Today in Generative Media
Apple stops AI news summaries; Most Americans use AI, most dislike it; UK AI safety
News and Opinion
Apple Plans to Disable A.I. Features Summarizing News Notifications (New York Times)
Nearly all Americans use AI, though most dislike it, poll shows (Axios)
Labour’s AI plan could be good for British people – except the creatives it will throw under the bus (The Guardian)
What Happens When You Turn Your Life Over to an AI Assistant? (Wired)
Software
You can now fine-tune your own version of AI image maker Flux with just 5 images (VentureBeat)
Luma AI releases Ray2 generative video model with ‘fast, natural’ motion and better physics (VentureBeat)
ComfyUI now supports Nvidia Cosmos: The best open source Image to Video model so far. (ComfyUI blog)
Research
SynthLight: Portrait Relighting with Diffusion Model by Learning to Re-render Synthetic Faces (project page)
Go with the Flow: Motion-controllable video diffusion models using real-time warped noise (project page)
MagicQuill: An Intelligent Interactive Image Editing System (project page)
LayerAnimate Layer-specific Control for Animation (project page)
CaPa: Carve-n-Paint Synthesis for Efficient 4K Textured Mesh Generation (project page)
Zero-shot mono-to-binaural speech synthesis (project page)
Vision-Language Models Do Not Understand Negation (project page)
Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps (arXiv)
Misc
Artificial Aesthetics: Generative AI, Art and Visual Media: Our book explores how generative AI is transforming our understanding of aesthetics, creativity, design, and art appreciation.
The Large Language Model Course (HuggingFace)
An open call for the next Google.org Accelerator: Generative AI (Google Blog)
AI Product Management has a bright future! (Andrew Ng)