This comment describes how the images for the “Best of LessWrong” (review winners) were generated. (The exact workflow has varied a lot over time, as image models have changed quite a lot, and LLMs didn’t always exist, and we’ve built more tooling for ourselves, etc.)
The prompt usually asks for an aquarelle painting, often in the style of Thomas Schaller. (Many other details, but I’m not the one usually doing artwork, so not the best positioned to point to common threads.) And then there’s a pretty huge amount of iteration and sometimes post-processing/tweaking.
This comment describes how the images for the “Best of LessWrong” (review winners) were generated. (The exact workflow has varied a lot over time, as image models have changed quite a lot, and LLMs didn’t always exist, and we’ve built more tooling for ourselves, etc.)
The prompt usually asks for an aquarelle painting, often in the style of Thomas Schaller. (Many other details, but I’m not the one usually doing artwork, so not the best positioned to point to common threads.) And then there’s a pretty huge amount of iteration and sometimes post-processing/tweaking.