e6b90246-780e-4113-a5c6-35fd620db0c0
- Queued
- Jul 18, 2026, 12:17 PM
- Completed
- Jul 18, 2026, 12:18 PM
- Execution time
- 13.8s
- Outputs
- 1 · 1.4 MB
- Inputs
- 2
- Cached nodes
- —
Outputs
1Click an image to view it full size.
Text prompts
2[SHOT 3.16 | REFS: @Daniel → daniel_ref_v1.png | @Marcus → marcus_ref_v1.png | @PullmanCoach → pullman_coach_plate_v1.png | @Badge → prop] MS two-shot in the aisle of @PullmanCoach — the decision beat. @Daniel stage-right faces @Marcus stage-left. Both men stand square to each other across the narrow aisle, the axis between them horizontal. @Daniel's expression has snapped back from the vulnerability of 3.15 — jaw set, eyes sharp and locked on @Marcus, chin lifted. Mission mode restored. @Marcus meets his gaze with a small acknowledging nod just completed — his chin is returning from the downward dip to neutral, mouth closed, professional. Wardrobe: @Daniel/Sept-Train, @Marcus/OnDuty. Badge legible on @Marcus's left chest. Gold pocket-watch chain visible. Cap with gold cord. @LedgerBook held at @Marcus's side in his left hand, lowered to hip height — the conversation has shifted from information to action. Composition: clean two-shot, the two men equally weighted in the frame at approximately the same scale. @Daniel fills the right half, angled slightly toward camera-left. @Marcus fills the left half, angled slightly toward camera-right. Between and behind them, the center aisle of @PullmanCoach recedes to the vanishing point with seated passenger extras in soft background. The olive-green seat backs frame both men at waist height. Brass sconces recede on the clerestory above. Camera: ARRI Alexa 35, Cooke S7/i 40mm at T4 — wider than the singles, two-hander geography lens, deep enough depth to read both faces and the coach context behind them. Lighting: warm 5200K sun-side window from frame-left keying @Marcus and providing rim on @Daniel's camera-right side. Cooler 6200K fill from frame-right catches @Daniel and provides fill on @Marcus. The cross-lighting creates honest modeling on both faces without favoring either. Grade: Kodak 2383, warm mahogany dominant, camel jacket and navy uniform balanced as equal visual weights, olive upholstery grounding. Style: photorealistic 2.39:1 cinematic still, prestige TV production quality, two faces equally sharp, badge legible, period authenticity, the framing communicates: these two men are now aligned.
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.
Input media
2Source images and video this run consumed.