Today in Generative Media
Meta's Black AI persona; Britain bans explicit deepfakes; Apple's broken AI news alerts
News
I talked to Meta’s Black AI character. Here’s what she told me. (Washington Post)
Britain to make sexually explicit 'deepfakes' a crime (Reuters)
Apple urged to withdraw 'out of control' AI news alerts (BBC)
Instagram Begins Randomly Showing Users AI-Generated Images of Themselves (404 Media)
Disneyland quietly removes suspected AI art at new gift shop after blowback (SFGate)
‘Minion Gore’ Videos Use AI to Post Murder to Instagram, TikTok, and YouTube (404 Media)
Why early generative AI ads aren’t working and how creatives will shift to integrate the tech into their work (digiday.com)
Video editing app Captions switches to a freemium model to boost growth (TechCrunch)
How Elon Musk’s xAI is quietly taking over X (The Verge)
Fear and coding in Las Vegas (Business Insider)
25 AI Predictions for 2025, from Marcus on AI (Gary Marcus on Substack)
Software
Adobe’s new AI tool can edit 10,000 images in one click (The Verge)
3D animations for All, powered by AI (anything.world)
⚡️Sana: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer (GitHub) [License revised to Apache 2.0]
Research
Large Motion Video Autoencoding with Cross-modal Video VAE (project page)
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation (project page)
D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (project page)
GenHMR: Generative Human Mesh Recovery (project page)
InterDyn: Controllable Interactive Dynamics with Video Diffusion Models (mpg.de)
Materialist: Physically Based Editing Using Single-Image Inverse Rendering (arXiv)