Today in Generative Media

Jobs upheaval; Good riddance to coding; Controllable image generation

• ChatGPT took their jobs. Now they walk dogs and fix air conditioners (Washington Post)

• It’s the End of Computer Programming as We Know It. (And I Feel Fine.) (New York Times)

• Diffusion Self-Guidance for Controllable Image Generation (project page)

• Getty asks London court to stop UK sales of Stability AI system (Reuters)

• Welcome to my world. (Twitter) - Tutorial using NeRF, RunwayML, and other tools to create trippy videos.

• Humans in 4D: Reconstructing and Tracking Humans with Transformers (project page)

• StyleDrop: Text-to-Image Generation in Any Style (arXiv)

• StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation (arXiv)

• Würstchen: Efficient Pretraining of Text-to-Image Models (arXiv)

• SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds (arXiv)

• The Hidden Language of Diffusion Models (arXiv)