The Render

I build guitars for a living. That is the first thing to know, because it explains everything after it.

I have spent over ten years at a bench, working wood by hand. It is slow. You measure twice because there is no undo on a piece of mahogany. That was the whole shape of my creative life until 2020, when I started teaching myself design at night. Graphic manipulation first, then whatever came next. In 2023 I found AI image tools, and something clicked that has not unclicked since.

I want to be honest about how it started, because it was not serious at all. I typed haikus into a prompt box to see what the machine would do with them. I fed it emotions and watched how it read them back to me. There was a pull to it, the kind a slot machine has. Throw a few words in and see what falls out. I still do it. It was never really about the picture at the end. It was about the small back and forth with the tool.

I needed a real portfolio. One place to hold the absurd creature videos, the wizard shorts, the brand work for Adobe and Topaz, the Stor-AI Time series. Something I owned, not a profile on someone else's platform. I didn't want to wrestle a template or hand-code it from scratch. So I built the whole thing by talking to Claude Design.

It worked. The site is live at glennwilliams.net. But "I described a website and a website appeared" is the marketing version, and it skips the part that actually matters. Here is the real account, and what I'd tell you before you try it yourself.

I have spent the last few weekends at my computer trying to land on the next experiment to run. Something to test, something to document, something to publish. Nothing has come. I open Firefly. I close Firefly. I look at the queue of half-formed ideas in my notes and none of them want to be a thing today.

This is what burnout looks like in my chair. Not exhaustion exactly. Not a lack of time. Just a flat, glassy refusal of the work to start.

This article documents the creation of Episode 1 of The Aperture, a five-part psychological cosmic horror miniseries built using a stack of AI generation tools. Episode 1 runs 3 minutes 21 seconds. It tells the story of Elias Marsh, a Brooklyn painter who realizes he hasn't been the one painting his work. The episode was produced through a workflow combining still image generation in Adobe Firefly and Nano Banana 2, video generation in Seedance 2.0, voice generation in ElevenLabs V3, and final assembly in Adobe Premiere Pro.

What follows is the actual production process. Some of these decisions were good. Some I had to walk back. The goal of documenting both is so that anyone attempting similar work has access to the iteration trail, not just the polished end state.

I spent two days this week running a single investigation. The question was simple on the surface: when you want a photorealistic image of some object being overtaken by biological overgrowth, a camera wrapped in coral, a typewriter sprouting mushrooms, what phrasing actually produces the best integration between the object and the organism?

The answer turned out to be more interesting than the question. What started as a prompt comparison ended as something closer to a map of how Nano Banana 2 actually reads language when you ask it to combine two things.

Forty-eight images, ten variations, two subjects, one rubric. Here's what I found.

I wanted to know exactly how much control you have over a finished graphic in NB2. Not concept control. I'd already tested that with impossible subjects and surrealist ad campaigns. Pure graphic design control. Typography. Color palettes. Borders. Seals. Layout grids. Ribbon banners.

So I designed a test. One brand. One product. Six variations. Each one adds a new layer of design instructions, from 5 up to 24, to see how far NB2 follows the brief before it stops listening.

I wanted to know something specific: if you give NB2 an impossible concept and tell it to sell it, does it just slap on some ad-looking text? Or does it actually think like an ad agency?

So I ran a test. Forty images. Ten variations. Two rounds. The concept: take things that can't physically be sliced open, clouds, ocean waves, flames, lightning bolts, the aurora borealis, render them as photorealistic cross-sections revealing their impossible internal structure, and frame each one as a luxury advertisement for a different product category.

What I found was bigger than I expected.

I've been running a daily analytics tracker on my X account for months. Every impression, every follow, every bookmark, every profile visit, logged and calculated down to the decimal. When I hit four consecutive payout cycles, I did something I hadn't seen anyone else do: I mapped every available metric against what I actually got paid.

The results surprised me. And if you're a creator on X trying to figure out what's worth your time, they might surprise you too.