Exactly.AI
I’ve got to share some of these images that I’ve been making with Exactly.AI (Durer.AI)
I was able to train a model on my paintings using about 15 images + a language component (describing the art that I’m uploading for training).
Here are some generations from the first model I trained. It’s kind of fun to play with the prompts as a parameter in regard to generations from my own models. This is something you can do with current LLMs (Large Language Models), where the GANs (Generative Adversarial Networks) or CANs (Creative Adversarial Networks) have used no prompting.
I’ll show you more of why this could be fun, but first, this first set of images was prompted using words that were very close to the words that I input for training, making them closer to the actual style of what they were trained on.
This next set is what happens with the subject (above is abstract botanical), when the prompt changes from the original input.
Here, I switched out parts to add different subjects like palm trees, crows, gnarled trees, birch trees, coral, cacti, landscapes, skulls, and cats.
Artists can use this kind of thing as a study to see how one style might transfer to a different subject, or to explore different variations on their work before they set to it with paint.
One subject that this model is really good for is leaves - since so much of the work it was trained on was botanical abstraction. I loved how these came out. The prompts included much of my original text that described the style, material, and colors, plus the description of leaves falling and blowing in the wind.
I trained another model with some newer paintings, and here is what they look like:
Again, I kept the prompts close to the original prompt used when training, and that keeps the results looking like mine.
For me, using AI art tools contributes to a process of reflection, contemplation, and integration.
I’d be curious to hear how other artists who paint intuitively have found the process of training an AI model on one’s own work.
REPRESENTATIONS
I’ve been working with AI art tools for a few years now, and while I was met with misunderstanding and fear sometimes, now I’m met with it MOST of the time. Even if people want to understand, now they have to UNLEARN and overcome what the media and misinformed audiences have planted into their brains. To be honest, it surprised me when I was met with fear and apprehension about what I was doing - training an artificial intelligence model on a body of my work, and working with the results - because I was absolutely delighted by it! It was so reflective, it fit right into my practice, bringing my knowledge about art therapy, mindfulness, connection, energy… all together. It felt therapeutic (from actually studying to be an art therapist and counselor, and from being a person with C-PTSD, actually in therapy). How could everyone get it so wrong?
I saw the Terminator films too! But I have also realized that I’m an early adopter, I’m someone who gets excited about ideas, and who is generally interested in changing the world to make it a better place. I also strongly identify with the concept of radical hope! I got really down about people being so hateful this year - if you didn’t know, the internet can be awful…
People fear what they don’t understand.
And this backlash has happened before in art history, with impressionism, dada, pop-art, the camera, the digital camera, photoshop, digital art… and now AI, which is probably the biggest change art historically, that most of us have been alive for.
So I really tried to listen, and what I kept hearing was the fear. Not only were people kind of afraid of AI becoming sentient and taking over the world, but they were also very afraid it would cause artists to lose their jobs, it would take over and kill art and creativity, and it would degrade the value of art. Everyone also seems to think all this creative AI was made up by big tech bros with an evil agenda to make money, and completely misunderstand how any of the technology actually works.
What I’ve heard about problems with AI are really systemic issues and total misunderstanding.
Which is why I chose to do the REPRESENTATIONS collaborative project for Taking. Up. Space. this year. It’s so important that people understand how this stuff works, and how to use it, because it’s here, and it’s happening, and you all need to be part of it! How else can you influence its direction?
This project has its own tab on my website, and will be virtually exhibited during May/June of 2023. Click Here to visit the page and learn more.
/describe
There’s a new feature in Midjourney, called Describe. You upload a photo and give the bot the /describe command. It gives you 4 descriptions the uploaded image. I’d played around with it with some images I had saved while testing the new rating system and voting on images from the new version (version 5). It was pretty cool to get descriptions about the art, especially because it links to any artists it mentions. It’s a neat way to explore styles and come up with new prompt mixes. I uploaded my own art as well, and it didn’t turn up artists I thought it might, and turned up some that haven’t influenced my work, but that I could see visual similarities in.
You can test out these new prompts by clicking the 1, 2, 3, or 4 buttons below, that correlate with the prompts above.
For testing these new features, there are places within the community where you can chat about them, give feedback, etc. Of course, someone uploaded a selfie, and the results were quite funny. It made me wonder… and I ended up quite enjoying results of my own 😂
The results were ephemeral, so they didn’t stay around and I didn’t realize it to get screen shots, but I was excited to see the terms “nerdcore” and “health goth” (I’m not sure what that is, but it sounds appropriate), as well as “apron with hair” and “distinctive nose” …. that’s right, all my Jones nose fam out there, it calls it “distinctive”!
But I wonder what “teethcore” is, and what “in the style of focus on joints/connections” even means?
AI is SO weird, and I love that…
Please enjoy these alternate versions of me, generated with all the weirdness that is a health goth, teethcore, dinopunk, socially minded, genderless, extremely gendered, deconstructive, light hearted, master of ink, cripplepunk, humanistic empathy, smilecore, photo taken with provia, woman with purple hair and a distinctive nose…
And, as for the links to artists:
It’s a super cool feature, because I am a nerd who loves art and art history, and one of the first things I geeked out about with AI text-to-image stuff was how much interest is being created in art history, and making it so accessible to people it wasn’t accessible or interesting for before! EVERYONE LEARN ART THINGS!
I wonder if other traditional artists have tried this out with their own work, and what results they got about artistic influences? If you use Midjourney, have you tried out /describe yet?
We have enough.
Expressions of Radical Hope: “We Have Enough”
Every week, I listen in to Midjourney Office Hours. I find so much of it fascinating, and I take notes to update my learning collective people to fill them in on changes, new features, and philosophy. There is a channel on the Midjourney Discord for the “daily theme” - you can choose to get notified when this theme changes or not, but it’s people in the same channel making art on the same topic. Often, this daily theme changes to reflect something discussed in office hours - like robot squid. I usually include some of these images with the update to the learning collective. This week it wasn’t really related, and I felt inspired by all the topics of discussion in general and made some abstract painting images. I try to prompt shapes, colors, styles, and materials I actually use.
I also used combinations of these ideas: new computer science, art history, biodiversity, responsibility, exploration, community, infinite compute power, radical hope, a beautiful future, post-scarcity, and monkeys looking for bananas in new places. (😂 It's always a good time!)
After making these images, I also used the /blend feature to really get something I was feeling. I took this image into Photoshop and used the neural filter Super-Zoom to upscale. Next up, I opened the upscaled image in Adobe Fresco to get painting - the live brushes are really lovely. If you’re a traditional artist working with AI, someone who has painted in Photoshop forever, or a new artist starting with AI-generated images and learning to paint digitally, definitely check it out.
I’m loving the tools that Midjourney has for making art, but also the community. So many acknowledgments of systemic issues and how we can have a better future. So much awareness that we have enough, for everyone. If I could see this community as a sea of people, I imagine many of them have these sparks of radical hope glowing within them… (Now there’s another thing for me to go prompt) 🖤✨
Irish
Who knows what truth is behind Ireland’s lack of snakes or St. Patrick, but I’ve always been curious about my Irish heritage, and the pre-Christian (Catholic, of course) roots. So, I did some photographic style prompts in Midjourney today involving pagan snakes, Irish lasses, and lots of clover 🍀
Dispelling Misinformation
I started using AI in my art practice a few years ago. I came across an article about Playform, and joined their artist studio. I had no idea how much I would love it, I was moving towards a glimmer of something catching the light, to see what it was. It felt reflective and magical, and it fit right into my work.
My affections towards technology are at least partially genetic. When I look at the familial lineup of mechanics, tinkerers, technology enthusiasts, information lovers, and wonder seekers, I shouldn’t be surprised. Many of the people close to me weren’t afraid of technology or people or ideas. And I mention this because it did surprise me when people reacted with fear and suspicion about my use of artificial intelligence in my art. (this was even before 2022 and the text-to-image cultural phenomenon)
As of now, everyone has pretty much heard SOMETHING about creative AI tools - but what they’ve heard is mostly misinformation and clickbaity opinion pieces aimed at getting a reaction. As a trained professional artist with a master’s degree, and with education in art therapy, art history, everything studio art, fine art, design and photography. Traditional media and new media, analog, digital, philosophy of art, ethics… and decades of experience, I’m absolutely qualified to speak on this.
I feel like I’m shouting facts into the wind sometimes, but then someone listens in and gets it, and it’s AWESOME. Because these tools are full of wonder, they are great for exploration, reflection, and I believe they have an immense capacity for healing and moving us forward.
One of the things I’m shouting - creative AI tools don’t “steal” other artists’ work and implement them into a kind of collage. That’s not how the AI tools work at all.
To explain in a relatable manner how they do work, I want you to imagine an art student, going with their class, to a museum, to study impressionist paintings. They look, they make sketches, they study them to figure out what makes them impressionist paintings, how the paintings were made, what they were made with, when they were made… they learn the concepts of what makes up impressionist paintings. Now, all of those students leave the museum and go to a painting studio, where they’re told to paint something in the style of an impressionist painting. Do they pull out paintings and copy them? Do they look at photographs of paintings and copy them? Or do they draw upon the concepts that they learned in order to make choices about color, composition, materials, etc.? When they reference these concepts, are they infringing upon some artist’s rights, living or deceased? No.
Another example - If you handed a group of people all some crayons and asked them to draw an apple, they could probably do it. Some might be red, some green, some more round, or some with spots, but everyone understands the concept of an apple. No one draws a bird or even another fruit. Those things are not part of the concept of “apple”, and the concept of an apple is so well trained in our minds that we don’t need an apple to be present to draw one.
Training isn’t stealing, and the original pieces of information that were studied are no longer present after training.
REPRESENTATIONS
As part of the @thrivetogethernetwork, and the Taking. Up. Space. global grassroots initiative, #takingupspace2023 I’m seeking submissions for a collaborative project, set to debut in May. This project is called “Representations” and the intent is to educate and encourage womxn to take up space and affect the future at the intersection of art and technology. All of the collective work will be used to train an artificial intelligence model, which will be used to generate a new body of work reflecting the collective. I’ll be sharing the process of creation through live sessions and videos, and the final body of work will be available as free-to-collect NFTs.
Call for art ends: February 26th, 11:59pm EST
A COLLABORATIVE PROJECT ENCOURAGING WOMXN TO TAKE UP SPACE AND AFFECT THE FUTURE AT THE INTERSECTION OF ART AND TECHNOLOGY
As part of the Thrive Together Network and the Taking. Up. Space. global grassroots initiative #takingupspace2023 I’m seeking submissions for a collaborative project, set to debut in May. This project is called “Representations” and the intent is to educate and encourage womxn to take up space and affect the future at the intersection of art and technology. All of the collective work will be used to train an artificial intelligence model, which will be used to generate a new body of work reflecting the collective. I’ll be sharing the creation process through live sessions and videos, and the final body of work will be available as free-to-collect NFTs.
Eligibility: Project participation is open to all women-identifying and non-binary artists. No knowledge of NFTs, Cryptocurrency, or artificial intelligence (AI) is necessary to participate!
Submissions:
Work must be submitted as a JPG or PNG file. One artwork is to be submitted by each participant, please select something that you feel represents your individual perspective or artistic style.
Enchanted AI Art
I’m excited to announce that the Visionary AI Art Learning Collective is LIVE!
Wait, the what what?
Okay. So I met these two fabulous women who were as excited about using AI to create as I have been, and we talked, and IDEAS! They had launched Magical Stock Art, and had been getting requests from people who wanted to learn how to make art this way themselves. …So I’ve been teaching AI for Fine Artists and AI for Creative Expression, and we’ve been testing and figuring things out. It’s been awesome to see people get inspired by the process of creating with AI art tools!
There is also a LOT of hate towards AI art tools being used right now. So let me dispatch it - with the many, many, many conversations I’ve been having, it comes down to fear, misinformation, and systemic issues.
As women, we are legendary at transforming fear into love through creativity and community.
THIS IS THE VIBE!
After I did a residency with a big community component in September, I knew I wanted to teach people how to use AI art tools, and I was already doing it as part of explaining how the heck I make my art. I believe I can make this a little less scary for people! - I genuinely LOVE people, and my enthusiasm for what others are creating is deep and authentic. I also think it’s important for womxn to pick up these tools and show up in this space because it’s crucial that we influence it!
So, I’m leading the Visionary AI Art Learning Membership! And you can join me there!
AI Art School
Curious about AI in art? Want to learn how to use AI in your established art practice, or to use AI for creative expression with no prior skills required? Join me…
I’ve started teaching classes about how to use AI in your creative practice! I’m really excited about this, because I want to share the magic that I sensed with AI in my own art practice with other artists, and develop the use of creative AI as a tool for reflective practice for anyone.
I’ll be teaching these first classes with a newly formed AI Art School, and if you’re interested in learning, there are two courses right now - one for fine artists, who already have a body of work, and one for anyone who wants to learn to use AI as a tool for creative expression. These are beginner level courses, so if you’re totally confused, or curious but don’t know where or how to start, these are for you!
The link below will take you to Rebecca Tolk’s website for further information and check out, don’t be alarmed, this is correct! I’m teaching the evening cohort of the AI for Creative Expression course, so click on that sign-up link to learn with me as your guide!
ON::VIEW Residency Finale
I’m so grateful for having been able to spend the past month in residence ON::VIEW at Sulfur Studios! Connecting with people, sharing my process, and how I use artificial intelligence in my work has been a great experience. Everyone comes at this with a different perspective, so I’ve gotten a lot of practice talking about the work and bringing people into my process from where they are.
During the residency, I held open studio hours, inviting people in to participate by painting with me. Participants were given the option of learning a little about how waves are physiologically calming, and creating a waveform painting, or doing a meditative prompt about body awareness and creating an intuitive abstract painting. With 30+ paintings in each series, the works were digitized and used to train two separate artificial intelligence models. These models then generate more work, that is a combination of everything it learned from that dataset. I comb through thousands of resulting images, and work with them further to create a final collection of images and video clips.
Here are some of the intuitive abstract results:
Here are some of the waveform series results:
It was cool to see people come back in for the finale reveal that had worked on the project with me, or checked up on its progress over time. I really liked having all the work hung from the walls as it built up, and still on display with the video pieces being shown on screens in the same space. It really gave a sense of the entire project.
The month flew by! I was too engaged in conversation all evening to get photos with people in them, so here’s one last shot of the studio before I moved out.
There is an NFT to collect for free from the project, and I’ll be sharing more from it going forward. You can collect those here: https://jenpalmerart.cent.co
I’ll also be making more prints available from this work, make sure you’re subscribed to get updates when those become available.
Thanks! 🖤
The Artist & The AI
This is a presentation adapted from a talk I gave during my residency at Sulfur Studios last month, a little about me, my work, and how I came to include AI in my creative process.
( Fast Evolving Tech Disclaimer: The data in the presentation was up to date when made, but could be different at the time of reading this)
FEATURED POSTS
