Art style: Cinematic Realistic. Maria standing in the near foreground; Darni standing further back in the frame. Пустое пространство магазина между ними. Maria is standing on стремянка in the near foreground in the background. Torso facing away from camera. Head in right profile. Eyes on books. Касаются полки. Мечтательность. Maria wears fixed_appearance. Partially behind none. Darni is standing on пол further back in the frame in the foreground. Torso in three-quarter turn to screen-left. Head in three-quarter turn to screen-left. Eyes on Maria. Опущены. Скрытая тоска. Darni wears fixed_appearance. Partially behind bookshelf. Medium-wide shot at eye level, 9:16. Horizon mid. Сложная композиция с двумя персонажами на разной глубине. Foreground: книжная полка. Midground: фигура Дарни в тени. Background: Мария на стремянке. Key light back_left, dim. Глубокие тени на Дарни. Focus: Мария. Dominant palette: shadow black, muted tan, pale blue, dusty wood. SPATIAL LOCK: пустое пространство магазина между ними. GAZE LOCK: Maria head in right profile eyes on books; Darni head in three-quarter turn to screen-left eyes on Maria. This is a single frozen instant (mid action) — no motion blur, no action chained. ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ FINAL STYLE ENFORCEMENT (this is the authoritative rendering directive — it overrides any style wording elsewhere in the prompt): Render this image entirely in "Cinematic Realistic" style. Match the lighting grammar, material response, colour science, level of realism / stylisation, line weight, and shading model typical of "Cinematic Realistic". Keep the subject, composition, camera angle, lighting direction, and colour palette from the description above — but EVERY surface, skin, fabric, material, and environmental element must be rendered in the "Cinematic Realistic" idiom, not in any other medium.
Free to start · Generate videos and images with AI in seconds