Gradienty was first conceived as a gallery of computer-generated gradients, but early attempts at generating an AI to combine colours produced some truly awful gradients. The AI would need training using two key inputs: user-generated gradients and a concept of what a good gradient.


User-generated gradients would be easy enough to build a tool for. The challenge would be understanding what a "good" gradient is, moreover, doing this without requiring tedious manual labour.

The ideal solution would be a way for users to 'like' or 'favourite' a pool of existing gradients. I settled on Tumblr for its flexible API – a gradient could be posted to then referred back to after a period of time to see users' reactions to it.

Gradient Creator

Visitors can search through all published gradients in a variety of ways, copy the colour values or complete CSS code, or create a brand new gradient. Tumblr users can like, reblog or comment on the gradient.

A new gradient is published every hour of the day and, at the time of writing, Gradienty's users and AI have generated a combined total of 45 thousand unique gradients.