I Tested an AI Art Generator and Here's What I Learned

I Tested an AI Art Generator and Here’s What I Learned

mid Road

I made these images with Midjourney.

Image: Sherin Shibu

The human creative process has historically escaped description. As the American novelist and journalist Theodore Dreiser once said, “Art is the stored honey of the human soul”. The 19th century painter Vincent Van Gogh once said, “I dream of painting and then I paint my dream”. For many, art taps into a deeper well of subconscious imagination.

How, then, do we integrate art created by AI into this conception of art? If humanity defines art, is it enough to reduce the definition to keywords typed into a generator?

This is a question that is no longer theoretical. At the end of August, an AI-generated artwork won a national fine arts competition. Jason Allen entered the Colorado State Fair in the digital art category with a collection he selected from the AI ​​Midjourney art generator. The winning piece, “Spatial Opera Theater” radiates potential, dominated by a bright sun or portal and elegantly spaced figures.


Screenshot of Allen’s Discord message.

Image: General Jumalon

How was the “Space Opera Theater” born?

Midjourney allows anyone to generate unique and creative pieces with a simple command. The only thing the AI ​​art generator requires from a human is a prompt: the user types in whatever they want, and the AI ​​gives them four new images in 60 seconds.

As long as you can access Discord, you’re good to go. Midjourney is in beta mode for public use.

Allen created many images using Midjourney, narrowed down his top three, increased his selections, and had them printed on canvas. He announced his first place on a Discord server, writing:

I decided to make a statement by using Midjourney competitively and wow! I couldn’t be more excited to have won with my favorite piece “Space Opera Theater”

What was the response to Allen’s victory?

The reaction was mixed, as you can imagine. A creator on Twitter commented that the biggest problem was that “the judges didn’t realize it was the AI… [which] doesn’t bode well for the discussion of illustration between humans and AI.” The victory was proof that AI can create works of art with little human intervention.

As Allen tweaked the images, other digital artists point out that the AI ​​takes elements of existing art to cobble together a new output. An artist wrote:

My problem with this is not that they “used AI”, but that using AI means that everything here was literally stolen from a group of artists in a way that even a tribute or a study does not.

The concerning element here is what defines creativity. Is it enough to write in a prompt, take an output, modify it and claim it as your own? Maybe the prompt was your idea, maybe you typed “Baroque in space” or “Royalty clustered around glowing sun” or something more specific, maybe you chose an output from hundreds. Does this make the art truly yours?

Going back to Van Gogh’s quote, dreaming of painting was only the starting point for him; the intention to create was not where it stopped. After the dream came the action: “I paint my dream”. In the harshness of the day, the dreams soften and fade away, but the artist captures them somehow. It may be an overly romanticized view of art, but isn’t there something a little mystical, a little magical about the experience of pouring your soul out onto the canvas?

AI-generated art takes the mystique out of the idea of ​​a new piece of art, but it still creates stunning and thought-provoking imagery – and that’s not going anywhere.

How can I use AI art?

If you want to experiment with the art of AI to find inspiration for your next piece or just see what it can do, there are a few technologies that are at the forefront. Midjourney, the software used by Allen, is the middle ground generator. I tried it myself and entered “happy couple in love in space” as a prompt. I got the following images:

mid Road

Image: Sherin Shibu

Very cute. The style is simple and dynamic, the color choices consistent.

Midjourney is free for the first 25 invites, after which it requires a subscription. The Basic plan is $10/month for 200 guests/month, the Standard is $30/month for 15 hours or 900 guests per month, and the Enterprise plan is $600/year for 7,200 guests per month. year.

If you click “Join Beta” on their homepage, you will be invited to their Discord channel. From there you can join a Bot channel, like #newbies-1, type “/imagine” and click on the prompt field, then type your command. For detailed instructions and gifs, see the official Midjourney documentation.

A high-end generator is DALL·E 2, which is now available in beta. This AI creates photorealistic images using a prompt you enter, and it not only identifies objects, but learns relationships Between objects.

The images generated by DALL·E 2 look like photos – they are amazingly realistic. The koala dunking a basketball image in the video above made me think it was from an alternate reality as realistic as our own.

If you join the DALL·E 2 waiting list, you could be among the first million to use the system. You get 50 free credits for your first month and 15 free credits for each month after that. One credit equals an original prompt with four images, such as Midjourney, or a modification of an existing image, resulting in three images.

The easiest to use generator that doesn’t require a subscription, Discord account, or anything other than a web browser is Craiyon.

Craiyon, formerly DALL·E mini, is a completely free generator that uses AI to draw images from any typed prompt. It all happens in your browser and it takes less than two minutes to generate nine images.

I tested Craiyon using a deliberately more abstract prompt: “happiness”. I got the following images:


Picture: Pencil

The image in the middle looks like my Betta fish before it attacks its breakfast. The face to his right is actively melting drops of metallic yellow. The bottom right image with pink drops in the background features a face that’s a bit too close for comfort. It is an impressive array of images that elicit a reaction from the viewer. At the very least, I might see an artist interpret one of these and use it as inspiration for their own work.

What makes art innovative?

Perhaps most interestingly, these tools again ask us to think about what exactly art is. Is it the intention, the execution and/or the reception of the art which makes it art? Far be it from me to keep the definition: artistic expression encompasses many forms. With AI art, however, the confusing aspect is that by selecting images and displaying them, the AI ​​artist is taking on more of a curatorial role in a digital museum of the artwork than the standard artist who delivers the work from start to finish.

Isn’t that the direction the art is going, though? We are in a period of post-modern contemporary art that rejects many of the traditional assumptions about inspiration, the nature of art, and what art can be and the role of the artist — a process which has now lasted for a century or more.

Also: Can AI help solve big data problems in education?

After experimenting with these tools, I understand the appeal. They are fast, personalized and fun to use. Perhaps art as the “stored honey of the human soul” can extend to whatever human beings can create to draw out this sweetness. Midjourney, Craiyon, DALL·E 2 and other AI generators are undeniably innovative and expand the capabilities of artists.

It’s a side of me. The other side feels that the intention of the artist, the tools they use to create, the work they put into a work, should be honored and rewarded. “I dream of painting and then I paint my dream” speaks of immersion not only in the expression of art, but also in the Arts and crafts. Of course, anyone can marvel at colors put together the right way, but the hard work of an artist who takes the time to master the techniques and create something step by step is the artist I want sustain.

I think modernism and post-modernism support my position. Take Warhol’s signature screen printing process. According to Sotheby’s, “Once he discovered the process and implications of working with silk screens, the content of Warhol’s output as a painter became inextricably linked to the process by which he created his art.” Content and process are inextricable, if not always visible. I then wonder what determines whether a process is valid. Will AI generators become the next silk screen?

Watching these generators work is like watching the mystical clouds of creativity that artists tapped into and couldn’t quite describe dissipate in less than 60 seconds. For better or worse, with AI generators, the process of creating innovative art goes beyond the indescribable and onto the assembly line.

#Tested #Art #Generator #Heres #Learned

Leave a Comment

Your email address will not be published. Required fields are marked *