CHARACTER 1] says in a [voice description]: “[LINE 1]”. [CHARACTER 2] replies in a [voice description]: “[LINE 2]”. Ambient pub noise, glasses clinking, low background chatter. Camera slowly pushes in. No subtitles, no text on screen.
Example for your video:
A cinematic, photorealistic medium two-shot of a large brown-furred Bigfoot holding a whiskey glass and a pale white-furred Yeti with hands folded, sitting side by side at a dimly lit wooden pub bar. Stained-glass lamp and bottle shelves behind them, blurred patrons drinking beer. Warm tungsten lighting, shallow depth of
