Why text-to-image AI keeps failing at scientific figures (and what actually works)

Over the past month I've been trying to replace my "spend half a day in Illustrator drafting figures" workflow with AI tools. I tried Midjourney, GPT-Image-1, DALL-E, Stable Diffusion fine-tunes, generic diagram-from-text tools, and finally a purpose-built scientific illustration tool. Only the last one actually worked for figures destined for a peer-reviewed paper. This post is the autopsy on why. The three failure modes of generic image AI on figures 1. Label hallucination...