Hello!

I’m Justin Pinkney and this site is my home on the web.

Most of the things on this website are either about Generative Art or Deep Learning or the combination of the two. Mostly written up as blog posts.

My day job is as a machine learning researcher at Lambda Labs. I spend most of my time writing code, developing algorithms, training models, and encouraging people to embrace good software development practices.

I spend a lot of my free time messing around with code and here I’ll write about some of it. Some things might even be called projects and hopefully the rest might still be of interest.

You can also find me on other places around the web, say hello on Twitter, or keep up to date with this site via RSS.

Most recently updated pages:

Experiments in Image Variation

Playing with interesting ways of using the Stable Diffusion Image Variations model

Text to Pokemon Generator

Fine tuning Stable Diffusion to generate Pokemon

Style Space Face Editing

A runway app to make silly face edits using the StyleSpace of StyleGAN

(draft) -- The Wonderful World of CLIP

A collection of the weird and wonderful uses of an exciting new vision and text model.

Ukiyo-e faces dataset

A dataset of thousands of high resolution aligned faces from uikyo-e prints

Making Toonify Yourself

The story of deploying a deep neural network to the cloud and Toonifying tens of thousands of images an hour.

Toonify yourself

Use StyleGAN model blending to find your Pixar self

StyleGAN network blending

Mixing GAN models for weird and wonderful effects

Ideas 💡

A list of ideas I probably wont ever have time to try out.

From feature space to input space

An article looking at the connection between input space and feature space in deep neural networks and how various novel methods have been invented by generalising techniques between the two.