Image 1 = this exact scene: OWNER and MANAGER on leather sofas at a brass table with the WTO skull hookah and the WTO jar in this lounge; use it for the room, the light, the objects and both men's faces and clothing. Image 2 = OWNER reference sheet. A few seconds later, the same place and light, the camera moved closer to OWNER: medium shot, waist up, three-quarter view of OWNER (45, stocky, broad square face, completely clean-shaven with smooth skin and no stubble, very short salt-and-pepper hair, dark-olive henley, tobacco-brown leather bib apron). He lowers the hookah mouthpiece, the last wisps of smoke dissolving around him, and gives a warm satisfied smile and a slight approving nod toward MANAGER, who sits at the left edge of the frame softly out of focus. Natural, restrained emotion, no exaggerated expression. The top of the WTO skull hookah with the slender black-and-gold bowl and glowing coals is partly visible at the frame edge. Warm light from a pendant lamp, lounge softly out of focus behind him. Everything in the frame is photographed together in the same shot: same light, focus and grain, natural contact shadows, real objects in the room, not pasted pictures. Photorealistic cinematic film still, natural skin texture, realistic hands with five fingers, subtle film grain. No text overlays, no watermark, no sparkle icon in the corners. Avoid: beard, stubble, mustache, different face for OWNER, gloomy faces, exaggerated expressions, deformed hands, extra fingers, duplicated people, pasted cut-out look, sticker-like objects, bartenders, plastic skin, CGI look, split screen, panels, visible seams.
Free to start · Generate videos and images with AI in seconds