I had forgotten I had signed up for an account with the DALL-E art site, which has gotten a fair share of notice for how it uses AI software to create art from written prompts. So when I saw an email yesterday, telling me my account was now active, I went in and played around. I used music themes for all of my prompts for the AI. The more specific the writing, the more interesting the image that the AI kicks out, I found.
I decided to create a “band” of musicians, with different settings and textual descriptions. It was an interesting experiment, and I used the “variations” tab quite a bit to see what the AI might generate in a second variation but for the most part, these come from the first round of algorithmic art by the platform.
I’ve included the text I used for the AI to generate the images.
You get a certain number of “credits” and then it costs some money to generate art.
Overall, I found the experience rather interesting, and yet I wondered how the AI was using my text descriptions to make itself “smarter” and was curious about what was going on underneath all of the code. There is a research paper available and the “about page” is full of positive elements of AI and the DALL-E site. It acknowledges the worries about AI, too, which I appreciated.
From the site:
Preventing Harmful Generations
We’ve limited the ability for DALL·E 2 to generate violent, hate, or adult images. By removing the most explicit content from the training data, we minimized DALL·E 2’s exposure to these concepts. We also used advanced techniques to prevent photorealistic generations of real individuals’ faces, including those of public figures.
Our content policy does not allow users to generate violent, adult, or political content, among other categories. We won’t generate images if our filters identify text prompts and image uploads that may violate our policies. We also have automated and human monitoring systems to guard against misuse.
I am also curious about this part of the Mission Statement:
Our hope is that DALL·E 2 will empower people to express themselves creatively. DALL·E 2 also helps us understand how advanced AI systems see and understand our world, which is critical to our mission of creating AI that benefits humanity.
Let’s hope so, eh?
Peace (and Art),
Peace (and thankful for it),
My students and I continue to doodle and draw daily with place-based themes that connect to both CLMOOC and Write Out (I’ve also been writing small poems each morning to the theme of the day, too). I am loving how the calendar itself becomes a work of art as each box gets doodled in.
I wrote about this project in an earlier post.
Peace (drawing it),
My students recently finished up working with a visiting artist — a woodcarver named Elton Braithwaite, who has been coming to our school now for 22 years — and their two pieces of collaborative carvings are very impressive. One has a tree theme. The other, a book theme.
The pieces have yet to be painted, so I took pictures of both carvings in their unpainted state, and began to play around with app filters (inspired by a friend of mine, Simon). One filter app I used (on the tree) is called Olli and the other (on the read) is Painteresque. The gif maker site is called Gif Maker.
I wanted to see the same image, fading in and out with filters. This approach worked better in another space, where Simon and I and others are sharing writing and art and more. The fade there was more natural. But here, I just used the online gif maker and layered the photos. The transitions are more abrupt, and a bit too quick (maybe I should have tinkered more with the settings on the gif creator).
It’s still kind of neat. The tree one works best, I think, for the app brings to the surface more of the textures of the carving piece. It’s a more natural piece of art. The read one is sort of distracting with the filters I used — at times giving it a sort of metallic sheen that goes counter to the concept of this being a carving on wood.
Peace (in the carving),
My wife and I visited the Mead Art Museum on the grounds of Amherst College yesterday, and its special exhibit was all about the intersections of science and art, in a field (I did not know about) known as “dimensionism.” The exhibit is entitled Modern Art in the Age of Einstein, and I found it fascinating and inspiring, and later in the day, I worked on my own artistic remix of some of the ideas my mind gathered from there.
This piece has multiple layers and multiple filters and frames as well as the layered small poem. The main visual layer is a from Marcel Duchamp’s Rotoreliefs, two spinning spiral wheels in motion on record players, explained in the art gallery this way:
When set in motion, the disc appears to transport the two-dimensional object into a wobbly three-dimensional cylinder that moves in four-dimensional space-time.
It’s fun to think of where art and science collide, and how poetry might also gain a toehold into our perceptions of these areas of overlap. Here, I hope your eyes are drawn to the center, the dark space of time, even as the shadows of my own hands taking an image allow you to step back to see the scene from another angle.
Peace (in the make),