Today in Generative Media
Meta genAI labels, OpenAI watermarks; Stability's improved AI video; AI Mickey Mouse
Meta Calls for Industry Effort to Label A.I.-Generated Content (New York Times)
OpenAI is adding new watermarks to DALL-E 3 (The Verge)
Stability AI launches SVD 1.1, a diffusion model for more consistent AI videos (VentureBeat)
This AI Model Is Trained On Public Domain Stills To Create Mickey Mouse Images (CartoonBrew)
Ikea’s AI assistant gives design inspiration — at least it tries to (The Verge)
China’s generative video race heats up (TechCrunch)
Galileo AI is a UI generation platform for easy and fast design ideation. (usegalileo.ai)
DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models (project page). Code on GitHub.
Natural language guidance of high-fidelity text-to-speech models with synthetic annotations (project page)
Guiding Instruction-based Image Editing via Multimodal Large Language Models (project page). Code on GitHub. Demo on HuggingFace.
MusicRL: Aligning Music Generation to Human Preferences (project page)