Digital humans, AI-powered digital counterparts, are going to change how we interact online. And they already do.

Large language models and the future of computing.

Colorize anything from old black & white photos to artworks. It’s as simple as instagram, free, and no sign-up required.

The technicalities behind ClipDrop's image relighting app.

DiffusionBee is the easiest way to run Stable Diffusion locally on your M1 Mac.

Stable diffusion fork for generating tileable outputs.

Text-to-image generators are opening up new avenues for design.

AI image synthesis goes open source, with big implications.

A state-of-the-art AI model available for everyone through a safety-centric open-source license is unheard of.

What images were used to train Stable Diffusion’s text-to-image AI model?

If you haven’t been paying attention to what’s going on with Stable Diffusion, you really should be.

Today we’re introducing Outpainting, a new feature which helps users extend their creativity by continuing an image beyond its original borders.

Jason Allen’s AI-generated work “Théâtre D’Opéra Spatial” took first place in the digital category at the Colorado State Fair.

I finally was able to try it. And I can assure you it’s impossible to create professional and useful images from a text description.

In this blog post, I use DALL-E to recreate some of the world’s most iconic album covers. Can we get it right?

This image was created by an AI, MidJourney. All I had to do was type in a prompt (“wildfire”) and aspect ratio.

I’ve been playing with AI-generated art via Midjourney and DALL-E, which take text prompts and turn them into images.

But the company has had to rush out fixes to the image-making model’s worst flaws to do so.

Meta AI has built and released the first 175B parameter, publicly available chatbot, and deployed it in a live interactive conversational AI demo.

You don’t understand the power of illustration.