AI Tech Guide - Art Edition

1) Midjourney:

Midjourney describes itself as “an independent research lab exploring new mediums of thought and expanding the imaginative powers of the human species.”

One can use the Midjourney bot to generate images from simple text prompts in seconds! And it’s about as easy as it sounds, as the website states: “Work directly in Discord. No specialized hardware is required.”

2) Stable Diffusion:

“This technology has tremendous potential to transform the way we communicate and we look forward to building a happier, more communicative, and creative future.” 

Stable Diffusion 2.1 is the latest text-to-image model from StabilityAI.It offers additional programs like guided image synthesis, a process where one can incorporate new elements into existing images. It also supports the use of prompts to partially alter an image using both inpainting and outpainting.

3) DALL-E:

A neural network that “creates images from text captions for a wide range of concepts expressible in natural language.”

DALL-E possesses the ability to modify several of an object's attributes, as well as the number of times it appears. It also allows for control over the viewpoint of a scene and the 3D style in which a scene is rendered.

DALL-E has also commented on the nuanced complications that come with the creation of such a program, and states: “We recognize that work involving generative models has the potential for significant, broad societal impacts. In the future, we plan to analyze how models like DALL-E relate to societal issues like economic impact on certain work processes and professions, the potential for bias in the model outputs, and the longer term ethical challenges implied by this technology.” 

Guest Contributor:

Evangeline Merritt

Friend of OMG Labs and classically trained student of  ballet, hiphop and modern contemporary styles for over 10 years. Evangeline is interested in the intersection of technology and the arts and is always prepared to dance battle if crossed.