subject_definitions:
<Subject 1>: The sole performer: the young adult woman from the reference images, with light complexion, long straight black hair and wispy center-parted bangs, large dark eyes, silver chandelier earrings, and a fitted black strapless ruched dress with a draped center detail and thigh slit. Preserve her recognizable facial features, wardrobe, and playful fashion-pose presence. Source(s): <Picture 1>, <Picture 2>.
summary:
A single-take vertical studio fashion portrait follows the referenced woman through playful, spontaneous poses that convey energetic, sensual, and cute charm while preserving the reference appearance and gray-studio aesthetic.
Hard constraints: Exactly one continuous 20.041667-second shot with no cuts, transitions, or hidden edits. | Match <Picture 1> at the opening: elevated close portrait, arms reaching toward the lens, direct gaze, soft gray studio backdrop. | Retain the referenced woman's identity, long black hair with wispy bangs, chandelier earrings, and black strapless ruched dress with draped center detail and thigh slit. | Strictly incorporate the candid pose vocabulary from <Picture 2> as continuous, physically connected performance beats. | Keep the vertical framing mobile-safe, protecting the face, hands, dress silhouette, and low shoe-adjustment action. | No narration, captions, or spoken dialogue.
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.
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 woman's identity, close elevated camera relationship, forward-reaching arms, black strapless ruched dress, silver dangling earrings, soft frontal studio lighting, and gray seamless backdrop..
<Picture 2> -> action: Use <Picture 2> as the authoritative action and pose reference: retain the same woman's wardrobe and studio setting while presenting the nine indicated candid-fashion beats in a readable continuous progression, including playful facial expressions, dress adjustment, hair movement, shoe-strap adjustment, hand-to-lens gesture, and low kneeling finish..
detailed_description:
[Shot 1] At 00:00.000-00:20.042, <Subject 1> begins exactly in the close elevated reaching pose: arms extended toward the camera, direct neutral gaze, long black hair over one shoulder, wearing the fitted black strapless ruched dress and dangling silver earrings against the smooth gray studio. She relaxes into a playful forward lean with closed eyes and a puckered expression, then looks down and lightly adjusts the front of the dress. She bends forward with a warm, bashful smile behind one hand, rises into a soft side-facing turn that sends her hair back, and faces forward again with both hands lifting and gathering her hair in an energetic, cute pose. Maintaining an unbroken flow, she lowers into a crouch to fasten the ankle strap of her black heel, then extends an open palm toward the lens so it briefly dominates the foreground. She withdraws the hand, moves into a low kneeling/reclining forward pose with both hands supporting her, and finishes smiling downward with a relaxed, lively settling beat. Her performance remains candid, sensual, and playful rather than choreographed. Camera: One continuous stabilized handheld-gimbal move. Start slightly above and close to her face in the <Picture 1> composition, with her forward arms softly blurred in the near foreground. Slowly ease backward and lower to a medium/full-body framing as she changes poses; make small motivated pans and lateral translations to retain her face, torso, raised hands, and low shoe action in the vertical safe area. Briefly allow shallow focus to favor her palm when it fills the foreground, then rack focus back to her face and settle in a low medium composition for the final kneeling pose. No zooms, cuts, or transitions. Motion: Moderate, readable continuous motion: quick but natural expression and hand changes in the first half, a single fluid hair turn at mid-shot, then a clearly paced descent to the shoe adjustment, one deliberate hand-to-lens gesture, and a calm final kneeling settle. Camera travel is smooth and responsive, with visible parallax from small lateral repositioning rather than abrupt reframes. Synchronized audio: Soft fabric rustle as she shifts out of the opening reach.; A light hair swish during the side turn.; Subtle heel-strap and floor-contact sounds during the low crouch.; A brief air whoosh as her open palm approaches the lens.; Instrumental beat remains soft and continuous, resolving at the final kneeling pose.
overall_soundscape:
Quiet indoor studio room tone under the instrumental score, with subtle synchronized dress rustle, hair swish, soft foot and knee shifts on the studio floor, a delicate heel-strap movement, and a brief close hand whoosh at the lens. No speech, narration, crowd, or captions. No narration, voice-over, spoken description, or audible prompt reading.
non_diegetic_music:
Light, polished fashion-editorial instrumental music only: a restrained upbeat electronic-pop groove with soft bass pulse, crisp muted percussion, and airy synth texture. Keep it below the visual performance and let it end cleanly with the final pose; no vocals or lyrics.
