That and *control,* there's an enormous difference between letting a model just ...

		jsheard 40 days ago \| parent \| context \| favorite \| on: Ovi: Twin backbone cross-modal fusion for audio-vi... That and control, there's an enormous difference between letting a model just YOLO a prompt, filling in 95% of the details with vaguely plausible whatever, and getting a model to execute on a meticulously planned out shot with every last detail in order.