Today in Generative Media
Copyright: Are users responsible? OpenAI, MSFT sued; Silverman's suit stumbles
WNIGM will be on vacation until Monday for the US Thanksgiving holiday. I’m sure nothing very interesting will happen while I’m away… 👀
Tech Giants Say That Users Of Their Software Should Be Held Responsible For AI Copyright Infringements (CartoonBrew)
OpenAI, Microsoft sued for copyright infringement in class-action lawsuit (Semafor)
Sarah Silverman Hits Stumbling Block in AI Copyright Infringement Lawsuit Against Meta (Hollywood Reporter)
Internet Archive Submits Comments on Copyright and Artificial Intelligence (Internet Archive)
Stephen Fry Reads Nick Cave’s Stirring Letter About ChatGPT and Human Creativity: “We Are Fighting for the Very Soul of the World” (OpenCulture)
Today, we are releasing Stable Video Diffusion, our first foundation model for generative video based on the image model Stable Diffusion (Stability.ai) Stability AI gets into the video-generating game (TechCrunch) Community demo for Stable Video Diffusion - Img2Vid - XT (HuggingFace)
LCM Painter live demo (HuggingFace)
Real-Time Latent Consistency Model using webcam or screen input (HuggingFace) To switch from webcam to a window on your screen, click on the monitor icon at the bottom of the webcam view.
Concept Sliders: LoRA Adaptors for Precise Control in Diffusion Models (project page)
PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics (project page)
MagicDance: Realistic Human Dance Video Generation with Motions & Facial Expressions Transfer (project page)
SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering (project page)
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction (project page)
NePF: Neural Photon Field for Single-Stage Inverse Rendering (arXiv)
NeuroPrompts: An Adaptive Framework to Optimize Prompts for Text-to-Image Generation (arXiv)
Workflow with KREA is magical for architectural compositions 🪄 (X)