Art style: Cinematic Realistic. Некромант standing in the screen-left third; Героиня sitting in the screen-right third. Visible space on the bed edge. Некромант is standing on пол in the screen-left third in the midground. Torso in three-quarter turn to screen-right. Head in three-quarter turn to screen-right. Eyes on Героиня. At sides. Curious. Некромант wears hooded robe. Partially behind none. Героиня is sitting on кровать in the screen-right third in the midground. Torso facing camera. Head facing camera. Eyes on Некромант. Holding blanket. Defensive curiosity. Героиня wears partially covered. Partially behind blanket. Wide shot at eye level, 16:9. Horizon center. Ending wide shot. Foreground: пол комнаты. Midground: персонажи. Background: дальняя стена в тени. Key light low, flickering. Long moving shadows. Focus: both characters. Dominant palette: black, midnight blue, dim gold. SPATIAL LOCK: visible space on the bed edge. GAZE LOCK: Некромант head in three-quarter turn to screen-right eyes on Героиня; Героиня head facing camera eyes on Некромант. This is a single frozen instant (post 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