250ae0de-37a4-4b79-9fe2-d9343170ce19

**POSITIVE PROMPT** Plate for shot S1.07 — @Loft, derived from the **P-05 glass macro plate**. Vertical 9:16, 1440x2560. Extreme macro on **@Monitor1's matte anti-glare surface**, square to the screen plane. The transcript region fills the lower two thirds. Her presence exists only as a **diffuse, unresolved suggestion of a face** floating in the upper region, apparently behind the glass plane, which inverts the depth relationship on purpose: the human element is the blurry one. Balance deliberately uncomfortable. Single plane plus the reflection layer. Lens character 85mm macro at 0.25 m, camera at seated eye height 118 cm, square to the screen, shallow plane of focus with the surface itself sharp. Surface: real anti-glare coating granularity resolving under raking light, the micro-texture that scatters rather than mirrors, **a thumb smudge at the lower left of the panel** from tilting it, **a faint spray of dried speech droplets across the lower third**, fine dust at the panel edge. @Monitor1 is matte, W2, thin bezel — bezel out of frame or barely intruding. Reflection: **diffuse only, capped opacity, heavy blur.** No features, no eyes, no legible geometry, no mirror image — a mirror image on this coating is physically impossible. Position consistent with her seated square to the screen, hair loose on the left. She does not move. Lighting: **green** screen emission only — Caller 2 playing. Self-luminous, flat and ugly like a real interface. No secondary source, no sodium reaches this frame. No glow bloom, no halation, no light wrap. **Generate the screen dark and empty.** Leave the lower two thirds clean and unpopulated as a comp receiver plate. No transcript text, no type, no letters, no cursor, no UI elements, no waveform in the generated image — all screen content is designed and composited. Static. Locked off. Nothing moves. **NEGATIVE PROMPT** glossy screen, mirror reflection, sharp reflection, legible reflected face, reflected eyes, recognisable person in reflection, high-opacity reflection, second reflection, reflection of a different room, mirror, glass sheen, specular highlight, screen glare, blue-white light, warm light, amber light, sodium light, coloured spill, glow bloom, halation, light wrap, lens flare, text, type, letters, words, numbers, timestamps, transcript, UI elements, interface, window, waveform, cursor, icons, menu bar, buttons, generated screen content, legible anything, watermark, subtitle, deep focus, sharp background, everything in focus, centred balanced composition, wider shot, bezel dominant, room visible, desk visible, keyboard visible, mug visible, hands, face, person in frame, body, camera movement, push in, drift, handheld, dolly, tilt, angled to screen, off-square, perspective distortion, dead pixel, pristine panel, new monitor, clean screen, no smudges, no dust, crushed blacks, high contrast, oversaturated, HDR, sharpening halo, grain, film emulation, vignette, colour grade, stylisation, cinematic look, moody, atmospheric, beautiful, aesthetic, curated, clean, tidy, horizontal framing, AI artefacts, morphing edges

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.