cdbbfe24-d574-40ba-abac-5527cc09bff3

[SHOT 3.07 | REFS: @Daniel → daniel_ref_v1.png | @PullmanCoach → pullman_coach_plate_v1.png] MCU of @Daniel, clean single. Matches the compression and framing of 3.06 for edit consistency but @Ellis has racked further out of the deep background — either moved back another foot or is now positioned outside the frame — leaving @Daniel truly isolated in the compressed space. @Daniel's chin has lifted a fraction from the 3.06 recovery position; his eye-line is locked forward-and-slightly-frame-left on off-camera @Marcus. Mouth is captured mid-line, subtly open — a controlled speaking posture, not exaggerated. Wardrobe: @Daniel/Sept-Train. Composition: same tight center-frame position as 3.06 for edit match, but starting slightly wider — this is the beginning of the 3% slow push-in that will finish over the clip. Head sits with two inches headroom at the top of frame. Background beyond @Daniel: soft olive seats, warm mahogany paneling, small brass sconce hint upper-right. Camera: ARRI Alexa 35, Cooke S7/i 75mm at T2.8 — matches 3.06. Lighting: continuous with 3.06 — same warm 5200K sun-side window key from frame-right, mahogany bounce fill from frame-left, 2:1 ratio. Grade: Kodak 2383, matches previous shots. Style: photorealistic 2.39:1 cinematic still, prestige TV production quality, natural skin, mole at outer left jaw present.

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.