ai image generation: a look back to art history “classics”

Where did this project originate?

My education in art history was a sign of the times I grew up in. At RISD, freshman foundation included a full year art history lecture course which was decidedly focused on Jansen’s “classical” European art historical timeline (maybe 4th or 5th edition). I grew a love of ancient art history and took as many ancient art history courses as I could—ancient art and archaeology, art and archaeology of ancient Mexico, art and architecture of India—my love of ancient art, especially Greek and Roman, I can’t seem to shake.

Much of the imagery I generate stems from this classical romanticism. Ancient ceramics and mosaics, red- and black- figure pottery unburied from the earth and excavated from deep beneath the sea was the starting point. Then mutation occurs. Images are meant to sprout appendages and encrusted surfaces to echo accretion, mutation, and decay.

Image generated with Hugging Face Stable Diffusion 2.1

Image generated with Durer ai (now Exactly.ai)

ai image generation: mutants from the sea revisited

Imagine a world where the effects of climate change accelerate creation and destruction. Sea creatures use sunken artifacts as homes, die, erode, replicate, repopulate, reattach, reanimate… a few of these guys are spending time in Salvador-BA Brazil at ARTELLIGENT, the International Art & AI Festival until end-November.

It takes more time and effort than one might think to get a visual convergence to create images like these. 

The project provokes reflection on identity, imperfection, and cultural continuity, showing how the past and the imaginary coexist with the digital. These are meditations on how myth and matter endure, evolve or disappear in a world of constant change.

Ai image generator: the philosophy

It’s been a while since I started this AI image project, so I wanted to share why I’ve been working with it and how it’s shaped my practice.

At first, I was simply curious—wondering if AI could help bring some of my ideas to life. I quickly saw how useful it is for fast iteration and brainstorming, but also began to recognize it as something bigger: an inevitable reality and part of our shared cultural consciousness.

In my work, I don’t treat AI as a replacement for the hand, but as an extension of the visual language we all inherit and reshape. It’s a way of looking at technological imperfections and mutations—images that, once seen, can’t be unseen and inevitably seep into my evolving vocabulary.

I use AI critically, echoing its distortions to highlight how mutation plays out in both consciousness and material form. At the same time, I’m aware of its complications—questions of authorship, labor, and originality. Wherever I have choice, I never use images, styles, or prompts from other artists.

Though touched by AI and echoing digital distortion, my work ultimately insists on the presence of my own invention and hand. I still experiment with AI, though less than when I first began, as its deviations have started to smooth out, leaving less room for chance and mutation.

Some of my earliest images generated with Hugging Face Stable Diffusion 2.1

ai image generator: craiyon improves

I’ve just gone back to try Craiyon image generator again after a long hiatus. When I used it originally I wasn’t impressed with the low-res output and super-basic images.

I’ve only generated a few images but it seems there might be some possibilities.

Here my prompts were for mutated ancient Roman vessels pulled from the sea after millennia. Craiyon fully determined the backgrounds without my input. As the prompts are tweaked the images are starting to become more strangely altered. The process takes a good amount of revisioning to approach what I envision.

I don’t often keep ai imagery in front of me when I create, or if I do I use it as a jumping-off point. Sometimes, though, bits of these images appear as I work, almost as through muscle memory.

Images generated with Craiyon ai.

ai image generator: back to basics

I’ve been disillusioned lately with the difficulty of finding ways to generate new images for free, options are getting fewer with more restrictions. I’m also not enamored with how much of the ai images look aesthetically with the improved ai engines. So today I went back to Stable Diffusion 2.1 for old times’ sake. It’s kind of charming in its inability to create anything complicated. I’m aiming for pots that are growing little shelves but I’m getting pots on shelves. Some are anthropomorphic, so it’s understanding and rendering some parts of the prompt that it can. This is strange old archaeology with a twist!

Images generated with Hugging Face Stable Diffusion 2.1

ai image generator: mutations and $

Opportunities for chance and organic inconsistencies can create strange and unique images. Engines’ need for monetization are making it more difficult to generate for free. Complicated prompts are creating much more specific and accurate visuals, especially when a personal model can be created. As model output gets more realistic, it becomes more difficult to create visuals with mutations.

Images generated with exactly.ai

ai image generator: flux ai

Every now and then I’ll try out a new image generator. Of late they are all generally creating more accurate images (eek), so it’s getting harder for me to create mutations that are aligned with the aesthetic I’m seeking. Today I tried out flux.ai, with similar results. It takes a lot of time and tweaking of prompts to create what I’m looking for so I am doing less and less ai generation.

Images generated with flux.ai

ai image generator: whimsically weird

I recently happened upon some amazing Japanese toy prints from Unai no tomo: Catalogues of Japanese Toys (1891–1923), highlighted by Public Domain Review. So I hopped over to Leonardo.ai and created a few Japanese-toy inspired ai images using some of my key word prompts. It’s wild to see what each ai engine picks up and prioritizes from popular culture, in this case color schemes, shapes and likenesses. I’m not sure how something from this might (or might not) be incorporated in my work but time will tell…

Images generated with leonardo.ai

ai image generation: adding checkers on 3d surfaces

As ai gets better how can it handle complicated surfacing prompts like adding checkerboard to forms? Added to my current subjects and themes? Clearly these additions are fun but not particularly precise. The mutations (especially) make these images publish-worthy.

Image generated with Leonardo ai

Image generated with Stable Diffusion 2.1

Image generated with Meta ai

ai image generation: eyes, eyes, eyes

Each ai generator has its own personality and small word tweaks can make a big difference in what is generated. A small sampling of the range I achieved when prompting about things like eyes, ceramics, antiquities and the sea follow— with a focus on eyes….

Image generated with stable diffusion 2.1

Image generated with meta ai

Image generated with bing ai

Image generated with ai playground

Image generated with exactly.ai

ai image generation: wall relief

Sketching ideas to jump off from with ai has been a main focus for this ai project. Ceramic wall relief has a long history and seems to be making a resurgence in the contemporary art world. Here are a few ai-generated relief installation concept close-ups with my spin.

Images generated with Bing.ai / Dalle-2

ai image generation: combining real and ai

One of the things I have been playing with is imagining my artwork in a fantastical ai gallery space. I mostly use ai generated gallery images that have clues that they are unrealistic (such as scale, strange proportions, flawed people, odd patterns, etc.) and I don’t put much effort if any into retouching to make it all more true to life. A quick look during a scrolling session could have someone thinking otherwise in some instances, but any of these images I post are labeled with what is mine, what is not and the ai generator used. It is fun to see what these combinations bring.

Gallery images generated with meta ai with my work added.

Gallery images generated with bing ai with my work added.

ai image generation: red and black

I often look back at the history of art and ceramics for inspiration, especially Greek and Roman black and red figure ware. Whether it’s a shape, painted scene or other aspect, I adopt something as I create. One of my areas of obsession is the use of red and black. This was one jumping off point in the prompts of many of my ai pots. I’m also constantly thinking about what pots would look like had they been buried in the sea for many centuries and retrieved. I visualize their appearance once they are fully or partially restored or “recreated” incorporating what’s attached.

Images generated with Deep ai.

ai image generation: symmetry

As ai gets more accurate it is becoming more difficult to create vessels with asymmetry. Could this be because of historical and contemporary ideals of art and the collection of images as sources? Because so many find symmetry pleasing? Whatever the reason, it is hard to break through. Some models are especially challenging, particularly in visualizing the outer silhouette.

Images generated with Leonardo.ai

ai image generation: mutation

How will life under climate change affect how species develop and adapt? What mutations will occur? As I research ideas and imagery, the lion, deep in symbolism and history keeps tugging at me for a number of personal reasons. These are a few images generated that incorporate lions and….

Images generated with durer.ai / exactly.ai