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> -> identity: Use <Picture 1> as the authoritative identity and wardrobe reference for the young woman: short dark-brown wavy bob with small light hair clips, petite slim build, ivory floral thin-strap romper/sleepwear-style shorts set, loose cream knit cardigan, and pale socks with light shoes..
<Picture 2> -> first_frame: Use <Picture 2> as the fixed first-frame and environment/composition reference: rear view of the woman on a pale turquoise vintage bicycle, centered on the wet downhill village road toward a black-green inlet, dark houses, and a vast cloud-shrouded mountain..
detailed_description:
[Shot 1] At 00:00.000-00:15.083, The young woman from <Subject 1> rides the pale turquoise vintage bicycle away from camera down the glossy, rain-wet single-lane road. Dark wooden village houses, wet stone walls, and grassy verges frame the route. Her short wavy bob and cream knit cardigan are buffeted by visible wind; the cardigan and floral hem flutter naturally without obscuring her cycling. After a readable riding setup, she briefly lifts one hand in a single relaxed wave into the oncoming wind, then returns it to the handlebar and continues steadily. As the camera physically eases backward and slightly upward, the landscape opens: black-green, almost inky water spreads beyond the village, the steep mountain looms under layered charcoal clouds, and warm house-window glows punctuate the cold wet scene. A distant lightning vein illuminates the cloud layers, followed later by a stronger fork over the water and a thunder response. Preserve realistic traction and safe, unhurried cycling; the storm feels monumental and ominous, not chaotic. Camera: One continuous handheld rear medium-long follow begins aligned with <Picture 2>, slightly above the rider and centered on the wet road. The operator tracks behind at a steady safe distance with restrained natural handheld sway, then gradually walks/rigs backward faster than the bicycle and rises slightly on a smooth shallow arc, creating genuine widening perspective and parallax rather than an optical zoom. Land in a wider, lightly top-down rear composition that keeps the rider in the lower central mobile-safe area while the inlet, mountain, and immense storm sky fill the frame. Motion: Continuous forward cycling downhill at a moderate readable pace. Wind pushes the rider’s cardigan, hair, and garment hem; she performs one short wave while maintaining balance, then resumes two-handed riding. Clouds drift and churn slowly, mist crosses the mountain, rainwater reflections slide beneath the bicycle, and lightning remains brief and distant. Synchronized audio: 0.0-5.0s: wet-tire hiss, subtle chain whir, and gusting wind dominate; distant thunder rolls beneath the restrained score.; 5.0-9.5s: wind rises as the cardigan catches the air; a broad low thunder roll follows a far lightning flash.; 9.5-12.5s: brief close thunder crack synchronizes with a visible lightning fork beyond the inlet; road spray and wind remain clear.; 12.5-15.083333s: bicycle and wind recede slightly in perspective while the storm ambience and subdued score settle.
overall_soundscape:
Strong gusting wind around the moving handheld camera, soft tire hiss and spray on wet asphalt, faint bicycle chain and frame rattle, occasional distant rain ticks, low thunder rolls, and one sharper thunder crack synchronized to visible lightning. No speech or narration. No narration, voice-over, spoken description, or audible prompt reading.
non_diegetic_music:
A sparse, low-volume ominous atmospheric score with distant sub-bass pulses and restrained dark strings enters under the natural storm soundscape; it remains subordinate to wind, bicycle, rain, and thunder, with no vocals.
