Today in Generative Media

Google, AI and copyright; Adobe's AI id and compensation woes; text-to-music apps

• Google and YouTube are trying to have it both ways with AI and copyright (The Verge)

• Adobe Grapples With How to Spot AI Images and Compensate Creators (Business Insider)

• Developers are now using AI for text-to-music apps (TechCrunch)

• By adding low-rank parameter efficient fine tuning to ControlNet, we introduce Control-LoRAs (Stability via HuggingFace). [ed. A GitHub repo predates this “introduction” of control-lora by 6 months.]

• Get AI generated short video clips for your audio or video podcast (flowjin.com)

• Generate music with AI on iOS (songburst.ai)

• MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR (project page)

• TADA! Text to Animatable Digital Avatars (arXiv)

• Midjourney's new inpainting feature gives fashion designers fresh clothing ideas before they even start designing. (X)

• CGI is about to get easy (X)