NightCafe now also offers a second text-to-image AI algorithm called CLIP-Guided Diffusion, which we refer to as the "Coherent" algorithm. 

This algorithm is fantastic at generating more realistic images, composed in a believable way, to look more like a photo. While VQGAN+CLIP often gives you things like buildings in the sky or repeating pixel patterns, Clip Guided Diffusion does a better job of obeying the laws of physics when you run the encoder.

The Coherent algorithm can be a little more hit-and-miss than the Artistic algorithm, however most of the top artists on NightCafe prefer the coherent algorithm.