cd4f4e9f-cce6-40a7-9d55-59fd8653fb63

[SHOT 3.06 | REFS: @Daniel → daniel_ref_v1.png | @Ellis → ellis_ref_v1.png | @PullmanCoach → pullman_coach_plate_v1.png] MCU of @Daniel, clean single with @Ellis SOFT in the deep background. @Daniel is centered in the frame at eye-level, tight — the composition is compressed and isolating, cutting him free of the space. His eyes are captured in the down-left position (looking down and to his own left, i.e., toward frame-left from the camera's POV) — the half-second before the recovery. Deep in the background at approximately twelve feet distance from @Daniel, camera-right of frame, @Ellis stands visible but out of focus, readable only as his silhouette and the mid-grey of his sport jacket. Small enough that identity is preserved but nothing sharp resolves. Wardrobe: @Daniel/Sept-Train, @Ellis/Sept-Train. Composition: @Daniel occupies the center of frame with the tight lens compression pushing him forward — headroom minimal (about one inch), his shoulders fill the bottom third. @Ellis reads as a soft grey-jacket figure deep in the frame's right third, behind and below @Daniel's shoulder. Background beyond @Ellis: soft olive seat backs, brass sconce warm hint upper right, mahogany paneling. Camera: ARRI Alexa 35, Cooke S7/i 75mm at T2.8 — compression, isolates @Daniel from the space, background compresses forward but stays soft. Lighting: same warm 5200K sun-side window key from @Daniel's frame-right as previous singles. Mahogany bounce fill from frame-left at 2:1 ratio. @Ellis catches only a whisper of the same window key — his silhouette edge glows faintly warm. Grade: Kodak 2383, warm mahogany dominant, camel jacket protagonist accent, honest olive-warm skin on @Daniel with the small dark mole at outer left jaw catching a soft shadow. Style: photorealistic 2.39:1 cinematic still, prestige TV production quality, tack-sharp on @Daniel's eyes especially — this is the story- critical frame — the mole at outer left jaw must render as a natural identity marker, @Ellis softly present without competing for attention.

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.