Today in Generative Media

AI's copyright woes; George Carlin estate sues creators; Graphic celebrity deepfakes

• We Asked A.I. to Create the Joker. It Generated a Copyrighted Image (New York Times)

• Anthropic Fires Back Against Music Publishers’ Injunction Motion: ‘Using Copyrighted Content As Training Data for an LLM Is a Fair Use’ (Digital Music News)

• Google Trained Its AI on Copyrighted Music, Sources Say — Now It’s Trying to Make Deals (Billboard)

• George Carlin Estate Sues Creators of AI-Generated Comedy Special in Key Lawsuit Over Stars’ Likenesses (Hollywood Reporter)

• Trolls have flooded X with graphic Taylor Swift AI fakes (The Verge)

• Diffuse to Choose: Enriching Image Conditioned Inpainting in Latent Diffusion Models for Virtual Try-All (project page)

• pix2gestalt: Amodal Segmentation by Synthesizing Wholes (project page)

• As someone who's created over 70 AI videos so far... I feel that AI video generators alone are not enough to create cinematic pieces. (X)

• Here's a demo I created which performs monocular depth estimation directly in your browser (no server needed)! 🤯 (X)

• Testing out the new LensGo style transfer feature with some free credits they gave me. Load up a video and change it with AI. (X)