The document below is a must read document for all.
DALL·E has not explicitly been ‘taught’ anything, like who Frida Kahlo is, or what a llama looks like, or what a wide-angle lens does. It has just studied 650 million images & captions, and left to draw its own conclusions.
That’s why there can’t be a regular ‘manual’ , based on functionality that the developers intentionally programmed in.
Even the creators of DALL·E cannot be sure what DALL·E has or hasn’t ‘learned’ , or what it thinks different phrases mean. Instead, we have to ‘discover’ what DALL·E is capable of, and how interacts. This document is a start!
Here is the manual of Dall e:
It it disappears here is the local link .. You never know