30c791bb-f0e9-4efa-933a-dc47e53d248c

[REFS: @Aidan, @Callum, @Elena] The cottage kitchen, same evening, moments later. @Callum and @Aidan face each other across the small kitchen, @Elena between them at the counter, her back against it, looking between the two men. A standoff framed vertically. @Callum top of frame, standing tall in his overcoat, hands clasped behind his back, chin slightly raised — authority, patience, control. His expression is a mask of politeness stretched thin over something colder. @Aidan bottom of frame, now standing, beer abandoned on the table, his body squared toward Callum, feet planted — a man who builds things with his hands facing a man who destroys things with words. His jaw is locked. His fists are not clenched but his fingers are straight and stiff at his sides. @Elena centre frame between them, the axis of the conflict, her eyes moving from one to the other, her hand behind her on the counter gripping the edge. She is the fulcrum. Both men are talking past her about her. Shot on full-frame mirrorless, 35mm at f2.8. The overhead bulb creates hard downward shadows on all three faces. Hyperrealistic — the wealth gap visible in every texture: Callum's tailored wool against Aidan's faded work shirt, Elena barefoot between them on cold tile. The small kitchen making the confrontation claustrophobic. 9:16 vertical.

Generate a single, hyper-realistic character reference image (strictly no collages, text, watermarks, or borders). The image must feature a cinematic, three-quarter portrait of the described character, maintaining a sharp, tack-focused emphasis on the face with natural skin textures, pore details, and realistic micro-expressions. The lighting should be cinematic and directional (e.g., subtle split or Rembrandt lighting) to give depth, blending seamlessly with the environment specified in the character description. The character must have a natural, living presence, looking slightly off-camera or directly at the lens with a subtle, context-aware expression. Ensure the full head, neck, and upper shoulders are completely unobstructed. This image serves as a high-fidelity identity blueprint for temporal-consistent video generation.