This weekend in Generative Media

Bing makes Disney logos; Artists: "Please regulate AI"; Can studios do AI responsibly?

• AI-generated movie posters with Disney logos force Microsoft to alter Bing Image Creator (Ars Technica)

• ‘Please regulate AI:' Artists push for U.S. copyright reforms but tech industry says not so fast (AP News)

• SAG-AFTRA’s new contract hinges on studios acting responsibly with AI (The Verge)

• Do Pixel 8 AI-edited photos have to be labeled as synthetic content on YouTube? YouTube is still figuring it out. (The Verge)

• Text-to-image AI models can be tricked into generating disturbing images (MIT Technology Review)

• Realtime generative AI art is here thanks to LCM-LoRA (VentureBeat)

• Microsoft releases AI tool for photorealistic copying of faces and voices (The Guardian)

• UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs (arXiv)

• Clearer Frames, Anytime: Resolving Velocity Ambiguity in Video Frame Interpolation (project page)

• 🎨🖌️ 3D Paintbrush: Local Stylization of 3D Shapes with Cascaded Score Distillation (project page)

• TOSS: High-quality Text-guided Novel View Synthesis from a Single Image (project page)

• InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image (arXiv)

• MetaDreamer: Efficient Text-to-3D Creation With Disentangling Geometry and Texture (arXiv)

• Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models (arXiv)

• PodReels: Human-AI Co-Creation of Video Podcast Teasers (arXiv)

• now you can control the influence of AI over the image (X)

• ✨ How to make a 100% AI-generated TikTok video of yourself (X)

• Make your own "Make Real" app with tldraw. (X)

• Turn doodles on tldraw → illustration with nearing real-time image diffusion model (LCM) (X)

• I've optimised my latent consistency model on Replicate to make it 3x faster (X)

• Stable Diffusion 360 Panorama Colab 🥳 (X)

• All of Silicon Valley right now (X)