Create a 4:3 aspect ratio six-panel storyboard grid, arranged in a uniform 2 rows × 3 columns layout, with a pure infinite black void as the background throughout. All panels share a locked-off camera, consistent framing, and dramatic rim lighting. Centered in every frame is the same matte-black coffee cup, paired with a pair of male hands in fitted matte-black gloves. Maintain highly consistent materials, lighting, and scale across the entire board, presenting an ultra-photorealistic premium CGI quality. No text, no logos, no extraneous objects. Panel 1 (0–1.5s): An empty coffee cup hovers stationary at the exact center of the frame. A pair of black-gloved hands enters from the bottom of the frame, settling into their starting gesture below the cup body. Panel 2 (1.5–3.0s): The right hand sweeps horizontally to above the cup rim. A glossy dark-brown espresso ribbon appears, hovering horizontally directly above the rim, with a fluid, sharp liquid form. Panel 3 (3.0–4.5s): The left hand sweipes upward to the side of the cup. A silky pure-white milk ribbon rises, spiraling around the espresso ribbon. The boundaries of the two liquids are crisp and clearly separated. Panel 4 (4.5–7.5s): Both hands pinch inward then pull apart to the sides. The milk first compresses into a dense white sphere, then expands into a soft, volumetric microfoam cloud. The espresso stream runs through the cloud, creating elegant coffee-brown marbling. Panel 5 (7.5–8.8s): Both hands push downward. The coffee and foam collapse smoothly, pouring cleanly into the cup. A complete cappuccino forms inside, its surface covered with dense, creamy microfoam. Panel 6 (8.8–10s): One hand sweeps above the cup. Fine cocoa powder settles evenly onto the foam surface. The hand exits the frame. The image freezes on a front-facing hero view of the finished cappuccino — the cup is complete, unobstructed, and in a perfect state. All panels retain only the cup, hands, and liquid elements. Fluid details are hyper-realistic and delicate, possessing physical texture and continuous morphological logic. No camera shake, no material deformation, no ghosting. The grid fully presents the core visual sequence of the commercial.
