프롬프트 라이브러리

Create a native 15-second, vertical 9:16 cinematic horror short. No reference image. No text, no captions, no logos. Clear simple story, every shot readable without sound.

CORE RULES
One adult woman, one ghost figure in a white sheet, one house: the front porch and the front hallway. Nobody else appears. The ghost never shows a face, hands or feet. Calm, slow, building dread, then a final scare.

CHARACTER
Lena, 27 years old, clearly adult, long dark wavy hair, pale skin, dark red lipstick, natural beautiful face, fitted black long-sleeve top, black high-waist jeans, black ankle boots. She holds a round black ceramic candy bowl full of orange and black wrapped candy.

FACE
Natural skin texture, real expressions: warm smile, then polite confusion, then slow fear, then pure terror. Mouth opens only moderately, only upper teeth show. Eyes stay sharp and alive. Head turns under 45 degrees.

GHOST
An adult-height figure fully covered by a plain old white bedsheet with two small black eye holes. It holds a small black trick-or-treat bowl through the sheet, the hands are never visible. It stands completely still and silent. The bottom hem of the sheet floats about 3 cm above the porch boards, with only darkness under it.

VOICE
Lena: soft, friendly, natural American English, then a shaky whisper.

CAMERA
Real cinema camera, slow controlled moves, shallow depth of field, gentle slow p

SCENE
A visceral solo transformation test on a charcoal-gray studio stage. The camera pushes in on Yan as something wakes inside her, then cuts wide as she slams the floor in a big ink explosion and becomes a white fox: she crawls forward as her hands turn into paws, whips her human form off inside an ink vortex, and drives four paws into the floor for the largest burst. She holds a stalking stance and growls. Ink and paint carry all of the energy, building from strong to strongest.

REFERENCES
@Image 1 - Yan: adult woman, amber-brown eyes, untidy black hair with an uneven fringe, patched oatmeal wrap with faded green trim and a loose collar, brown waist tie, ragged dark sage skirt with a muddy hem, worn brown shoes, tied cloth bundle. Use it for her face, costume and painted finish. Her pose, gaze and every action come from this prompt.
@Image 2 - the same character's completed form: slender white female fox, amber almond eyes, tall ears, long legs, one broad tail with a jade outer band and white center, large quiet painted fur masses with sparse silhouette tufts. Use it for design. Her stance and gaze come from this prompt.

FIRST FRAME
Full-body Yan from @Image 1, centered and facing the camera, already mid-stagger: hunched, one hand clutching the wrap over her chest, shoulders heaving, head bowed so her hair falls forward over her face. Her tied bundle lies on the floor bes

Act as a cinematic landscape designer who writes image-ready and motion-ready scene briefs. Help me design one hero shot of a red wooden covered bridge over a calm, misty river in peak autumn foliage at sunrise. The shot will first be generated as a still image and then animated into a short video that uses that image as its first frame. Your brief must make the still image rich in elements that can move naturally (low mist drifting over the water, a few leaves falling and floating, soft ripples, light shimmering on the reflection, branches swaying slightly) while keeping the composition calm, balanced, readable, and easy to animate.

My starting idea: ${idea:a classic red covered bridge over a still river at sunrise, with low mist on the water and blazing autumn trees on both banks}

My starting choices:

• Bridge: ${bridge:a long red wooden covered bridge with a dark grey shingled roof, an open entrance with white trim on the left end, resting on stone abutments}
• Position: ${position:spanning the river slightly right of center, seen from the water level a little downstream}
• River: ${river:a calm, mirror-still river filling the lower half of the frame, reflecting the bridge and the trees}
• Mist: ${mist:a thin low layer of mist drifting over the water and under the bridge}
• Trees: ${trees:dense orange, red, and yellow maples and birches on both banks, brighter and sunlit o

Ultra-high-resolution 4K enhancement based strictly on the provided reference image. Absolute fidelity to original facial anatomy, proportions, and identity. Preserve expression, gaze, pose, camera angle, framing, and perspective with zero deviation. Clothing, hair, skin, and background elements must remain unchanged in structure, placement, and design.
Recover fine-grain detail with natural realism. Enhance pores, fine lines, hair strands, eyelashes, fabric weave, seams, and material edges without introducing stylization. Maintain original color science, white balance, and tonal relationships exactly as captured. Lighting direction, intensity, contrast, and shadow behavior must match the source image precisely, with only improved clarity and expanded dynamic range. No relighting, no reshaping. Remove any grain.
Apply controlled sharpening and high-frequency detail reconstruction. Remove compression artifacts and noise while retaining authentic texture. No smoothing, no plastic skin, no artificial gloss. Facial features must remain consistent across the entire image with coherent anatomy and clean, stable edges.
Negative constraints: no warping, no facial drift, no added or missing anatomy, no altered hands, no distortions, no perspective shift, no text or graphics, no hallucinated detail, no stylized rendering. Output must read as a true-to-life, photorealistic upscale that ma

References:
@[ref1]: Yuki. Shoulder-length silver-white hair with long bangs, olive-green eyes, small round silver earrings, loose pale camisole, flat deadpan face.
@[ref2]: Sumi. Short black bob with uneven bangs, brown eyes, small gold earrings, cream camisole under an oversized off-white shirt, loud and easily flustered.
@[ref3]: the style reference. Hand-drawn look, line quality and palette only; not its pose or layout.

Visual style: Rough hand-drawn anime sketch, loose black ink lines, flat watercolor washes, muted grey, sage and beige palette, soft indoor daylight. Shot as a phone front camera video: handheld, restless, constantly bobbing and tilting with whoever holds it, quick crash zooms and whip pans.

Avoid: No subtitles. No background music. No slow motion. No other people. Yuki and Sumi never merge or swap faces.

Two friends goof around nonstop with a phone camera through a small apartment, each new spot in front of a different strange painting. Every change of place comes through a whip pan or a cut from the phone itself; nobody stands still. A visible gap always separates their faces. Sound: footsteps, phone rustle, shrieks, laughter, one line. Shot list: 8 shots, about 30 seconds.

Scene 1: Continuous, in front of an orange painting with two huge round owl eyes.
Shot 1 (0-4s): Close two-shot, high angle; the camera bobs quickly with Sumi, who holds the phone w

Build an 11-second motion design product film in 16:9 (1920x1080, 30 fps) for my AI tool ${name}, which ${what_it_does}.
Build it as one HTML page with one animation timeline, so I can export it as an MP4.

Look: soft grey-green background, cream paper sheets, a dark green app panel, and gold as the only signal colour, used like a highlighter pen.

Text builds word by word: "${problem}" / "${name} [does step 1], [step 2], and [step 3]." / "${claim}."
Scene 1: a stack of paper sheets with the problem line on top.
Scene 2: one line on a sheet gets marked in gold and lifts off as a strip.
Scene 3: one camera move to the app panel. The strip lands there as a card.
Scene 4: the card opens and shows the better version: ${result}.
Scene 5: a gold marker stroke draws the logo. Name and claim appear.

Rules: one object carries the story from start to end. Only one camera travel. Every move is eased.

Build an 11-second motion design product film in 16:9 (1920x1080, 30 fps) for my product ${name}, which ${what_it_does}.
Build it as one HTML page with HTML, CSS and inline SVG only (no photos), on one animation timeline, so I can export it as an MP4.

Look: a warm map seen from above. Sand-coloured ground with soft contour lines, dark brown type, and ONE signal colour ${hex} for small things only.

Text builds word by word: "${problem_in_one_sentence}" / "${name} ${what_it_does_in_one_sentence}." / "${claim}."
Scene 1: low, angled view of the map while the problem appears.
Scene 2: the camera rises to a top view in the same place. Areas light up one after another.
Scene 3: one camera move to a second place. A dark panel shows the result: ${result}.
Scene 4: one area turns into the logo. Name and claim appear.

Rules: only one camera travel in the whole film. Words grow up from their baseline. Nothing moves linearly.