These were today's experiments in aggressive prompting over unrelated generative images I've made before. Some of the results were interesting, and I feel like I learned something new about the way the machine works. In this case, I'm using the renders as guideless noise paints. Unlike noise paints, which I usually use to control the machine, what I'm doing here is exploratory and collaborative. At least on the short form pieces.
At the same time, I'm working on developing the longer form collage process, and some of these pieces include that. A couple of them are layered the old fashioned way, and composited in Clip Studio. I've notated all of these pieces for long and short process, if you're curious. This is also the first time I'm working seriously with section divides.
That's where you chop your image into sections and subsections, and re-render pieces of it selectively to achieve the effect or look that you're shooting for. Ai's can be really muddy default, and sectioning them off with this method improves the resolution and lod.
I'm also carrying over the lessons we learned last week about framing by studying magazine cover layouts, and the work we did the week before with color theory. This is incremental progress, for sure.