Back to Articles
The Shape Of The Experiment From Prompting To Research Keeping The Loop Short A Pipeline With Handles The Target Image The Lineage How The Agent Chose Its Levers First, Make The Image Legible Then, Learn What Was Not The Bottleneck Repair The Semantic Order Finish Conservatively What The Run Suggests Closing References Disclosure. This experiment was supported by JarvisLabs. I used JarvisLabs GPU instances and the jl CLI to run candidate generations in parallel, fetch the results, and shut the machines down after the run.
The first useful thing this experiment reminded me of is that image generation is not really a prompting problem.
Or, more precisely, prompting is only the part that is easy to talk about. The real work begins after the first image disappoints you in a specific way. A floor collapses into a shelf. A telescope appears in the wrong room. A composition looks beautiful, but the thing you asked for is not actually there. At that point, the question is no longer how to write a prettier sentence. The question is what to change next.
That was the loop I wanted to build.
