Today in Generative Media

Google pauses AI people pics; AI pros oppose deepfakes; Hollywood's AI expansion

• Google Pauses AI-Made Images of People After Race Inaccuracies (Time)

• Google Suspends AI Tool’s Image Generation of People After It Created Historical ‘Inaccuracies,’ Including Racially Diverse WWII-Era Nazi Soldiers (Variety)

• Hundreds of AI luminaries sign letter calling for anti-deepfake legislation (TechCrunch)

• Can Hollywood Be Trusted To Put People First In Its AI Expansion? (Refinery29)

• Holly Herndon’s Revolutionary AI Music (Jacobin)

• Viral fashion company Selkie is being slammed for using AI art (Mashable)

• BRIA raises $24 million Series A for ‘ethical’ visual generative AI platform (CTech)

• A Comedian And A Generative AI Tool Walk Into A Bar... (Forbes)

• SDXL-Lightning by ByteDance, is a fast text-to-image model that makes high-quality images in 4 steps (Replicate) Model on HuggingFace.

• RealCompo: Dynamic Equilibrium between Realism and Compositionality Improves Text-to-Image Diffusion Models (GitHub)

• FlashTex: Fast Relightable Mesh Texturing with LightControlNet (project page)

• Joint-TensoRF: Improving Robustness for Joint Optimization of Camera Poses

  and Decomposed Low-Rank Tensorial Radiance Fields (project page)

• You'd think that AI would drive a boom for the entertainment/gaming industry. Instead, incumbents from entertainment are facing incredible friction as they attempt to experiment with generative AI. (X) [long-form blog post]

• Spoke with a big co today about working with their IP. There is a lot of worries about a beloved character being manipulated into saying something inappropriate. (X)

• Announcing Stable Diffusion 3, our most capable text-to-image model, utilizing a diffusion transformer architecture for greatly improved performance in multi-subject prompts, image quality, and spelling abilities. (X)

• OurT2Remake: 🍿 Premiering in Hollywood, CA on March 6th! 🎟️ Get your tickets: https://t2remake.com

• Here’s our test using open source tools. You can get a decent level of creative control with AnimateDiff (X)

• Generative AI founders right now trying to compete with Sora (X)