[Image Description: A photorealistic AI generated image of a French press filled with steaming coffee sitting on the counter of an English traditional style kitchen.]
Before embarking on this residency, I have been thinking a lot about the idea of ‘process.’
During lockdown, repeat processes and set routines kept me grounded. I particularly think back to buying a coffee machine. You know, the ones where you buy the fancy-looking pods, pop them in the machine, press a button and watch your espresso be poured for you at the perfect temperature. There was something so unappealing about this. I was craving a deeper connection between the process and output of my morning coffee.
Now, in 2024, the coffee machine gathers dust while I use a simple French press instead. I enjoy grounding the beans to my liking, scooping the grounds into the press, filling it up with hot water, waiting a while, pushing the plunger down and finally pouring my coffee into a mug.
Perhaps this all sounds silly, but I learned a lot from reintroducing ‘process’ into my coffee routine. It’s for this reason that I’ve previously been a bit apprehensive about using artificial intelligence in my creative practice. The idea of it felt like I was once again removing the process of making art.
Now on this residency, I feel quite differently. I’m excited to explore the ways I can use AI within my process. I predict that I’ll use AI during the research and the early visualisation stages of my projects and then take that inspiration into the 3D production work that I’ve been developing over the last few months. However, I’m also happy for any of these predictions to change.
Anyway, the initial image on this post is one of my first attempts at using Midjourney, a generative AI tool. It did a really good job, but there are a few mistakes if you look more closely. The actual plunger used to press the coffee grounds to the bottom is nowhere to be seen. Also, you can see quite a lot of liquid coffee at the top. These mistakes are really exciting because it means it is my job as an artist to figure out solutions to these errors..or even exploit the errors for creative purposes.
[Image Description: A photorealistic AI generated image of a Black woman with dreadlocks pouring coffee from the French press into her cup in front of an old kitchen table.]
The next image I have included here is me trying to recreate my mornings with my French press using Midjourney. This is the prompt I used to generate the image:
“a photorealistic image of a Black woman with dreadlocks pouring coffee from a French press into a mug in a traditional British kitchen“
What I notice in these images (and the many others I tried to create) is that the algorithms do not understand how we as humans pour coffee from French presses into mugs. In the above photo, the person is pouring from a French press into a mug from a strange angle. They also hold a random unidentified object in their other hand. I tried to fix the issue with further prompts, but I think it will take more time for me to get it right.
The last thing I’ll add is that the image descriptions used in this post were supported by AI, but I’ll go into more detail on that in another post.
This is all part of the fun and I’m excited to see what will come of these AI experiments.