Today in Generative Media

Schumer pushes regulation; 'Secret Invasion' AI credits; Publishers replace jobs

• Schumer launches ‘all hands on deck’ push to regulate AI (Washington Post)

• Artists are upset that ‘Secret Invasion’ used AI art for opening credits (TechCrunch)

• Major publishing house to replace hundreds of jobs with AI. (Futurism)

• Microsoft Bing (which uses GPT-4 in Creative Mode), accepts images as input.

  The results are impressive. (Ethan Mollick, Twitter)

• From MidJourney prompt to a vectorized final design, I share my full process for creating logos with AI. (Twitter)

• I went to an AI art conference, and here's what I learned (CreativeBloq)

• Some common errors folks make when first using AI (Ethan Mollick, Twitter)

• Proving that truth is always stranger than fiction, it looks like the next big thing in machine learning is going to be “just writing textbooks.” (Twitter)

• Emerging Architectures for LLM Applications (a16z)

• 🚀 vLLM is an open-source LLM inference and serving library that accelerates HuggingFace Transformers by 24x (GitHub)

• Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition (CVPR 2023, project page). Colab implementation is available!

• Consistent View Synthesis with Pose-Guided Diffusion Models (CVPR 2023, project page)

• Fast Segment Anything (arXiv) - claims to be 50x faster than Segment Anything with similar accuracy.

• DreamTime: An Improved Optimization Strategy for Text-to-3D Content Creation (arXiv)