Today in Generative Media
Veo 2 trounces Sora; AI addresses 'sameness problem'; Odyssey's world models
News and Opinion
Google's AI video generator blows OpenAI's Sora out of the water. YouTube may be a big reason. (Business Insider)
Writer’s new AI model aims to fix the ‘sameness problem’ in generative content (VentureBeat)
Generative World Models for Film, Gaming, and Beyond (Odyssey) We’re excited to welcome Ed Catmull, co-founder of Pixar, to our board. Together, we’re pioneering generative world models, beginning with Explorer.
AI is burying company websites in search results, but Otterly.AI thinks it can help (TechCrunch)
Why Does OpenAI Need So Much Money? (New York Times)
Who wants ‘Her’-like AI that gets stuff wrong? (TechCrunch)
Where Humans Still Have the Edge on AI (Harvard Business Review)
Cloud AI Startup Vultr Raises $333 Million at $3.5 Billion Valuation (Wall Street Journal)
AI Startup Perplexity Closes Funding Round at $9 Billion Value (Yahoo Finance)
Perplexity acquires Carbon to connect AI search to your work files (TechCrunch)
Software
Ideogram Batch Generation is here! (X) Enhance your creative workflow by simplifying image creation at scale – no more manual adjustments or constant supervision needed. Simply upload a spreadsheet with prompts and settings to generate images in bulk. Now available for Ideogram Pro users.
Krea Editor is here. Our new editing tool is now available in open beta. Free for everyone. (X)
Moonshine Web: Real-time in-browser speech recognition that's faster and more accurate than Whisper (X)
GitHub is making its AI programming Copilot free for VS Code developers — with limits (VentureBeat)
Research
Genesis: A Generative and Universal Physics Engine for Robotics and Beyond (project page)
Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos (project page)
MegaSynth Scaling Up 3D Scene Reconstruction with Synthesized Data (project page)
Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion (project page)
Deformable Radial Kernel Splatting (project page)
Lifting Motion to the 3D World via 2D Diffusion (project page)
3DGUT: Enabling Distorted Cameras and Secondary Rays in Gaussian Splatting (project page)
Gaussian Billboards: Expressive 2D Gaussian Splatting with Textures (arXiv)