TL;DR



HiDream-O1-Image 8B Full raw outputs collapse on plain Japanese prompts — both instruction-following and aesthetics fail at once
Tried to swap to Dev-2604 (preference-tuned, 3.5× faster). It's better aesthetically but the gap is small in our use case, and worse — the 96GB GPU can't host both models alongside the rest of the stack
Pivoted...