

Tim Salimans
134 posts

@TimSalimans
AI Research Scientist







You may think discrete distillation is fundamentally flawed, you are (surprisingly) wrong. 🤯 Meet Discrete Moment Distillation (D-MMD). It is a new method that brings fast, few-step sampling to discrete diffusion models! 🧵👇

1/6 Introducing Unified Latents: what if your diffusion model's latents were measured in bits? Instead of relying on dimensionality reduction, we learn a latent AE with explicit bitrate control. Paper: arxiv.org/abs/2602.17270 @emiel_hoogeboom, @TimSalimans



What if you could not only watch a generated video, but explore it too? 🌐 Genie 3 is our groundbreaking world model that creates interactive, playable environments from a single text prompt. From photorealistic landscapes to fantasy realms, the possibilities are endless. 🧵




Amsterdamse huizenbezitter moet sleutels sociale huurwoning inleveren ift.tt/O6evCPk


Today, we’re announcing Veo 2: our state-of-the-art video generation model which produces realistic, high-quality clips from text or image prompts. 🎥 We’re also releasing an improved version of our text-to-image model, Imagen 3 - available to use in ImageFX through @LabsDotGoogle. → goo.gle/veo-2-imagen-3






