f49d7759-6d6d-472b-b70e-9d87554a8985
- Queued
- Jul 18, 2026, 12:01 PM
- Completed
- Jul 18, 2026, 12:02 PM
- Execution time
- 16.7s
- Outputs
- 2 · 2.6 MB
- Inputs
- 1
- Cached nodes
- —
Outputs
2Click an image to view it full size.
Text prompts
2[SHOT 3.13 | REFS: @Daniel → daniel_ref_v1.png | @PullmanCoach → pullman_coach_plate_v1.png] MCU of @Daniel, clean single, reacting to @Marcus's information. His expression is caught in genuine curiosity — for the first time in the sequence his face is not performing. Brow slightly drawn together, eyes narrowed a fraction in thought, mouth closed and level — not the polite smile of 3.04 or the professional mask of 3.07 but an unguarded processing expression. His jaw is set but not clenched. The small dark mole at the outer edge of his left jaw is visible. At the very bottom edge of the frame, his right hand is partially visible — thumb touching the pads of his fingertips in his thinking gesture, the hand held at approximately sternum height. Wardrobe: @Daniel/Sept-Train. The camel-tobacco suede collar and the navy micro-check flannel collar are both visible at the neckline. Composition: @Daniel center-frame with tight headroom, matching the compression and isolation of the 3.06/3.07 singles. Background: soft olive-green tufted seat backs, warm mahogany paneling, small brass sconce hint upper-right, all out of focus. Camera: ARRI Alexa 35, Cooke S7/i 75mm at T2.8 — matches the compression of previous @Daniel close singles for edit consistency. Lighting: continuous with previous @Daniel singles — warm 5200K sun-side window key from frame-right, mahogany bounce fill from frame-left, 2:1 ratio. The key catches the furrowed brow and gives the thinking expression visible modeling. Grade: Kodak 2383, warm mahogany dominant, camel jacket accent, honest olive-warm skin with visible pore texture. Style: photorealistic 2.39:1 cinematic still, prestige TV production quality, tack-sharp on eyes — this is a genuine emotion beat, not performance, natural unretouched skin, mole present at outer left jaw.
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
1Source images and video this run consumed.