Image - 2026-10-27 13:31
Art style: Cinematic Realistic. Ваган standing in the near foreground; Мариам standing further back in the frame. Ваган is standing on floor in the near foreground in the midground. Torso in three-quarter turn to screen-right. Head in three-quarter turn to screen-right. Eyes on Мариам. Holding jewelry. Pleading. Ваган wears shirt. Мариам is standing on floor further back in the frame in the midground. Torso in three-quarter turn to screen-left. Head in three-quarter turn to screen-left. Eyes on Ваган. At sides. Sad. Мариам wears dress. Medium shot at eye level, 9:16. Vertical framing. Key light side, soft. Focus: couple. Dominant palette: warm beige, gold. GAZE LOCK: Ваган head in three-quarter turn to screen-right eyes on Мариам; Мариам head in three-quarter turn to screen-left eyes on Ваган. This is a single frozen instant (action start) — 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. Character identity reference (face, age, build and clothing only): - Мариам: армянская женщина сорока восьми лет, красивые черты лица, темные волосы с проседью, мудрые глаза, изящная фигура, спокойное выражение, естественное освещение на нейтральном фоне The SCENE description determines the cast, number of people, actions, setting and framing. Include every character it calls for together in this scene; do not turn it into a solo character portrait.
Free to start · Generate videos and images with AI in seconds