concepts Personalization from Single Videos (project page)

• 🍮 FLAM: Frame-Wise Language-Audio Modeling (project page)

• 4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time (project page)

• Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details (arXiv)

Misc

• Flawless is hiring on our Face Perception team. If you are an experienced researcher interested in solving complex problems for the film industry related to face detection, segmentation, occlusion aware detection and motion tracking, we would love to chat. (LinkedIn)

• Can AI do inbetweening? Well, it's a work in-progress... (LinkedIn)