Today in Generative Media

Anthropic vs. UMG AI copyright suit; Half of game dev's studios use AI; AI misinfo

• Anthropic fights back against Universal Music Group in AI copyright lawsuit (CoinTelegraph)

• Game developer survey: 50% work at a studio already using generative AI tools (Ars Technica)

• AI-driven misinformation ‘biggest short-term threat to global economy’ (The Guardian)

• TikTok can generate AI songs, but it probably shouldn’t (The Verge)

• Novelist wins award, then reveals she used ChatGPT. (Futurism)

• Samsung puts an annoying little watermark on its version of Google’s AI wallpapers (9to5Google)

• Microsoft's AI-powered reading tutor lets students choose their own adventures - and it's free (ZDNet)

• Can Recraft’s foundational model for graphic design swerve the AI controversy? (TechCrunch)

• WhisperSpeech: An Open Source text-to-speech system built by inverting Whisper. (GitHub)

• Official implementation of Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers (GitHub)

• Perspectives on Diffusion: a blog post by Sander Dieleman comparing different derivations of diffusion models.

• Bringing Telepresence to Every Desk (project page)

• SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wild (project page)

• CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects (project page)

• VideoCrafter2 : Overcoming Data Limitations for High-Quality Video Diffusion Models (project page) Demo on HuggingFace.

• TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion (project page)

• WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens (project page)

• Rethinking FID: Towards a Better Evaluation Metric for Image Generation (arXiv)

• DiffusionGPT: LLM-Driven Text-to-Image Generation System (arXiv)

• Krea AI has announced three new features: text-to-image, background removal, and an eraser. These are available on free accounts, so go ahead and try them out. (X)

• Animate Anyone in Comfy (X)

• I present "Sister of Battle", my new AI film! (X)