Today in Generative Media

Adobe's AI audio separation; Google's genAI helps you shop; Meta's Emu Video / Edit

• Adobe is using AI to break apart messy audio (The Verge)

• Google will make fake AI products to help you find real gifts (The Verge)

• Introducing Emu Video and Emu Edit, our latest generative AI research milestones (Meta)

• If you get sued for an AI-generated creative work, OpenAI says it will protect you while Anthropic says you're on your own (Business Insider)

• Transforming the future of music creation (DeepMind) More info:

  • Perspectives from the artists collaborating on our early music experiments (YouTube Official Blog)

  • YouTube previews AI tool that clones famous singers — with their permission (The Verge)

  • Google is embedding inaudible watermarks right into its AI generated music (The Verge)

• Innovative technology from Typecast allows generative AI to transfer human emotion (VentureBeat)

• Everyone is playing with Krea’s new real-time generation feature: Julie W. Design, Javi Lopez, portraits, AlchemAIst, with Runway GEN-2 in the mix too (X)

• Others have built similar prototypes using LCMs: Illumine AI, and an iPad App (X)

• TLDraw is a prototype where you can simply draw a user interface and click “Make it Real.” (X)

• Learn how to use invideo.ai, a free AI video generator that can turn any text into a stunning video. (YouTube)

• EDMSound (project page)

• David Attenborough is now narrating my life Here's a GPT-4-vision +

  ElevenLabs python script so you can star in your own Planet Earth. (X) Code on GitHub. Related: Steve Jobs is now critiquing my designs directly in Figma! (X)

• I’ve resigned from my role leading the Audio team at Stability AI, because I don’t agree with the company’s opinion that training generative AI models on copyrighted works is ‘fair use’. (X)