subject_definitions:
<Subject 1>: The same adult woman shown in the references: light skin; short-to-medium dark brown wavy bob with damp separated strands; white zigzag hair clips on viewer-right; rosy glossy complexion; cream floral thin-strap camisole and draped cream open-knit cardigan. Retain her close-up identity and styling consistently across the entire take. Source(s): <Picture 1>, <Picture 2>.
summary:
A vertical intimate smartphone close-up follows an adult woman through the nine reference selfie poses in sequence, beginning from the supplied first-frame pose. The single-take boyfriend POV remains stable, warm, flash-lit, and tactile, with close ASMR material detail.
Hard constraints: Exactly one continuous shot, with no cuts or hidden transitions. | Start from the <Picture 1> close-up pose and preserve the referenced adult woman’s identity, hair clips, damp-looking hair, floral camisole, cream knit cardigan, warm indoor setting, and direct flash-like illumination. | Use a stable handheld iPhone-style boyfriend POV with a fixed focal length; no optical zoom. | Perform the nine pose beats from <Picture 2> sequentially in one take. | 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 authoritative first-frame reference for the adult woman’s identity, damp glossy styling, wardrobe, warm direct-flash indoor lighting, intimate vertical close-up composition, and initial head-back eyes-closed pose..
<Picture 2> -> action: Use <Picture 2> as the reference for the same woman’s appearance and for the ordered sequence of nine distinct close-up expression and cardigan-interaction pose beats; interpret the static collage as sequential performance states, not as a literal on-screen collage..
detailed_description:
[Shot 1] At 00:00.000-00:15.083, An adult woman remains very close to the camera in a warm, softly blurred indoor space, her short damp-looking dark wavy bob, white zigzag hair clips, glossy flushed complexion, cream floral camisole, and loose cream knit cardigan matching the references. She begins exactly in the <Picture 1>-inspired pose: head tipped back, eyes closed, lips softly parted, with moisture-like sheen catching the direct flash. In one readable continuous performance, she then progresses through the nine <Picture 2> pose states: first a lifted head-back expression; then direct eye contact with a subtle smile and parted lips; then a playful sideways tongue gesture; then eyes closed while resting her cheek against the raised knit sleeve; then a centered forward look with lips gently pressed; then eyes closed in a broad smile with the sleeve held along one side of her face; then a direct, slightly upward gaze with her face angled toward the phone; then eyes closed with her chin lifted; and finally her cheek resting on the knit sleeve as she looks toward the camera with softly parted lips. Keep each pose brief but clearly legible, with tactile sleeve and hair interactions rather than exaggerated movement. The mood is close, affectionate, and sensual without revealing additional body areas or changing the reference wardrobe. Camera: One uninterrupted vertical iPhone-style close-up from the boyfriend’s eye level, held steadily at a fixed focal length with direct flash-like frontal light. Begin slightly below her eye line on the head-back pose. Maintain chest-to-hairline framing and central mobile-safe composition; allow only tiny natural wrist stabilization corrections and a subtle, motivated settling reframe to keep her face, raised sleeve, and hair clips visible. No zoom, no cut, no camera whip, and no change of location. Motion: Slow, natural facial and upper-body transitions only: head lowering from the opening tilt, gentle eye and mouth expression changes, one brief playful tongue gesture, repeated soft cheek-to-knit contact, small chin lifts, and restrained cardigan-sleeve adjustments. Motion has moderate natural easing and settles on the final sleeve-resting expression. Synchronized audio: 0.0-2.0s: faint room tone, soft cardigan rustle, and a barely audible handheld phone grip adjustment.; 2.0-7.5s: synchronized knit-sleeve brushing and small fabric folds accompany the changing facial poses.; 7.5-15.083333s: gentle clothing movement, a tiny hair shift, and quiet settled room tone as she lands in the final cheek-on-sleeve pose.
overall_soundscape:
Close indoor room tone, subtle smartphone handling, soft cardigan fibers brushing, quiet fabric shifts, natural breathing, and faint skin-and-hair movement. No dialogue, narration, captions, or other voices. No narration, voice-over, spoken description, or audible prompt reading.
non_diegetic_music:
A very quiet, warm ambient pulse with soft muted tones enters beneath the natural close-up sounds and remains subordinate throughout; no vocals, lyrics, or rhythmic beat that competes with the ASMR detail.
