CLIP

Technical

Vokenization: Multimodel Learning for Vision and Language

How can language models better model human learning? A new technique known as Vokenization addresses this by grounding information from the external visual world.

Read
AI Art

Alien Dreams: An Emerging Art Scene

In January 2021, OpenAI released the weights and code for their CLIP model, and since then various hackers, artists, researchers, and deep learning enthusiasts have figured out novel methods for combining CLIP with various generative models to create beautiful visual art from just a text prompt. In this blog post I document the evolution of this new art scene and share a bunch of cool artwork along the way.

Read