Today in Generative Media
Meta AI's Movie Gen; Investors love ElevenLabs; Sora co-lead moves to Google
News and Opinion
Movie Gen sets a new standard for immersive AI content (Meta AI)
Investors are scrambling to get into ElevenLabs, which may soon be valued at $3 billion (TechCrunch)
A co-lead on Sora, OpenAI’s video generator, has left for Google (TechCrunch)
Confessions of an illustrator: How I really feel about AI (Creative Bloq)
I spoke to a 60-year-old AI version of myself and it was…. unsettling (Popular Science)
Online spaces are rife with toxicity. Well-designed AI tools can help clean them up (The Conversation)
Software
Introducing canvas A new way of working with ChatGPT to write and code (OpenAI)
Google Lens now lets you search with video (The Verge)
Gemini Live will support more languages for its AI voice chat (The Verge)
Research
Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis (ECCV 2024, project page)
Flash-Splat: 3D Reflection Removal with Flash Cues and Gaussian Splats (ECCV 2024, project page)
Depth Pro: Sharp Monocular Metric Depth in Less Than a Second (arXiv). Code on GitHub
Self-Supervised Audio-Visual Soundscape Stylization (project page)
ComfyGen: Prompt-Adaptive Workflows for Text-to-Image Generation (project page)
Misc
AI ragdoll (X)