ControlNet

image

An add-on for diffusion models that gives you structural control: it locks composition to a guide input — a pose skeleton, depth map, edge sketch, or scribble — while the prompt controls content and style. Want a character in an exact pose? Feed a pose reference through ControlNet and the output follows it precisely, no prompt gymnastics needed. It is the bridge from roll-the-dice generation to real art direction. Example: sketch a rough layout of your ad, run it through ControlNet with a polished prompt, and get finished art in your exact composition.