Today in Generative Media
SAG supports California AI bill; Facebook hides AI labels; Video in Adobe Firefly
News
One of California’s most influential unions weighs in on AI safety bill (The Verge)
Facebook and Instagram are making AI labels less prominent on edited content (The Verge)
Adobe says video generation is coming to Firefly this year (TechCrunch)
The Godmother of AI Wants Everyone to Be a World Builder (Wired)
Facebook admits to scraping every Australian adult user's public photos and posts to train AI, with no opt-out option (Australia’s ABC News)
China wants red flags on all AI-generated content posted online (theregister.com)
Taylor Swift endorses Kamala Harris in response to fake AI Trump endorsement (The Verge)
First impressions of OpenAI o1: An AI designed to overthink it (TechCrunch)
Software
"Pixel Screenshots" Is the First AI Feature I’m Actually Excited to Use (How-To Geek)
This new AI creates 3D worlds from simple sketches, making game development accessible to all (Creative Bloq)
Introducing VideoGen, the world's first AI that can create and edit videos for you. (videogen.io)
Transform Images And Videos Into Immersive 3D With AI (digitalcarbon.ai) [Warning: this site brought my browser to its knees, YMMV!]
Create comics and manga with AI! (anifusion.ai)
Chat with AI to build web apps. Sync with GitHub. One-click deploy. (gptengineer.app)
🧹 Room Cleaner: Upload an image and use the pencil tool (✏️ icon at the bottom) to mark the areas you want to remove. (HuggingFace)
One-DM:One-Shot Diffusion Mimicker for Handwritten Text Generation (GitHub)
Thin-Plate Spline-based Interpolation for Animation Line Inbetweening (GitHub)
⚡️FLUX PuLID: FLUX-dev based Pure and Lightning ID Customization via Contrastive Alignment🎭 (API on Replicate)
SAM2 Studio: This is a Swift demo app for SAM 2 Core ML models. (GitHub) Core ML Segment Anything 2 (HuggingFace)
Research
FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally (ECCV 2024, arXiv)
Robust Dual Gaussian Splatting for Immersive Human-centric Volumetric Videos (SIGGRAPH Asia 2024, project page)
PersonaTalk: Bring Attention to Your Persona in Visual Dubbing (SIGGRAPH Asia 2024, project page)
PoseTalk: Text-and-Audio-based Pose Control and Motion Refinement for One-Shot Talking Head Generation (project page)
Vchitect 2.0: 20-second video generation, flexible aspect ratios, generative space-time enhancement, long video evaluation (project page)
Dynamic Scene Reconstruction from Single Landscape Image Using 4D Gaussian in the Wild (project page)
Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation (project page)
LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation (project page)
TrackGo: A Flexible and Efficient Method for Controllable Video Generation (project page)
Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos (project page)