Today in Generative Media

Madonna's genAI video; Meta's AI flimsy watermarking plan; Anthropic's Claude 3.0

• Do AI video-generators dream of San Pedro? Madonna among early adopters of AI's next wave (Bloomberg)

• Meta's AI Watermarking Plan is Flimsy, At Best (IEEE Spectrum)

• Introducing the next generation of Claude (Anthropic)

• Anthropic claims its new AI chatbot models beat OpenAI’s GPT-4 (TechCrunch)

• Midjourney rival Ideogram gets $80M in Series A led by Andreessen Horowitz (VentureBeat)

• Competition in AI video generation heats up as Deepmind alums unveil Haiper (TechCrunch)

• Today, we’re publishing our research paper that dives into the underlying technology powering Stable Diffusion 3. (Stability)

• Transparent Image Layer Diffusion using Latent Transparency. This is a WIP extension for SD WebUI (via Forge) to generate transparent images and layers. (GitHub)

• Relightful Harmonization: Lighting-aware Portrait Background Replacement (CVPR 2024, project page)

• SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation (project page)

• DUSt3R: Geometric 3D Vision Made Easy (project page) While looking for a rental apartment on airbnb for my vacations, i noticed I had difficulty grasping the layout and space of the apartment based on photos alone. Solution: put all photos in DUSt3R and voila :) (X)

• - this is the raw output of a MotionLora

  - it was trained on the footage on the left. (X)

• as a person who spent hours learning about technical analysis of films, I just don't believe AI can ever dominate this area (X)

• I see people on LinkedIn, even professionals with experience in the industry, talking about Sora and panicking without reason, without analyzing and breaking down that AI. (LinkedIn)