Today in Generative Media
AI's 'Her' era arrives; Senators propose $32B for AI; Google's new AI models and tools
A.I.’s ‘Her’ Era Has Arrived (New York Times)
Senators Propose $32 Billion in Annual A.I. Spending but Defer Regulation (New York Times)
New generative media models and tools, built with and for creators (Google Keyword Blog)
Google unveils Veo and Imagen 3, its latest AI media creation models (Engadget)
Introducing VideoFX, plus new features for ImageFX and MusicFX (Google Keyword Blog)
Ask Google Photos to help make sense of your gallery (Engadget)
Google’s generative AI can now analyze hours of video (TechCrunch)
Google’s invisible AI watermark will help identify generative text and video (TechCrunch)
OpenAI's generative video software is more tedious than actual filmmaking (BoingBoing)
Meta is reportedly working on camera-equipped AI earphones (Android Authority)
Glifs are fun AI apps anyone can build (glif.app) we just shipped the easiest way to get ComfyUI workflows up and running fully online… for now, you can now edit & run full workflows right inside of glif, and wrap them in a nice UI so your friends without 4090s or comfyPatience can run them too (X)
Mini-DUSt3R Demo: Unofficial DUSt3R demo using the mini-dust3r pip package (HuggingFace) Mini-Dust3r is so fast 4 frames 10s, visualized with Rerun (X)
LayGA: Layered Gaussian Avatars for Animatable Clothing Transfer (SIGGRAPH 2024, project page)
AT-EDM: Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models (project page)
SwapTalk: Audio-Driven Talking Face Generation with One-Shot Customization in Latent Space (project page)
All ten winning films from the 2024 AI Film Festival are now available to view at http://aiff.com (X)
Check out my new Cyberduck! I made this on my local machine & you can too. Here's how🚀 (X)