Three Months to Book Cover - by Kenneth Cross
Restless Forge
SubscribeSign in
Three Months to Book Cover<br>AI Did NOT Make This Easy
Kenneth Cross<br>Aug 07, 2026
Share
I’m bad at art.<br>That’s not an exaggeration. My four year old daughter is rapidly approaching my skill level, and that’s okay. Most of the time.<br>A few months ago I finished a manuscript dedicated to my wife: Dinosaur Road. I wanted to see this particular story fly, but self-publishing has one wall that towers over the rest for someone who can’t draw: the cover.<br>In 2026 ChatGPT and Gemini both do real image generation. I have a laptop, a terminal, and a fleet of tools that are supposed to make this easy.<br>Right?
Subscribe
First Missteps with Claude
Despite a cramped usage ceiling, Claude is still my tool of choice. I started by uploading my manuscript and asking for some advice on cover design, but I quickly realized that this wasn’t going to work.<br>Maybe part of the reason I get along with Claude is that we’re both bad at art. No matter how much it tries to sell me on Lissajous Curves and how beautiful they are I realize that its preference is likely due to the fact that it has to generate everything programmatically. This is because Anthropic hasn’t added imaging capabilities to its ecosystem.<br>The initial results from Claude:
This image is quite alARMing<br>This wasn't usable, but it also wasn't a wasted effort. It yielded a rough composition to hand to models that actually do images: ChatGPT and Gemini.<br>The first 80%
I turned to the other members of our group project: ChatGPT and Gemini. I fed in the design from Claude as well as the manuscript and asked for a cover based on the original image. And you know what? It looked good!
Yellow lane markers drifting, a doubled Gemini watermark, and too many palm trees. Close, not done<br>But not good enough for a professional cover. Now it was time for the last 20%, which I assumed would be the easy part.<br>Crude Attempts at Inpainting
I went to Gemini's annotation tool, circled the problem areas in red, and prompted: "Fix these areas. Edit only what's marked in red."<br>It sort of listened. Models will follow an instruction’s spirit more reliably than its letter, and “only what’s marked in red” turned out to mean “mostly what’s marked in red, with some improvisation.” The results were clunky and (worse) unpredictable. The same prompt would produce different kinds of wrong.
Before -> Masked -> After with minor improvements<br>My lesson here: if you need the model to respect a hard edge then you need precision. A highlighted region and a polite request just aren't enough.<br>So I had three options:<br>Burn through hundreds of re-rolls hoping for a lucky one
Pay for a dedicated inpainting service
Build my own pipeline
I picked the third option, mostly out of stubbornness.<br>Resurrecting Automatic1111
I have a fossilized version of Automatic1111 on my laptop from the prehistoric year of 2024. Back then it worked pretty well for playing around with image generation using custom models.<br>But a lot has changed since 2024.<br>This particular attempt never got off the ground because of one thing: VRAM.<br>SDXL didn’t exist back when I ran this last, and my casual 8GB graphics card is not up to the task of serious image generation.<br>Moving to RunPod
Pivoting, I decided to rent a GPU by the hour and run a container with Automatic 1111’s successor, Forge. If you decide to go this route for image generation there are three mistakes I made (so you don't have to):<br>Container images matter, and it's easy to grab an unmaintained one or get lost in a sea of community forks of the "real" version.<br>The Solution: run Better Forge CUDA12 Light
When you stop a pod your files don't necessarily survive.<br>The Solution: use a persistent storage volume rather than the pod's temporary disk.
RunPod only stocks a limited number of each GPU type per region, and popular cards sell out.<br>The Solution : either wait or pick a different (probably more expensive) card.
The Style Inconsistency
Forge was finally running with a model loaded from Civitai after several days of fighting, but there was still plenty of turmoil ahead. In my first inpaint attempt, something immediately went wrong.
Like if Banksy painted a tiny patch of Van Gogh’s canvas<br>If you take one artist’s style and try to copy it into another artist’s painting then the results aren’t going to be great. This is exactly what happened when inpainting with a different model. You cannot patch one model's output with a different model.<br>If you need consistency, you have to generate and edit in the same model, start to finish. No exceptions.<br>Starting from Scratch
Two months in, I made the hard decision to start over. If consistency was what I needed, then I needed to use the same model all the way through. To simplify further, I left the car and passengers out of the base image entirely. Those could come in later through inpainting, once the environment was locked.<br>Using Claude to draft prompts...