Today in Generative Media
Culture war meets AI tech; X is spreading AI porn; What was Sora trained on?
AI Companies Are Getting the Culture War They Deserve (Intelligencer)
Bobbi Althoff deepfake spotlights X’s role as a top source of AI porn (Washington Post)
What was Sora trained on? Creatives demand answers. (Mashable)
Gemini image generation got it wrong. We'll do better. (Google Keyword blog)
Creators vs. Artists (Rei Inamoto on Substack)
Unleash creativity with GoEnhance AI. Video to Video: Turn video into videos with many different styles. (GoEnhance.ai)
We are launching IP Adapter on Scenario, here is a quick look and overview of what it is (Scenario.com)
TTS Arena: Benchmarking TTS Models in the Wild (HuggingFace)
FiT: Flexible Vision Transformer for Diffusion Model (GitHub)
Visual Style Prompting with Swapping Self-Attention (project page)
Cameras as Rays: Pose Estimation via Ray Diffusion (ICLR 2024, project page)
Symbolic Music Generation with Non-Differentiable Rule Guided Diffusion (project page)
ToDo: Token Downsampling for Efficient Generation of High-Resolution Images (arXiv)
GaussianHair: Hair Modeling and Rendering with Light-aware Gaussians (arXiv)