A prompting technique for multi-character AI video scenes with back-and-forth dialogue: instead of one freeform description of the exchange, the prompt is structured as a per-second timeline (e.g., across an extended 15-second Seedance 2.0 clip) specifying what happens or who speaks at each moment, so the dialogue lands in the correct order rather than overlapping or scrambling.
Used alongside Higgsfield @-Element Asset System — with two or more tagged character elements (e.g., @MateoDino, @NaomiQuinn) placed in the same shot — the per-second breakdown is what keeps the exchange coherent once the characters are already visually locked in. It complements continuity techniques like 180° Rule for AI Video Dialogue Continuity and Reverse-Angle Environment References for Dialogue Continuity, which govern spatial/camera coherence across a dialogue scene, by governing temporal/verbal coherence within a single generated shot.
Apply: For multi-character video prompts with dialogue, extend duration (e.g., to 15s) and write the prompt as a timed, second-by-second sequence of actions/lines rather than a single paragraph, especially when two or more tagged elements are exchanging lines in one shot.