“The simulation of human intelligence generated by a computer system is AI.”
DALL-E 2, a system of AI that has made possible the creation of images through generating texts, For the past few months, it has been intriguing to see how computers have been creating these images. One model specifically, called the DALL-E Mini, has been fascinating to look at as to how it has achieved image status throughout the last week, facilitated by the AI storehouse.
So when DALL-E was asked to create a self-portrait, the results were startling.
The outcomes were… blended. And, in DALL-E Mini, it either sees itself as some kind of seabird, a goat-like animal, or a baffling sphere that looks like a minute organic entity — among numerous other strange transformations.
The DALL-E Mini’s authors wrote, “By simplifying the architecture and model memory requirements, as well as leveraging open-source code and pre-trained models available, we were able to satisfy a tight timeline.” Considering in what manner or capacity numerous people are currently teaming up with AI models to make craftsmanship, it was not out of the question to request that the AI reveal itself as a self-picture.
Added to DALL-E 2
It has been said that the model is still in training. The DALL-E 2 is the newer AI system that can create realistic images and art from a description in natural language. It can create original, realistic images and art from a text description. It can combine concepts, attributes, and styles. It can make realistic edits to existing images from a natural language caption. Furthermore, it can add and remove elements while taking shadows, reflections, and textures into account. By taking an image, it can create different variations of it inspired by the original. DALL-E 2 has learned the relationship between images and the text used to describe them. It uses a process called “diffusion,” which starts with a pattern of random dots and gradually alters that pattern toward an image when it recognizes specific aspects of that image.
