MLearning.ai
Published in

MLearning.ai

Machine Learning Art

20 billion-parameter AI art model

Pathways Autoregressive Text-to-Image model PARTI

Google Research Pathways PARTI Autoregressive Text-to-Image prototype (Parti), an autoregressive text-to-image generation model that can create HQ photorealistic images and supports content-rich synthesis with activities to create and world knowledge. Recent improvements in diffusion models for turning text into images, like Google’s Imagen, have also shown impressive skills and state-of-the-art achievement on research benchmarks. Both Parti and Imagen look at autoregressive and diffusion models
the Parti models at three different scales — 750M, 3B, and 20B

When read or talk about a scene, they can picture it in their minds in great detail. Supporting the ability to make images based on these descriptions could open up creative possibilities in many areas of life, such as the arts, design, and multimedia…

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store