Generated an AI image, it's close but not quite what you want? In this article, I will teach you a few simple prompting techniques to let you dial-in the details of your images. We will use this Stable Diffusion GUI for this tutorial. See my quick start guide for setting up in Google's cloud server. Note that many of the techniques outlined in this article only works on this software.

As the saying goes: "Beauty is in the eye of the beholder." But this egalitarian sentiment is easy to forget in our image-conscious age of photoshopped social media stars. Many feel pressure to look "perfect" and apps like Snapchat only help to filter out the "ugly" bits -- also known as reality. My own reflection was scrutinised this week in an uncomfortably public social experiment. A "biometric mirror" set up in Melbourne's CBD scanned my mug and used an algorithm to assess my level of "perfection".

Facebook has created an algorithm that can pick a face out of a crowd almost as accurately as a human. Called DeepFace, it uses technology the firm bought when it acquired Israeli startup face.com last year. Its creators say it pick a face out of a crowd with 97.25 per cent accuracy. Facebook's DeepFace uses a 3-D model to rotate faces, virtually, so that they face the camera. Image (a) shows the original image, and (g) shows the final, corrected version which the software can then attempt to recognise.