These images were created for John at The Window at Delaware Street. He requested I generate ai images tied to the theme of “driftwood” for an exhibition. These are composite ai images created with one of my models on exactly.ai. Many thanks to John for the opportunity to create for The Art of Driftwood!
Images generated with exactly.ai
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
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
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
These mutated beauties speak for themselves. As seen on instagram collab with exactly.ai.
Images generated with exactly.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.
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… These are three of my favorites.
Images generated with exactly ai.
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.
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
A rewarding part of playing with ai has been collaborating with exactly.ai and getting to articulate why I enjoy using their image generator. Below is a series of my images cross-posted on Instagram and my answer to “how do you use exactly.ai?”
Images generated with exactly.ai
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
One of the things I’m curious about with ai is how it creates various textures. As it gets more accurate, the textures are getting more varied.
Images generated with Leonardo ai
I have always had a fascination with archaeology and the sea and I continue to circle back around these topics. For quite some time I mainly worked in printmaking and multimedia, but I’ve recently refocused more around ceramics and drawing. This has led down an interesting path both in terms of concept iteration and in what I’m producing.
I started thinking about ceramic vessels— if sat in the sea for a long time what would accumulate on them and how could they mutate and take on a life of their own. I’ve continued to follow this line of thought to see where it will bring me both conceptually and visually.
Bing’s Dalle-2 was a fun place to play out some of these ideas and concepts. Here are some initial iterations of vessels with the eye as an inherent part of a seashell, sometimes manifesting as a pupil (hole) or an operculum of sorts. Though they are symmetrical they are not too uniform so there is an uncanny handmade quality to them. The ceramic texture are spot on as are the imperfections.
Images generated with Bing.ai / Dalle-2
I’ve been using Freeform as a digital sketchbook and to track series of ai generated images in a sort of look book. It’s a great way to quickly create pages with image groups and it prints nicely. It has remove background and snap to grid features that help making quick layout.
Images generated with Stable Diffusion 2.1. Layout in Freeform
Images generated with Stable Diffusion 2.1 and Exactly ai / Durer. Layout in Freeform
So at that point last summer, I was generating lots and lots of ai images for concept and visual iteration. Playing with these images led to some fun digital collages.
Invaders Digital collage with ai 2023
Illuminate Me digital collage with ai 2023
Liar Digital collage with ai 2023
Meta ai’s Llama-3 feels pretty much like Bing’s Dalle-3. Images generated with the same prompt seem to live in the same family. Here are more pepto pink images to compare to those from Bing in the previous post. Though these are supposed to be ceramic they look more like glass to me.
Images generated with Meta.ai
Playing with Bing’s image generator I found Dalle-2 to be my favorite version. The images I started generating in early August had personality! I particularly liked the mix of realism and quirky ai oddness. Bing has moved on to Dalle-3, which I find to be too over the top. Every image generated is completely covered in stuff from top to bottom like it’s trying too hard and there is no nuance to these images. See the difference between the photos below using the same prompt, Dalle-2 first, then Dalle-3. Dalle-2 is no longer available for free unfortunately. I wish it was, I miss it!
Images generated with bing.ai / Dalle-2
Image generated with bing.ai / Dalle-3
Things started to get more interesting when I realized I was an early adapter for durer.ai (renamed exactly.ai). I had access to model creation using my own images. This enabled me to develop a “signature look”, and ownership of the images.
I used images I had previously created with ai and photos of my artwork to train models. This better aligned my ai iteration to my imagined ideas… sometimes. Much of what is generated is not up to snuff, but the impact of using my own artwork and the element of random generation has led to new veins of thought.
Image generated with durer.ai (now exactly.ai)
Screenshot of durer.ai model creation page and images used to create the model. Images generated with durer.ai- now exactly.ai, stable diffusion 2.1, ai craiyon, dream.ai, and photos of my then recent ceramic work (positioned sideways)
So it may seem easy, but having images in your mind is a far cry from what you may get with text to image prompts. It’s an art of sorts to push image makers to create something that is “successful.” The process is similar to photography in that many, many images need to be generated and then the best is selected through an editing process. Image generation has the added step of writing, tweaking and re-editing the prompt many times to try to veer the generator in the desired direction. As I continue to generate images, prompt writing is a constant challenge. The prompt is a living, always changing and evolving part of my ai project creative process now.
Images generated with stable diffusion 2.1
As I was trying different image generators I discovered durer.ai, which has since become exactly.ai. Its models at the time provided a varied and complex range of more mature art styles, and for me an interesting photo-realistic aesthetic. This generator has continued to pique my interest as it has matured.
Images generated with durer.ai (now exactly.ai)