Today in Generative Media

SAG-AFTRA's AI gamble; Creatopy raises $10M; Trump deflects blame on AI pics

News

• SAG-AFTRA’s AI Deal: A $5 Billion Gamble On The Future Of Voice Acting (Forbes)

• Creatopy, which automates ad creation using AI, raises a $10M Series A (TechCrunch)

• Donald Trump Isn’t Worried Taylor Swift Will Sue Him Over Fake Endorsement Post With AI Images: ‘Somebody Else Generated Them’ (Variety)

Software

• ElevenLabs’ AI Reader app can now narrate text in 32 languages (The Verge)

• Scalable Autoregressive Image Generation with Mamba (arXiv). Code on GitHub.

• RunFlux - a Google Colab Notebook to spin up a FLUX1-dev LoRA training at RunPod.io (X)

• Voice-to-voice AI using Open Source tools. (X)

• Phi-3.5-mini (3.8B) running in-browser at ~90 tokens/second on WebGPU w/ Transformers.js and ONNX Runtime Web! (X)

• ComfyUI v0.1.0 is out! (X)

Research

• Sapiens: Foundation for Human Vision Models (project page)

• Subsurface Scattering for Gaussian Splatting (project page)

• Robust 3D Gaussian Splatting for Novel View Synthesis in Presence of Distractors (project page)

• Video-Foley: Two-Stage Video-To-Sound Generation via Temporal Event Condition for Foley Sound (project page)

• Real-Time Video Generation with Pyramid Attention Broadcast (arXiv)

• DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments (arXiv)

Misc

• As a computer science major, I am so impressed by how large this AI-generated crowd looks tonight (X)