A young woman runs through a vast meadow toward a distant, massive fairytale palace during cool blue dusk light, with fireworks blooming over its towers.
Character appearance (critical for identity accuracy — reference Image <<<image_2>>> face only):
Oval-to-heart shaped face, fair-to-medium warm-toned skin with soft natural glow, dark brown almond-shaped eyes with a defined double-eyelid crease and naturally long lashes, softly arched natural eyebrows (not overly groomed), small straight nose with a slightly rounded tip, full lips with a defined cupid's bow and a natural soft pink-mauve tone, subtle small beauty mark near the mouth, soft rounded cheeks with natural low-key contour, delicate jawline. Long straight dark brown hair, center part, face-framing strands falling naturally on both sides. Expression should read as soft, warm, and naturally expressive — not stylized, not anime-like, not overly symmetrical or "AI-perfect." Preserve these exact proportions and features throughout every frame; do not drift toward a generic or idealized face.
Reference images: Image <<<image_1>>> (character reference — outfit, hairstyle, body, everything except the face): navy baseball cap, dark grey oversized jacket and wide-leg pants set, long straight dark brown hair, middle part, body proportions and styling. Image <<<image_2>>> (face reference ONLY — strict): use only for facial identity per the appearance description above — face shape, eyes, nose, lips, eyebrows, skin tone. Ignore clothing, hair styling, pose, lighting, background from this image.
Location (fully original, massive and majestic fairytale palace — photorealistic, light-toned, genuinely huge in scale, not a small manor or house):
A vast open lowland meadow with a winding S-shaped stream cutting through fresh, light, vividly green grass. In the distance stands an enormous fairytale palace-complex — not a single small building, but a sprawling, monumental structure that dominates the horizon, clearly scaled many times larger than a house or manor, with a footprint wide enough to suggest an entire royal residence. The palace is enclosed by a long, low pale-stone perimeter wall with rounded corner turrets marking its boundary, giving it a sense of a fortified royal estate rather than an open building. Behind this outer wall rises the main palace structure itself: multiple tall, gracefully tapering towers of varying heights clustered together, crowned by one soaring, elongated central spire with a small gold finial that reaches dramatically higher than everything around it. Each tower is capped with a smooth cone-shaped roof in soft light teal-blue with delicate thin gold trim. Walls are pale cream and light warm-grey natural stone with real, photographically accurate texture — visible stone joints, subtle weathering, natural imperfections — grounded and believable rather than smooth, glossy, or plastic-looking. The overall silhouette should feel vast, layered, and imposing — many rooftops and towers stacked and overlapping in depth, not a single flat façade — genuinely awe-inspiring in scale even from a great distance, filling a large portion of the horizon rather than reading as a small distant object. Windows are tall, rounded-arch, evenly spaced across multiple levels, glowing with warm golden interior light against the pale stone. The palace sits far in the distance, near the horizon line — noticeably further away than a typical foreground landmark — softened by natural atmospheric haze and gentle phone-lens depth-of-field so its edges are not perfectly crisp, yet its overall silhouette, tower arrangement, and central spire remain clearly identifiable as the palace described above, not an indistinct blur. No drawbridge, no dark stone, no moss/ivy overgrowth, no logos, no signage, no text of any kind, no recognizable real-world landmark — a fully original design, shot and lit like a real photographed location.
Sky and light: Clear evening dusk sky in cool blue tones — no orange, amber, or golden hues anywhere in the scene. Soft fading twilight light, a few faint early stars beginning to appear, large dramatic sculptural clouds in cool blue-grey and pale lavender slowly drifting across the sky. Ambient light on the grass and figures is cool and soft, not warm.
Camera setup: Not a selfie. A friend films her from a few steps away, holding an iPhone 15 Pro. Natural handheld micro-shake, realistic phone motion blur, slight auto-exposure breathing throughout, with a natural shallow depth-of-field — the distant castle and background rendered in soft focus, gently blurred like authentic phone-camera bokeh, while the foreground subject and immediate grass stay sharp — a maximally photorealistic yet authentically iPhone-shot look. Full realism throughout: real skin texture, real fabric physics, real grass and water behavior — no stylization, no illustrative or CGI look.
Scene (timing):
0-7s (combined, kept tight and fast-paced — do not let this section drag): Wide shot, full body clearly visible from head to feet, standing alone in the vast meadow at a distance that keeps her entire figure in frame — no crop at the waist or knees. The camera faces her from behind/side at an angle where the palace is not yet in frame — it exists just off to the left, beyond the current framing, not visible to the viewer yet. She gazes to her left, off toward that same direction where the palace actually is, with a soft, quietly mesmerized expression — her gaze is the visual cue for the direction the scene will move toward. Cool blue dusk sky above with drifting clouds, wind moves her hair and jacket hem gently, grass sways. Within this same window, a small flock of sheep briskly crosses close past the person filming from that same left side — camera dips naturally with a subtle jolt at the moment of contact, then rises back to reframe her, still keeping her full body in frame. She turns her head to keep watching the sheep for a brief delighted glance, then turns her gaze back to that same left-hand direction, takes a short breath, and breaks into a run — running toward her left, the exact same direction she had been gazing the entire time — all within 7 seconds total, no lingering static holds.
7-11s: The moment she starts running left, the friend filming begins jogging after her in that same leftward direction at an unhurried pace, phone held at the same low, steady handheld height as before — no rise, no zoom, no reframing beyond natural handheld drift, trailing a few steps behind her, camera axis staying consistent with her running direction throughout.
11-12s: In one deliberate motion, the person filming lifts the phone upward and slightly outward, continuing to face the same leftward direction she has been running toward this entire time — a natural human gesture of raising the phone higher for a bigger view, revealing the vast landscape opening up ahead along that same axis. This lift happens only once, right as the palace comes into view exactly where her gaze had been pointing from the start.
12-15s: With the phone held higher, the palace becomes visible for the first time, far away on the horizon along the same direction she has been running, softly hazed by distance and natural phone depth-of-field while still clearly identifiable in silhouette, set against the cool blue dusk sky with drifting clouds. The moment the palace comes into view, a bright, magical fireworks display begins above the towers — vivid bursts of warm gold, white, and soft blue-violet light, with visible glowing trails rising up before each burst and blooming into full, beautiful explosions — realistic in physics and scale but more vivid and eye-catching than a faint distant show, believable photographic quality, not garish or flat-CGI looking. After the single lift, the camera holds its new higher position steady with only natural handheld drift — no further rising, no zooming, no closing the distance. She remains a small, distant figure moving along the winding stream through the vividly fresh green meadow, running light and unhurried strictly along the grassy edge — her feet never touch or enter the water, staying a natural safe distance from the water's edge as she follows its curve. The water's surface trembles gently from the breeze, reflecting the cool blue sky and distant fireworks in soft rippling reflections rather than glassy stillness. In the distance, exactly three sheep stand grazing calmly near the palace view, correct quadruped anatomy.
Overall mood: Cinematic, vast open landscape, cool blue dusk light, epic slowly-drifting cloudscape, gentle wind animating hair, clothing, grass, and water, a bright and magical yet realistic fireworks display over the distant, elegant, light-toned, massive palace, ultra-photorealistic textures, natural film grain, shallow authentic phone depth-of-field, one deliberate single phone-lift gesture exactly as the palace view opens up along the same axis she has been looking and running toward, otherwise a continuous steady handheld take at constant trailing distance, no unnatural cuts, no orange/golden tones anywhere — believable as footage shot on an iPhone by someone simply walking after her.
Negative prompt: wrong face, generic/idealized face not matching reference, blended facial features from wrong source, orange or golden warm tones in sky or light, castle visible before the turn, she looks one direction and runs a different direction, camera revealing the castle on the opposite side from where she was looking, camera zooming in while she runs, camera gradually rising or craning upward while she runs, multiple lifts or repeated reframing, camera closing the distance to her, she runs into or through the water, she steps in the water, wet shoes or splashing, flat/static sky, misty/foggy castle, dark or dull grass, cropped body, close-up on face only, waist-up framing, small castle, tiny castle, single small tower, manor house, cottage-scale building, castle reads as a small distant dot, castle too close in frame, castle perfectly sharp with no atmospheric distance, cartoon castle proportions, plastic/glossy castle texture, oversaturated toy colors, Disney branding, theme park iconography, any trademarked or copyrighted structure, logos, signage, cartoonish, unnatural sheep anatomy, more or fewer than three sheep near the castle view, stiff running, oversharpened, plastic skin, warped hands, jump cuts, low frame rate stutter, she looks at camera, she smiles at camera, fireworks flat or hazy or barely visible, fireworks without rising trails, static hair/grass/water, overly polished CGI look, long static gaze scene, midday harsh light.
Có khoá nhất quán: một đặc điểm mà prompt yêu cầu model giữ nguyên.