Today in Generative Media

OpenAI offers only $1M to publishers; GPT Store launching soon; AI laser engraving

• OpenAI Offers Publishers as Little as $1 Million a Year (The Information)

• OpenAI GPT Store launching next week (VentureBeat)

• The first ever AI laser engraver with Midjourney support looks pretty wild (CreativeBloq)

• DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models (HuggingFace)

• High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models (Demo/API on Replicate). 80 frames; a single generation; 10 second video at 1280x (X)

• SIGNeRF: Scene Integrated Generation for Neural Radiance Fields (project page)

• Street Gaussians for Modeling Dynamic Urban Scenes (project page)

• What You See Is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs (project page)

• TrailBlazer: Trajectory Control for Diffusion-Based Video Generation (project page)

• VideoDrafter: Content-Consistent Multi-Scene Video Generation with LLM (project page)

• 🐏🐕🐁🦌 Learning the 3D Fauna of the Web (project page)

• Instruct-Imagen: Image Generation with Multi-modal Instruction (arXiv)

• Announcing 𝚐𝚛𝚊𝚍𝚒𝚘 𝟺.𝟷𝟹 🚀🚀 (X)

• The second edition of GEN:48 is coming 2/3 - 2/5. Registration opens soon. (X)

• A book on Amazon, published in 2023, with the same title as my 2019 book. The "sample" on Amazon reads like a ChatGPT summary of my book (with some small post-editing). Is this legal? (X)