6cec3a2e-0724-47f3-95e6-7ac269e8af37

[REFS: attach @Aidan face reference image] Medium close-up of this man sitting on weathered wooden porch steps, his body turned to face the woman on his left. Same framing and distance as the companion shot of the woman — intimate, close, real. He is looking at her. She is on the far left edge of frame — only her shoulder and oatmeal wool sweater visible, soft, out of focus. His face fills the right two-thirds of the frame. He is about to speak — mouth slightly open, brow furrowed gently, searching for words. Behind him: weathered grey porch railing, the grey Atlantic and coastal fog beyond, all soft. Overcast late afternoon, diffused light from the left where she sits. Faint amber cloud-break catching the edge of his jaw. He wears a faded navy henley, sleeves pushed to elbows. Shot on full-frame mirrorless, 50mm at f1.8. Natural light only — no artificial source, no fill, no bounce. The light falls where physics puts it. Hyperrealistic at the level of a documentary photograph — real skin with pores and imperfections visible, real stubble, real weathering, real fabric. Nothing smoothed, nothing filtered. 9:16 vertical. negative prompt: cinematic lighting, color grade, beauty filter, smooth skin, airbrushed, CGI, 3D render, anime, studio light, fill light, reflector, lens flare, horizontal framing, looking at camera, smiling, standing, woman fully visible, indoor, artificial light, glamour, male model

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.