Same prompt. Same reference photo. Different result (with a consistent style).
And the process of resubmitting the prompt and reference image to Midjourney lasted all 2 seconds.
(There is literally a ‘????’ button you can click to resubmit your request).
To reiterate my point from yesterday:
AI hyper contracts all the while, work, learn, trial and error between ‘idea’ and ‘final creation’.
I didn’t have to explore a new location, hire models, monitor the weather, control lighting, edit film or change lenses to continue experimenting here…
All it took was two clicks. (Spooky, no!?).
It feels like a creative cheat code…
So what’s the difference between building a photographic style manually and doing it with AI?
(No surprises here) it’s different in almost every way. In every way except one.
I could be way out of here, but this is how I’m starting to see it….
The process of creating your own art style is different in every situation, but the formula it’s the same. This is what I mean…
The formula:
Personal taste + influences = new art style.
(The stronger your personal taste is, and the more influences you draw from it, the more unique your style becomes).
This formula seems to remain the same regardless of the process.
Process vs Process:
The manual process for running that formula (in the case of photography) might look like this:
Take in a range of influences as you test different film stocks, digital sensors, formats, compositions, lenses, camera bodies, lighting effects, subjects, set styling, chemical processing, digital post-effects, etc.
Repeat that process over years of trial and error until you have a new photographic style.
The AI process looks like this:
Give the AI your own original photos (that reflect your personal taste), describe the scene you want depicted, and list your artistic influences.
Repeat that process with 5-10 minutes of trial and error (tweaking prompts and reference images as you go) until you have a new photographic style.
Okay… but where is the line between influence and plagiarism?
There is resistance from many artists, who have a very understandable (and justified) problem with AI models that allow individuals/companies to mimic their artistic styles almost 1:1.
I’m not here to mimic, but to mix and recreate.
That’s a nice feeling – but it doesn’t answer the question: where is the line between influence and plagiarism!?
For me, I draw the line with a simple question:
If [artist(s) you’re using as influences] would hold an exhibition featuring the AI-based work you created:
Would everyone be shocked by the new direction of their work and the apparent departure from previous styles?
Or better yet, if the work didn’t have an artist’s name next to it, wouldn’t viewers know who was responsible for creating it?
If so, then you’re good. It has become his thing.
If not, it’s too close to that artist’s style.
(It’s not perfect – but it works).
Okay, more tomorrow in Part 4.