Today in Generative Media

Copyright office in an AI clash; Google Lumiere's cute animals; Artisse raises $6.7M

• The Sleepy Copyright Office in the Middle of a High-Stakes Clash Over A.I. (New York Times)

• Google’s latest AI video generator can render cute animals in implausible situations (Ars Technica)

• Artisse AI raises $6.7M for its ‘more realistic’ AI photography app (TechCrunch)

• Famed Photographer Shows How Easy it is to Recreate His Photos With AI (PetaPixel)

• Deepfake deluge expected from AI image generation breakthrough (so long, LoRA?) (VentureBeat)

• Radiance Fields appear at KidSuper Fashion Show (radiancefields.com)

• MIT AI for filmmaking hackathon (MIT)

• 3DTopia: A two-stage text-to-3D generation model. (GitHub)

• Code release for GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (GitHub)

• Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis (ICLR 2024, project page)

• Large-scale Reinforcement Learning for Diffusion Models (arXiv)

• Now you can run InstantID with LCM-LoRA on your local machine (Mac, Windows, Linux) with 1 Click using the updated gradio app (X)

• I was approached by the Founder of The Future of Money event in Toronto to create a unique 40 sec AI-video for their home page banner, illustrating the dynamic evolution of money. (X)

• Remember peeps AI film is for everyone, for every genre, for every taste, it's not just robots, anime and astronauts as illustrated in this beautiful piece by Chrissie. (X)