subject_definitions:
<Subject 1>: Adult woman seated in the transit carriage: slim build, light skin, long straight dark hair over one shoulder, black off-shoulder outer layer over a pale pink camisole, light-blue denim shorts, light sandals, and a light-colored smartphone. She remains focused on her own phone and never acknowledges the camera. Source(s): <Picture 1>, <Picture 2>.
summary:
A close, candid-feeling passenger POV observes an adult woman quietly using her phone on a metro bench, then making small seated adjustments including a brief lower-leg and sandal movement, with tactile transit ASMR and a subtle intimate mood.
Hard constraints: One unbroken 15.083333-second take; no cuts or transitions. | Vertical 640x1152 framing with an iPhone-like handheld viewpoint from the opposite seat at a consistent distance. | Retain the referenced adult woman, clothing, smartphone, seated transit-carriage setting, cool diffuse lighting, and low across-aisle perspective. | She never looks toward the camera. | Begin with her looking down at her phone in the <Picture 1> seated pose, then naturally reframe to her lower-leg movement. | No spoken dialogue, narration, or subtitles.
Generation controls (authoritative) —
Prompt-text rule: every section label and descriptive sentence is silent production direction, never speech content. Do not speak, recite, chant, sing, or read this prompt aloud.
Background music: enabled. Generate a context-appropriate non-diegetic score unless the user explicitly requests silence or no music.
Dialogue permission is enabled, but this plan contains no dialogue lines. Generate no character speech, conversation, chanting, singing, or other vocals.
Dialogue language: automatic. Preserve each explicit <d> language tag; otherwise use the language required by the scene and user intent.
Narration: disabled. Generate no narrator, voice-over, spoken description, or audible reading of prompt text, section labels, instructions, asset tags, or metadata.
Subtitles: disabled. Do not render subtitles or dialogue captions.
Creative direction (authoritative within explicit user intent and reference fidelity)
Priority: Apply these creative directives clearly wherever they do not conflict with explicit user requirements, identity retention, or fixed first/last-frame composition.
Format and direction: Build the clip around precise tactile interaction, close material detail, slow readable hand motion, and tightly synchronized diegetic micro-sounds. Avoid chaotic motion and keep any score subordinate to taps, folds, pours, brushes, clicks, or texture sounds requested by the scene. Keep the camera emotionally close and responsive to small gestures while avoiding intrusive or unmotivated movement.
Camera execution: Follow the action continuously in a single unbroken take, using only motivated pans, small translations, and reframing needed to preserve spatial clarity.
Look: Treat connected visual references as authoritative for identity, wardrobe, objects, environment, composition, lighting, color, and medium; do not impose an unrelated restyle.
Pacing and composition: Use moderate, readable motion with natural acceleration and enough settling time for each important beat. Use exactly one continuous shot with no hidden or explicit cuts; express all action beats through blocking, performance, camera motion, reframing, and synchronized sound. An explicit user-requested shot or cut count remains authoritative over this density preference. Compose for a vertical frame: protect faces, hands, and essential action inside the central mobile-safe area; favor depth movement and avoid losing subjects at narrow side edges.
retention_analysis:
<Picture 1> -> first_frame: Use <Picture 1> as the primary reference for the adult woman’s identity, long dark hair, black off-shoulder layer over pale pink top, light denim shorts, light sandals, silver smartphone, dark transit bench, central metal pole, cool green-silver carriage palette, and opening seated pose looking down at her phone..
<Picture 2> -> composition: Use <Picture 2> for the later natural seated posture: the same woman leaning slightly forward, phone held low, with a brief lower-leg and sandal adjustment while remaining absorbed in her own activity. Retain the low across-aisle transit composition and blurred foreground obstruction..
detailed_description:
[Shot 1] At 00:00.000-00:15.083, An adult woman with long dark hair sits on a dark teal metro bench in the same wardrobe and cool green-silver carriage environment as the references. She begins in the <Picture 1> pose: eyes lowered to her light-colored smartphone, one arm relaxed near her hair, legs crossed, fully unaware of the observer. Her behavior remains ordinary and unperformed: a small thumb movement on the phone, a faint shift of the black outer layer, and a relaxed change in her seated balance. Without looking up or toward the camera, she lowers the phone slightly, leans forward a little, and briefly smooths or adjusts along her lower leg and sandal in the natural manner suggested by <Picture 2>. The camera gently follows only this change in attention, ending on her lower legs, footwear, hand, and the glossy green floor edge while the transit interior remains softly present around her. Camera: One continuous rear-phone-camera-style take from a seated observer across the aisle. Start low and steady at a fixed across-aisle distance, framing her upper body, crossed legs, phone, and the vertical steel pole. Natural hand tremor causes only slight micro-sway. Around the middle of the take, make a slow motivated downward tilt and small wrist reframe—not a push-in—so her hands, knees, calves, and sandal remain centered in the vertical mobile-safe area. Settle on the lower-body detail while preserving enough of the seat and metal carriage panel to establish place. Motion: Readable, restrained performance: opening stillness and phone interaction; small hair, garment, and posture shifts; then a gradual lean and one brief lower-leg/sandal adjustment before settling. The train environment has subtle vibration, while the camera has controlled handheld micro-instability only. Synchronized audio: Continuous low train rumble, ventilation, and faint carriage resonance.; Soft phone-screen taps during the opening phone check.; Quiet fabric and seat-vinyl movement as she changes posture.; A gentle sandal/foot contact sound during the lower-leg adjustment.
overall_soundscape:
Close diegetic ASMR: steady train rumble and rail vibration, low ventilation, faint carriage resonance, subtle seat and fabric shifts, light fingertip taps on the phone, a quiet sandal/foot adjustment, and distant indistinct transit ambience. No intelligible speech and no narration. No narration, voice-over, spoken description, or audible prompt reading.
non_diegetic_music:
A very soft, sparse ambient tonal underscore enters beneath the carriage ambience and remains subordinate to tactile ASMR details; no vocals, lyrics, or prominent beat.
