Character Prompts

A character is a readable silhouette plus one detail that implies a life. Everything else is decoration.

About Character prompts

Character prompts fail in a predictable way: people add accessories until the description is a shopping list, and the model returns someone wearing all of it and meaning none of it. Strong character design works the opposite direction — establish a silhouette that reads at thumbnail size, then add a single specific detail that implies history.

The silhouette is what makes a character recognizable, and it is almost never mentioned in prompts. Broad shoulders and a narrow waist, a hunched profile, an unusually long coat — these shape decisions survive any rendering style. A well-chosen prop or piece of wear does the rest: a mended sleeve says more about a person than five adjectives about their personality.

The prompts here are tested with their real outputs. Read them for what they leave out — the memorable ones usually describe fewer items than you would expect, and describe them more precisely.

How to write Character prompts

1Describe the silhouette first: proportions, posture, and one distinctive shape. "Tall, narrow, long coat past the knees, shoulders slightly hunched" is a character before any detail is added.
2Pick exactly one telling detail and make it specific — a mended sleeve, mismatched gloves, a tool worn smooth at the grip. One earned detail beats five invented ones.
3Give the face a state rather than a beauty rating: tired, wary, mid-laugh, distracted. Expression carries characterization; "beautiful face" carries nothing.
4For a consistent character across generations, fix three unchanging attributes and repeat them verbatim in every prompt — the same hair description, the same garment, the same one prop. Vary everything else freely.
5State the framing and what it reveals: full body for silhouette and costume, waist-up for expression and prop. Trying to get both in one image usually loses both.

Frequently asked questions

How do I keep a character consistent across multiple images?

Lock three attributes and repeat them word for word in every prompt — typically hair, one garment, and one prop. Consistency comes from repeated exact phrasing far more than from long descriptions, and any attribute you paraphrase will drift.

Why do my character prompts produce generic-looking people?

Usually too many accessories and no silhouette. Models average across everything you list, so a long inventory produces a mannequin wearing items. Describe the shape first, then add one specific detail that implies a history.

What framing works best for character design prompts?

Full body when the silhouette and costume are the point; waist-up when expression and a held prop matter more. Deciding this explicitly avoids the common failure where the model splits the difference and delivers neither clearly.

All Images Videos Audio

0:20

CharacterCinematicCityscape

Create a 20-second cinematic vlog featuring a cheerful young Japanese woman exploring a hidden little town in Japan. Character & Outfit: A cheerful young Japanese woman wearing a cute pastel short summer dress with a delicate floral pattern, white ankle socks, and adorable sneakers. Soft hairstyle, natural makeup, bright expressive eyes, warm smile, youthful and wholesome summer-vlog aesthetic. 0–5s — Discovering Japan: She walks through a beautiful hidden Japanese alley decorated with colorful lanterns, flowers, traditional wooden houses, and tiny cafés. She turns the camera toward herself, smiles excitedly and says: “Hi guys! I found the cutest little place in Japan!” 5–9s — The Cat Appears: She sits outside a cozy flower-filled café, holding a cute drink. Suddenly, a tiny fluffy cat slowly walks toward her and stops in front of her. She looks surprised and smiles: “Oh… hello, little one. Did you come to see me?” The cat gently rubs against her leg. She giggles and kneels down. 9–13s — First Bonding Moment: She offers her hand. The cat curiously sniffs it, then gently places one tiny paw on her hand. She smiles warmly and says: “Aww… I think we’re friends now.” She gently pets its head while the cat happily stays beside her. 13–17s — Cute Friendship: The cat curls up next to her on the bench. She gently strokes its fluffy fur and laughs softly: “You’re way too cute!” The cat looks up at her and gives a tiny playful meow. She looks at the camera and whispers: “Okay… you’re coming with me.” 17–20s — Sweet Ending: Golden sunset beside a peaceful Japanese river. She sits with the cat beside her, gently pets its head, looks into the camera with a warm smile and says: “Best day ever. See you tomorrow!” She giggles and waves goodbye while the cat looks toward the camera. Visual & Audio Style: Ultra-realistic cinematic vlog, natural English dialogue, realistic Japanese female voice, accurate lip-sync, adorable facial expressions, playful reactions, realistic fluffy cat fur and movements, authentic Japanese scenery, lanterns, flowers, cozy café, peaceful river, warm golden-hour lighting, cinematic depth of field, smooth handheld vlog camera, gentle close-ups, natural transitions, soft ambient café and street sounds, wholesome kawaii atmosphere, photorealistic 4K.

0:30

CharacterVintageRealistic

Create a 30-second ultra-realistic video that feels like a genuine forgotten home-video recording from the early 2000s. It must NOT look cinematic, staged, polished, or AI-generated. MAIN SUBJECT: Young Korean woman, early 20s, natural everyday appearance. Faded charcoal-grey sleeveless crop top, loose high-waisted light-wash jeans, black canvas sneakers, black cord necklace. Black wavy hair tied in a messy side ponytail with wispy bangs. Minimal makeup, realistic pores and skin texture, subtle imperfections. Warm, approachable personality. Maintain EXACTLY the same identity, face, hairstyle, clothing, proportions, and appearance throughout. LOCATION: Authentic quiet Korean residential neighborhood on a warm late afternoon. Narrow concrete lanes, low-rise houses, small gates, potted plants, old bicycles, utility poles, tangled overhead wires, parked scooters, laundry hanging from balconies, mature trees, uneven concrete, faded walls. No shops, signs, advertisements, cafés, crowds, or tourist landmarks. CAMERA: Early-2000s consumer MiniDV camcorder recorded casually by her friend. Heavy natural handheld shake, imperfect framing, occasional accidental cropping, autofocus hunting, lens breathing, exposure pumping when entering shade, slight rolling shutter, motion blur during quick movement, mild digital compression, subtle sensor noise, faded consumer-camera colors, soft contrast. No stabilization. No cinematic camera movement. No gimbal. No modern HDR. No artificial film look. 00:00–00:04 The recording begins abruptly while the camera is already moving. She is walking out through a small metal gate carrying a reusable grocery bag. She notices the camera and gives a slightly confused smile, as if she didn't realize her friend had started recording. The operator walks backward awkwardly and briefly loses her face from frame. 00:04–00:08 They turn into a narrow residential alley. She suddenly notices a small delivery box left near a neighbor's gate. She picks it up and looks around, trying to figure out whose it is. The camera moves closer too quickly, autofocus briefly locks onto the box instead of her face. 00:08–00:12 A middle-aged Korean neighbor appears from a doorway and gestures that the package is hers. The woman laughs softly, hands it over, and gives a small polite bow. The interaction feels spontaneous and unscripted. The camera shakes slightly as the person filming laughs behind the camera. 00:12–00:16 She continues walking and stops beside an old vending-style outdoor water dispenser near a residential entrance. She takes a small sip from her reusable bottle, wipes her mouth with the back of her hand, then notices the camera still pointed at her and playfully covers the lens for a moment. 00:16–00:21 The camera drops slightly as her hand moves away, revealing her walking ahead beneath large trees. Sunlight flickers naturally across the pavement and her clothing as leaves move in the breeze. A bicycle passes slowly in the distant background. She casually kicks a small fallen leaf forward while walking. 00:21–00:25 She reaches a tiny neighborhood convenience-style residential rest area with a concrete bench, but there are NO commercial signs or branding. She sits down, places the grocery bag beside her, and checks her phone. She suddenly looks toward something off-camera and smiles naturally, reacting to her friend rather than posing. 00:25–00:28 The friend walks closer. She looks directly into the lens and says casually, "Why are you still filming me?" with a small laugh. Her expression should feel completely spontaneous, not performed. 00:28–00:30 She stands and starts walking toward the camera. The operator instinctively backs away, causing noticeable shaky footage and brief focus hunting. She reaches toward the camera as if trying to stop the recording. The image abruptly cuts to black while her hand is still approaching the lens. AUDIO: ONLY authentic location sound. No music. No cinematic sound design. No narration. Include distant birds, leaves moving, footsteps on concrete, fabric rustling, a faint scooter passing, bicycle wheel sounds, neighborhood voices far away, subtle traffic in the distance, the neighbor's brief greeting, her natural laughter, and the actual sound of the camcorder operator moving and breathing. Dialogue should sound naturally recorded through a cheap built-in microphone, slightly compressed and imperfect. REALISM REQUIREMENTS: The entire video must feel accidentally captured by a real person, not directed for a film. Avoid beautiful composition, dramatic lighting, perfect framing, slow motion, smooth transitions, excessive depth of field, exaggerated facial expressions, perfect skin, artificial bokeh, cinematic color grading, CGI-looking environments, or overly clean textures. Small imperfections are essential: missed focus, exposure fluctuations, awkward framing, slight camera shake, realistic motion blur, occasional clipped highlights, compression artifacts, imperfect timing, natural pauses, and genuine micro-expressions.

0:15

CharacterCinematicFashion

Create a 15-second ultra-realistic cinematic YouTube-style fashion vlog featuring the girl from the uploaded reference image as the exact character reference. Preserve her facial identity, eye color, skin tone, hairstyle, body proportions, and overall appearance throughout the entire video. The video begins with a handheld selfie-style shot inside her cozy bedroom. She looks directly into the camera and says with playful indecision, "I'm going to a party tonight, but I seriously have no idea what to wear." She looks toward her wardrobe, walks behind the curtain, and quickly returns wearing a stylish cropped top with a mini skirt. She flicks her fingers toward the camera — snap! Her outfit instantly transforms into a fitted crop top with high-waisted jeans. She looks down at herself, poses, then gestures toward the camera as if asking, "This one?" Another finger flick — snap! The jeans transform into a trendy short skirt with a different top. She spins once, lets the skirt move naturally, then gives a playful uncertain expression. She flicks again — snap! Her outfit changes into a stylish party dress with heels and accessories. She strikes a confident pose, checks herself in the mirror, then looks back at the camera with an excited smile. For the final beat, she rapidly flicks her fingers once more and changes into a completely different glamorous party outfit. She looks at the camera, points at herself, then gestures "Which one?" with a playful expression as the camera pushes in. Fast seamless outfit transformations, no jump cuts during the actual changes, realistic fabric morphing, natural hair movement, consistent bedroom environment, handheld creator-vlog energy, expressive reactions, quick camera movements, smooth whip pans, natural daylight mixed with warm bedroom lighting, realistic skin texture, cinematic depth of field, photorealistic, ultra-detailed, 4K HDR, 24fps, 16:9. Audio: Natural room ambience, footsteps, wardrobe movement, finger snaps with satisfying transformation sound effects, subtle upbeat vlog-style background music, natural spoken dialogue. No subtitles, no logos, no watermark, no distorted hands, no duplicate people, no face changes.

0:15

CharacterCinematicFashion

Translate the following AI generation prompt into English. Output ONLY the translated text — no quotes, no markdown, no explanations. Preserve line breaks and formatting. Use the uploaded reference image as the exact character identity reference. Keep the same woman throughout the entire video — identical face, hairstyle, skin tone, body proportions, makeup style, and recognizable appearance. She is a professional adult fashion model preparing for a stylish outdoor photoshoot. Create a fast-paced, cinematic fashion behind-the-scenes sequence where the photographer is never visible in frame. The camera is always positioned from the photographer's perspective, making it feel like we are seeing the photoshoot through their camera. The video opens inside a stylish bedroom or makeup studio. She finishes her makeup, fixes her hair, checks herself in the mirror, puts on her accessories, grabs a small fashion bag, and confidently walks outside for the shoot. She arrives at the first location: a beautiful street-side café. Wearing a stylish fitted crop top with a mini skirt, she stands beside the café window, adjusts her hair and looks directly toward the unseen photographer. She says naturally: “Okay, here… now click.” A realistic camera shutter sound plays — CLICK. Instant cinematic transition to the next location. Now she is sitting casually on a vintage scooter parked along a charming street, wearing a different fashionable outfit. She crosses one leg over the other, turns her face toward the camera, plays with her hair and gives several confident poses. She looks toward the unseen photographer and says: “This angle… now click.” CLICK. Quick flash-style transition. Next, she appears in a glamorous resort-style outfit with a tasteful two-piece swimwear look, posing beside a luxurious poolside setting. She walks toward the camera, turns over her shoulder, then gives a confident editorial pose. She smiles and says: “Wait… this one. Click.” CLICK. Cut to a busy urban street. She is now wearing fitted jeans with a stylish crop top and heels. She leans casually against a street pole, changes poses with every camera movement, looks away, then suddenly looks directly into the lens. “Okay, hold it… now click.” CLICK. Rapid transition to another location: a colorful outdoor café terrace. She wears a completely different elegant outfit, sits at a table with a coffee, crosses her legs, takes a small sip, then poses naturally while looking toward the unseen photographer. “One more… click.” CLICK. Final location: golden-hour city street. She wears her strongest fashion look, walks toward the camera, stops under warm sunlight, turns slightly, lets her hair move naturally in the breeze and gives a confident final model pose. She looks directly into the camera with a playful smile: “That’s the one.” One final realistic camera shutter — CLICK. Use seamless match cuts, camera-flash transitions, natural body movement, realistic hair and clothing physics, shallow depth of field, cinematic lens changes, handheld photographer perspective, natural street ambience, realistic lighting, premium fashion-commercial aesthetics, photorealistic skin texture, elegant color grading, strong temporal consistency, and smooth transitions between locations. No photographer visible, no camera visible, no logos, no subtitles, no watermarks, no distorted hands or face, no identity changes. 16:9 cinematic composition, high-end fashion editorial photography, realistic camera shutter sounds and natural location ambience.

Ultra-realistic candid Y2K evening fashion portrait of a glamorous young adult woman with long volum — AI image prompt — Nano Banana Pro

CharacterFashionPortrait

Nano Banana Pro

Ultra-realistic candid Y2K evening fashion portrait of a glamorous young adult woman with long voluminous copper-red hair styled in loose slightly messy waves, deep side part, natural lift at the crown, individual strands, and subtle flyaways. Fair warm ivory skin with clearly visible pores, realistic skin texture, delicate natural freckles across the face, shoulders, arms, and legs, subtle facial vellus hair, natural skin variation, softly flushed cheeks, feathered brows, minimal champagne-toned eye makeup, softly defined lashes, hazel-green eyes, and glossy peachy nude lips with realistic lip texture. She wears a dramatic silver rhinestone fringe halter crop top constructed from dense rows of sparkling crystal chains cascading vertically across the chest and midriff, with long free-hanging crystal fringe that catches the flash. Pair it with a fitted high-waisted black leather mini skirt featuring realistic smooth leather grain, subtle seams, natural wrinkles, and glossy flash reflections. Accessories include very long dangling rhinestone statement earrings, stacked silver crystal bracelets on both wrists, several delicate silver rings, and a small black shoulder bag completely covered in shimmering silver rhinestones. Metallic silver strappy high-heeled sandals complete the look. She stands casually against a rich dark walnut-paneled wall with vertically ribbed smoked-glass inserts, leaning slightly into the wall with one knee softly bent and legs naturally crossed. Both hands rest loosely near her waist while she looks directly into the camera with a relaxed, slightly parted-lip expression. Upscale dimly lit restaurant, cocktail lounge, or hotel bar at night featuring dark polished wood, ribbed glass, warm table lamps, deep shadows, and subtle ambient background lights. Captured with an early-2000s disposable film camera aesthetic using strong direct frontal flash, slightly tilted spontaneous framing, hard flash shadows behind her, bright skin highlights, sparkling star-like reflections from the rhinestones, glossy leather reflections, mild film grain, slightly warm color cast, imperfect exposure, subtle highlight clipping, and authentic point-and-shoot nightlife photography. Subject remains extremely crisp while the background falls naturally into darkness. Y2K party-girl editorial, vintage nightlife snapshot, candid celebrity afterparty aesthetic, realistic anatomy, authentic hands, individual hair strands, highly detailed rhinestones, visible pores and freckles, natural skin texture, RAW-like photographic realism, high resolution, maximum photorealism.

ultra-detailed high-end 3D CG character art, refined anime-style 3D modeling, cinematic rendering.
T — AI image prompt — Seedream 5

CharacterAnime3D Render

ultra-detailed high-end 3D CG character art, refined anime-style 3D modeling, cinematic rendering. The entire image has an exceptionally crystalline, translucent, luminous, jewel-like quality, as if the scene were made from clear water, glass, crystal, pearls, and refracted rainbow light. Smooth and delicate materials, pristine surfaces, soft luminous lighting, sophisticated transparent and semi-transparent shaders, realistic glass reflections, holographic iridescence, and subtle prismatic dispersion. No painterly texture, no oil-painting effect, no visible brushstrokes. Scene: a magical, crystal-clear underwater world. An extreme close-up side profile of a beautiful anime-style girl with long white hair underwater. The camera is positioned extremely close to her face, emphasizing her elegant profile. Her face fills most of the frame, with her eye and round glasses forming the absolute visual center of the composition. She has pale, translucent porcelain-like skin with delicate subsurface scattering and soft luminous highlights. Long, finely detailed eyelashes are clearly visible. Her lips are slightly parted, with a wet, transparent, glossy finish that catches the underwater light. Her long white hair floats weightlessly through the water, with an enormous amount of individually rendered strands. The hair is silky, delicate, slightly translucent, and naturally carried by underwater currents. The edges of the strands glow with brilliant white, icy blue, and subtle rainbow rim light. She wears round, thin-framed metallic glasses. The frame combines polished silver metal with sophisticated holographic and iridescent materials, reflecting flashes of cyan, pink, lavender, emerald green, turquoise, and violet. The lenses have pristine transparent glass material with strong mirror-like reflections. Clearly reflected inside the lenses is a miniature underwater world: the rippling water surface above, sunlight penetrating through the water, shimmering caustic patterns, silhouettes of tiny swimming fish, refracted waves, and distorted underwater light. The edges of the lenses produce delicate prismatic dispersion and rainbow refraction, like perfectly polished crystal. Her visible eye is extraordinarily clear and luminous. The iris has the layered transparency of a precious gemstone or crystal, containing saturated pink, cyan-blue, turquoise, and violet highlights. Tiny starburst reflections sparkle inside the pupil, as if light were trapped within a transparent jewel. Strong underwater optical effects. Sunlight penetrates the water surface and creates beautiful underwater caustic patterns across her cheeks, nose bridge, glasses, glossy lips, and floating white hair. These luminous patterns gently bend, ripple, shimmer, and move with the surrounding water. Numerous crystal-clear air bubbles of different sizes slowly rise around her face and hair. Each bubble has realistic transparent glass-like surfaces, thin-film reflections, and subtle rainbow halos along its edges. The water itself is exceptionally clean and transparent. Light passing through the water, glass lenses, bubbles, and crystalline elements creates rich layers of refraction, reflection, chromatic dispersion, and iridescent highlights. Subtle RGB color separation appears along selected edges, creating a sophisticated prism-like optical effect. The background has a strong shallow depth of field with soft, luminous underwater bokeh. Several delicate, whimsical little fish swim behind the girl, their scales shimmering with translucent, pearlescent, and iridescent reflections. The dominant palette consists of crystal aqua, transparent turquoise, icy blue, pearl white, and luminous cyan, accented with vivid flashes of pink, violet, emerald green, and holographic rainbow colors. Small amounts of transparent crystal fragments, prism-like light shards, sparkling particles, and microscopic bubbles may float through the scene, adding visual richness while keeping the composition clean and elegant. The final image should feel like entering a dreamlike underwater universe made of clear ocean water, crystal, glass, pearls, and rainbow light — luminous but never overexposed, luxurious yet pure, colorful yet transparent. Key visual priorities: extreme close-up side profile, white-haired anime girl, round glasses as the focal point, underwater reflections inside the lenses, gemstone-like transparent eyes, crystalline materials, glass textures, holographic iridescence, underwater caustics, transparent bubbles, flowing individual hair strands, prismatic dispersion, tiny fish, ultra-refined 3D CG character modeling, cinematic rendering, extreme detail, crystal-clear transparency, luminous underwater atmosphere.

0:15

CharacterFoodRealistic

Duration: 15 seconds | Aspect Ratio: 16:9 | Style: Authentic UGC / iPhone selfie-vlog, handheld, natural light, slight motion blur, TikTok/Reels energy — NOT cinematic. Product Reference: Use the uploaded ramen bowl image as the only product reference. Keep the broth color, noodle thickness, toppings, egg placement, chashu slices, and bowl appearance identical throughout every shot. Camera: iPhone 15 Pro handheld with front/back camera switching, realistic autofocus hunting, natural handheld movement, slight exposure shifts, warm apartment lighting. Character Description Name: Yuna A young Japanese woman in her early 20s with soft natural beauty, shoulder-length dark hair tied loosely, subtle makeup, oversized gray hoodie, cheerful personality, filming casually inside a cozy apartment kitchen. Shot Breakdown SHOT 1 (0–2s) — Selfie holding the ramen bowl. Dialogue: "Late-night ramen again." SHOT 2 (2–4s) — Overhead reveal with steam rising. SHOT 3 (4–6s) — Close-up autofocus on noodles and broth. SHOT 4 (6–8s) — Chopsticks lifting noodles with a natural noodle stretch. SHOT 5 (8–10s) — Selfie bite reaction. Dialogue: "That's insanely good." SHOT 6 (10–12s) — Casual b-roll of the bowl while she reaches for another bite. SHOT 7 (12–14s) — Selfie holding noodles toward camera. Dialogue: "Worth every bite." SHOT 8 (14–15s) — Freeze frame with handwritten overlay: "ramen fix 🍜" Look & Feel Warm lighting, natural phone quality, authentic UGC pacing, jump cuts, realistic handheld movement. Negative Prompt cinematic look, luxury commercial, perfect framing, CGI noodles, unrealistic steam, plastic food, distorted chopsticks, extra fingers, warped hands, overprocessed HDR, text artifacts.

0:15

CharacterAnimeCinematic

High-quality anime footage. Expression progression: eyes -> brows -> eyelids -> mouth -> gaze. [Reference image and character lock] Same girl, same person, same identity in every shot. Use image 1 as the sole highest-priority reference for this girl's face, eyes, hair style, hair color, outfit, accessories, body type, and equipment. In every cut, strictly maintain the same single girl as in image 1. Do not reference text, UI, layout, background, pose samples, expression lists, or small drawn face variations within image 1. Even if image 1 contains multiple expression variants or small face samples, do not treat them as different people — use them only as variation information of the same person. Averaging the face, turning her into a different person, outfit swapping, duplication, cloning, and additional characters are prohibited. Allowed changes are limited to expression, gaze, mouth, pose, breathing, and natural hair/fabric movement. Expression changes must always be shown in the order: eyes -> brows -> eyelids -> mouth -> gaze. The face must strictly maintain image 1's: small soft oval shape, delicate jaw, large iris layered from purple to blue, magenta and cyan reflections, multi-layer catchlights, thin upper lashes, pale skin, long pink twin-tails, slanted bangs, purple flower and dark purple ribbon on the head. Maintain the outfit, accessories, body type, and equipment from image 1: deep purple short cape with antique gold trim and star-flower embroidery, white frilled blouse, black-purple corset, dark brown leather belt, short layered skirt, white thigh-highs, purple-black and antique gold boots, purple crystal brooch. Prioritize shapes, colors, and materials clearly visible in image 1; only fill in unclear areas naturally while keeping the same design. Props: a dark brown leather-bound grimoire with gold openwork and a purple crystal, a purple glass vial at the waist, and a purple crystal charm. There is only one grimoire. It is closed at the start, always supported by the left hand, and only the right hand opens the cover and turns a single paper page. The glass vial and charm remain fixed at the waist and are not used. [Fixed rendering: 3D toon/cel-look] Thin, controlled colored line art. Line color is not black but deep purple-brown. Shading uses 2–3 layers of toon shadows with soft mid-tone gradients. Color palette is centered on pink, deep purple, white, antique gold, and jewel magenta. Eyes are multi-layered, hair is pearlescent, metal and crystal have sharp localized highlights. Separate materials: matte skin, silky hair, woven cape fabric, thin white blouse fabric, leather for belt and grimoire, antique gold for ornaments, transparent crystal for gems and glass vial. Render at high density: face, lashes, hair strands, frills, gold ornaments, leather, magic sigils, wet stone floor, brass door, arched window. Thick outlines, single-layer flat cel shading, generic 3D anime faces, smooth plastic CG materials, low-density backgrounds, photorealistic, semi-photorealistic, dull colors, and mixed art styles are prohibited. [World and tone] Midnight royal magic archive. Wet black stone floor, tall arched windows, brass star-shaped locks, dark bookshelves stretching into the depths. Cinematic teaser using black negative space, ivory, deep purple, magenta, and antique gold geometric color fields. Ratio: suspense 60%, noir jazz 40%. Mysterious, urban, composed, agile. No horror, no heavy tragedy, no cheerful jazz MV. Core of the story: "One star has been stolen from the grimoire's emblem." Not combat — show the girl discovering the anomaly and tracing the remaining magical traces. [Camera and editing design] Camera state: position=three-quarter and over-shoulder; height=eye level then low angle; direction=tracks then push-in; subject scale=close-up to medium; vanishing axis=archive depth axis; purpose=to show the clue chain and reveal the missing star. Narrow split panels open into a vast archive space, creating a clear scale change. The camera moves to show the causality of each action. Iris anomaly in extreme close-up, clue progression in asymmetrical split screen, door unlocking with a low follow, approach to truth with a depth-direction push-in, final resolve stopping at a chest-up three-quarter front. Do not keep the subject locked to screen center during movement — use diagonal compositions, foreground occlusion, and depth differences. No soft dissolves or liquid morphs — connect everything with hard cuts, masks, wipes, and tile rearrangements. A single thin ivory line is drawn across a black screen, then transforms into the outline of image 1's right eye. Extreme facial close-up. In the iris, the star-flower emblem of the grimoire is reflected — one star silently disappears. The girl changes, in the order eyes -> brows -> eyelids -> mouth -> gaze, from a faint small smile to a wary, quiet expression, and drops her gaze to the grimoire at the lower right of the frame. The circular reflection in the iris rotates like an old astronomical record disc, becoming a hard circular wipe. The screen snaps into an asymmetrical two-panel split. The left narrow panel shows a close-up of the closed grimoire's metal fittings. The right large panel shows her boots and long cape hem advancing across the wet stone floor. Deep purple and magenta color fields, thin antique gold frames, assemble piece by piece. The girl stops her right fingertips a few centimeters from the grimoire's purple crystal. The crystal lights up once on its own, and from that ignition a thin magenta magical trace line extends from the crystal toward the door. The door remains closed until the trace line arrives. When the tip of the trace line exactly overlaps the center of the star-shaped lock on the door, the brass lock turns once and the door opens vertically. The door's vertical line becomes a hard vertical cut. From the opened darkness, a flat, non-human long shadow crosses the stone floor and wipes across the entire screen once. Do not give this shadow a face, body, or three-dimensionality. After the shadow passes, the girl opens the single grimoire supported by her left hand with her right hand and turns one paper page. The edge of the paper page hard-cuts to the next screen. On the page, only a geometric star chart appears — no readable text. Three thin frames snap into a tile arrangement, simultaneously showing the eye reflection, the star-shaped lock, and the broken magenta trace. The girl takes one step forward. A low rear camera rises to over-shoulder, revealing the massive arched window in the depth and a constellation missing exactly one star. The outline of a giant English letter "A" slides in from off-screen, becoming a hard letter mask through which only the next footage is visible. The girl turns her right palm upward, and a single star-flower magic circle unfolds above her palm. The circle consists of an antique gold outer ring, magenta fine lines, and a purple-crystal center — with exactly one star missing in black. From the missing point, a red-purple straight line runs sideways and hard-cuts to a chest-up composition. The camera whips sharply from the magic circle to her face. The girl, in the order eyes -> brows -> eyelids -> mouth -> gaze, understands the anomaly — not frightened, but shifting into quiet resolve. She dismisses the magic circle, closes the grimoire with her right hand, and places her right hand on the closed cover. The grimoire's purple crystal and the brooch each light up once in response. Finally, black, deep purple, and ivory rectangular tiles snap hard together to assemble a single frame. End type: pose lock. Left: the girl in chest-up three-quarter front. Right: sufficient black negative space. On the right, display the English title "LILIA ASTRA: THE STOLEN STAR" once, with completely correct spelling. Below it, display "COMING SOON" once. No other text, job titles, names, kanji, hiragana, katakana, pseudo-letters, or unreadable symbols. The girl holds one closed grimoire with her left hand, right hand resting on the cover, motionless. The flat shadow stops at the right edge of the frame. No new elements enter. Hold the title completely for two seconds. Cut on the exact frame where the tense chord and single drum hit finish their resonance. [Sound] Fully original 15-second title music. Do not imitate existing songs or melodies. Low drone, tense string pizzicato, cold synth pulse, low kick, sparse brush, short walking-bass fragment, short baritone sax, clipped brass accent. Opening: low frequencies and hi-hat. Low kick around 3 seconds. Jazz bass movement around 6 seconds. Short sax and brass riff around 10 seconds. At 13 seconds, place a tense chord and a single drum hit, holding the resonance until 15 seconds. No dialogue, narration, or singing. Sound effects sync to visible actions and occur only at that moment. Only when the leather-bound grimoire opens or closes: a short leather creak. Only when one paper page turns: a dry paper sound. Only when the brass star-shaped lock turns: a short dry brass ring. Only when boots land on the wet stone floor: damp stone footstep sounds. Only when the cape and hair move: light fabric rustle. Only when the purple crystal lights up: a thin crystal resonance. Do not confuse materials. [Prohibited] Different person, face collapse, eye color change, hair style change, outfit simplification, outfit swap, missing accessories, equipment multiplication, grimoire duplication, broken fingers, extra arms, additional characters, crowds, clones, face averaging, combat, explosions, blood, terrified expressions, evil spirits, horror lighting, photorealistic conversion, semi-photorealistic conversion, art style shift, thick outlines, low-detail backgrounds, plastic texture, soft dissolves, liquid morphs, excessive depth of field, camera shake, unreadable text, spelling errors, duplicated title, subtitles, logos, watermarks.

0:15

CharacterCyberpunkAnime

Use the uploaded image as the exact source image and first frame. Preserve the original character design, composition, face, pale skin, glowing icy blue eyes, braided black hair, cybernetic head implants, exposed mechanical neck and chest structure, white and cobalt-blue jacket, blue serpentine mechanical creatures, labels, symbols, and the clean white background. Keep the result extremely faithful to the original illustration. The animation should feel like the original artwork has come alive, not been redesigned. Create a premium, stylish, high-end anime animation with a refined cyberpunk aesthetic. The overall impression should be elegant, cold, hypnotic, dangerous, and visually luxurious. Emphasize precise Japanese anime craftsmanship: crisp linework, beautiful cel shading, highly detailed mechanical rendering, controlled highlights, graceful motion, and strong temporal consistency. The animation should look polished, expensive, and intentional. The central character remains calm, dominant, and nearly still. She faces forward and maintains an unwavering, piercing gaze directly into the camera. Her expression is cool, emotionless, intelligent, and slightly predatory. Avoid exaggerated acting. Only subtle micro-movements are allowed in her eyelids, breathing, neck posture, and facial tension. Her presence should feel powerful even in stillness. The main animated elements are the multiple blue mechanical serpents surrounding her. They move with smooth, layered, snake-like elegance. Each serpent has slightly different timing, path, and rhythm, so the movement feels organic and sophisticated rather than synchronized. Their bodies undulate in natural S-curves with believable weight, inertia, and continuous motion. Some serpents slowly raise their heads, some glide across her shoulders and around her face, some tighten or loosen their coils, and some subtly cross behind or in front of the composition to reshape the frame. Their movement should feel alive, hypnotic, and controlled, never frantic. Preserve the segmentation, scale texture, metallic fittings, joints, and cable-like details. Small articulated components should shift with delicate mechanical precision. Her long green tongue moves like a real serpent tongue but remains elegant and stylized. It slowly extends, retracts, and sways with controlled, organic softness. The forked tip performs subtle tasting-the-air flicks. The tongue should feel eerie, sensual, and mesmerizing, never comedic. The tongue motion should complement the serpents’ motion, acting like a focal accent that draws attention toward her mouth and face. Add subtle secondary motion throughout the scene. Her shoulders and upper torso rise and fall gently with slow breathing. Tiny motions should ripple through the hood, jacket folds, loose blue fabric, fine cables, and a few hair details. The exposed mechanical chest and neck assembly should feel alive through micro-movements: slight cable tension shifts, minute piston adjustments, tiny joint rotations, and restrained vibration. These details must remain subtle and tasteful, never distracting from the face and serpents. Lighting should remain clean and striking. Preserve the white background and the strong graphic contrast between the white, cobalt blue, black mechanical detailing, and neon green tongue. Let reflections glide softly across the blue serpents’ scales and metallic joints. Metallic parts in the neck and chest may shimmer subtly. The green tongue should remain a vivid accent with slight wet gloss or faint luminous emphasis. Maintain a polished illustration-like finish while introducing dimensionality through moving highlights and soft shadow transitions. The camera should perform an extremely slow and smooth frontal dolly-in over the full 15 seconds. The framing begins as a stable medium close-up and gradually becomes slightly tighter and more intense. The camera should never move abruptly. No shake, no tilt, no sudden zoom, no spinning, and no dramatic reframing. The face, eyes, and tongue should become increasingly dominant as the sequence progresses, while the surrounding serpents continue to frame the composition. The movement of the camera should feel cinematic and hypnotic, reinforcing tension through slow approach. Structure the motion over the 15-second duration with deliberate pacing: Seconds 0–3: begin in near stillness. Only the faintest breathing, tiny hood and cable motion, and a barely perceptible serpent twitch. Establish tension and the character’s unwavering blue-eyed stare. Seconds 3–6: the serpents begin to awaken. One or two serpents slowly lift their heads and start gentle undulating motion. Reflections start traveling across their blue surfaces. The tongue begins a slight side-to-side sway. Seconds 6–9: more serpents join the motion. The body language of the serpents becomes richer and more layered, circling her shoulders and face with elegant S-curve motion. The tongue extends a little farther and retracts slowly, with subtle fork-tip flicks. The camera continues its slow push inward. Seconds 9–12: reach the most hypnotic phase. The serpents are now fully active but still graceful and controlled, framing her face dynamically. Their movement should feel luxurious and predatory. The tongue performs its most visually striking serpent-like motion here, synchronized with the heightened tension. Highlights glide across scales and metal details. Her gaze remains locked and emotionally unreadable. Seconds 12–15: sustain and slightly resolve the intensity. The serpents continue moving but begin to feel more settled, as if entering a poised equilibrium. The camera reaches its closest framing, emphasizing her eyes and green tongue while still preserving enough serpents in frame for visual impact. End on a powerful, composed, hypnotic final moment that feels elegant and complete. The emotional tone should be futuristic, eerie, sensual, intelligent, and luxurious. The final result should resemble a high-budget anime opening shot or a premium animated key visual. Prioritize elegance, polish, and controlled visual storytelling over excessive motion. Every motion should feel deliberate and aesthetically composed. Maintain strict model fidelity and visual stability. Do not alter the character’s face shape, eye design, hairstyle, skin tone, clothing, mechanical anatomy, serpent design, or color palette. Do not add new objects, extra serpents, extra tongues, extra limbs, or background elements. Do not morph the face or let the eyes drift. Do not let the serpents fuse together unnaturally or intersect in broken ways. Do not allow clipping through the body or clothing. Do not change the jacket symbols or graphic details. Do not shift into 3D, live action, or a different illustration style. Avoid flicker, line wobble, perspective drift, detail melting, unstable anatomy, scale inconsistency, random deformation, abrupt motion, or composition changes.

0:15

AnimationCharacterFantasy

The Condor Heroes protagonist fun word lesson: dream

0:15

CharacterCinematicFashion

CHARACTER & WORLD LOCK + FULL 15-SEC MASTER PROMPT A 15-second continuous UGC-style vlog in 9:16 vertical format. Jessy, a woman in her mid-20s — use her facial features exactly as shown in her reference photo, keep everything else about the scene freshly designed — wears an attractive pastel-colored dress (soft lavender, mint, or buttery yellow) that visually pops in contrast against the bubblegum-pink Olipop can. Location: a bright, clean modern kitchen/countertop with soft natural daylight. Product: a can of Olipop Blackberry Vanilla — pastel pink can, magenta blackberry illustration, white vanilla flower, dark green "Blackberry Vanilla" wordmark, "Supports Digestive Health" text near the top, "A New Kind of Soda™" tagline (use the uploaded product photo as the exact visual reference for the can). Style: authentic smartphone UGC vlog, natural handheld feel, realistic skin texture, no over-retouched look. She speaks casual, upbeat, conversational English directly to camera with natural lip-sync. The video follows this exact beat sheet, with clean cuts between each moment: 00:00–00:02 — Front-camera selfie, slight handheld sway, Jessy fans herself lightly in the kitchen, looking for something refreshing, smiles at camera: "Okay I need something fun to drink right now." 00:02–00:04 — Eye-level medium shot, she opens the fridge and pulls out the pink Olipop can, face lighting up with delight: "Ooh, Blackberry Vanilla Olipop — yes please." 00:04–00:06 — Close-up on her hands slowly turning the can, label details ("Prebiotics, Botanics, Plant Fiber") visible: "Prebiotics AND it tastes like dessert? Sold." 00:06–00:08 — Tight macro shot, her fingers pop the tab, condensation and a light fizz mist visible: "Listen to that fizz." 00:08–00:10 — Slow-motion macro shot, pink soda pouring over ice into a clear glass, bubbles rising: "Look how pretty that color is." 00:10–00:12 — Close-up on her face as she sips, eyes lighting up with genuine, pleasantly surprised reaction: "Wait... that's actually so good." 00:12–00:13 — Macro hero shot of the can alone on the counter, condensation dripping, soft bokeh kitchen background, slow subtle push-in, no dialog. 00:13–00:14 — Medium shot, she smiles at camera, can raised slightly at chest height: "Blackberry vanilla was the right call." 00:14–00:15 — Close front-camera selfie, can held beside her face, warm bright smile into the lens: "Go grab an Olipop, seriously." Continuous natural ambient kitchen sound, subtle upbeat pop background music underneath, her voice clear and casual throughout. Consistent face, outfit, and setting across every beat. No text overlays, no captions, no watermarks, no horizontal framing, no changes to the can's design or branding.

0:15

CharacterAnimeCinematic

Japanese full-color anime film style, cinematic high-quality visuals. No BGM, no dialogue, no subtitles, no text, ambient sound only. # Visual Style Priority on the sense of the character from the attached illustration. No excessive realism, thick painting, or complex shading. Do not change the character's facial features, hairstyle, body type, costume, or accessories. # Constraints Vary the framing and angle across all cuts to avoid monotony. No text or logos. Use natural, everyday gestures. Each cut is a completely fixed camera (no camera movement or panning). No fades or morphing—switch instantly with clear hard cuts. Movements are extremely slow, quiet, and minimal. Never place the "character's face" and "detailed hand work" in the same cut. # Characters ## Woman The adult woman from the attached illustration. # Setting A low table in the living room at night. Cardboard boxes and packages wait inside the circle of lamplight. # Scene The woman opens an assortment of overseas sweets. Tape, cushioning material, wrapping paper. Maximize the pleasure of the opening sounds while building anticipation until the contents are revealed. Alternate between the unboxing steps and her gestures. As the single highlight of this video, be sure to include a "top-down shot of colorful wrapping papers spreading across the table" in the latter half of the cuts. cut1: Extreme close-up. Inside the circle of lamplight, the cutter blade touches the tape on the box. Ambient sound: Only the clicking sound of the blade being extended. cut2: Extreme close-up, directly overhead. The tape is sliced smoothly. Ambient sound: The sound of tape being cut. cut3: Close-up, front view. Eyes sparkling, hands reaching for the lid. Ambient sound: The stillness of the night. cut4: Close-up, from inside the box. The lid opens, and a face peering in appears. Ambient sound: The creak of cardboard. cut5: Extreme close-up, hands. Peeling back one sheet of bubble wrap. A single finger pops one bubble. Ambient sound: The bubble wrap sound takes center stage. cut6: Close-up, profile. Holding her breath, gazing inside. Ambient sound: Silence. cut7: Extreme close-up. Peeling away tissue paper sheet by sheet. Ambient sound: The delicate sound of tissue paper. cut8: Extreme close-up. A glimpse of part of the overseas sweets assortment. The whole thing is still not revealed. Ambient sound: The final sound of unwrapping. cut9: Medium shot, directly from behind. Her back as she continues unboxing within the circle of lamplight. Ambient sound: The sound of wrapping, the stillness of the night. cut10: Close-up, overhead. The overseas sweets assortment is revealed. She gently lifts it with her fingertips. Ambient sound: The sound of wrapping falling. cut11: Close-up, profile. Holding the overseas sweets assortment up to the lamplight, gazing at it adoringly. Ambient sound: Silence. cut12: Extreme close-up, hands. Flipping through the accessories and instruction booklet to check them. Ambient sound: The sound of paper turning. cut13: Close-up, diagonal from above. Gently placing the overseas sweets assortment in its usual spot in the room and adjusting its angle. Ambient sound: The small sound of setting it down. cut14: Extreme close-up. Crushing the empty box flat. Cleaning up after the unboxing ritual. Ambient sound: The sound of cardboard. cut15: Wide shot, full view of the table. The opened wrappings and the spoils remain in the circle of light. Ambient sound: The stillness of the night. cut16: Wide shot. Displaying the cutest tin on the shelf. Within the lamplight, an air of satisfaction fills the room. Ambient sound: Fading into silence.

0:15

CharacterDramaticShort FilmCinematic

【Style】Popular Chinese rich-tycoon (爽剧/Satisfying Drama) (Viral CEO Drama), vertical composition (Portrait Mode), high saturation filter, extreme facial close-ups, dramatic emotional range. 【Duration】15 seconds 【Characters】Humiliated groom (wearing cheap suit, eyes showing suppressed anger) VS disdainful mother-in-law (covered in jewelry, looking disgusted). [00:00-00:05] Shot 1: Extreme humiliation (Humiliation). Luxurious wedding venue. The mother-in-law slams a "divorce paper" onto the male lead's chest in front of everyone, surrounding guests burst into laughter. 【Action】Mother-in-law pokes her finger at the male lead's forehead. 【Dialogue lip-sync guidance】"Want to marry my daughter without a car or house? Take this hundred bucks and scram!" [00:05-00:10] Shot 2: Sudden reversal (The Turn). Male lead suddenly smirks and tears the divorce paper. At this moment, a massive helicopter sound (audio effect) drowns out the entire venue, the wind wildly messes up the mother-in-law's hair. 【Action】Male lead adjusts his collar, his aura instantly becomes domineering. 【Dialogue lip-sync guidance】"This marriage is what you want to cancel." [00:10-00:15] Shot 3: Rich tycoon reveal (The Reveal). The main door is kicked open, two rows of black-clad bodyguards rush in, kneeling on one knee to roll out a red carpet. An elderly butler tremblingly holds up a yellow robe (or ultimate black card) and runs to deeply bow in front of the male lead. The mother-in-law is so scared she collapses to the ground, her pupils shaking. 【Dialogue lip-sync guidance】The butler shouts: "Welcome back, Dragon King (Young Master)! Family assets have been unfrozen!"

0:15

CharacterDramaticAnimeCinematicSci-Fi

A massive cosmic arena forms in a blinding void, Tournament-of-Power scale. Crowds from countless universes roar. At the center stands the narrator: Gintoki Sakata, relaxed, wooden sword on his shoulder, bored eyes, sharp tongue. He announces the rules casually, almost mocking fate: "This tournament decides the strongest. Winner gets a harem." Beat. The crowd explodes. Gintoki sighs. "Yeah, yeah. Don't look at me like that. I didn't write the rules." The camera glides to elevated platforms revealing the women of legend, all clearly unimpressed in different ways: Bulma adjusts her device, already annoyed. Android 18 crosses her arms, deadpan. Hinata watches quietly, composed. Sakura cracks her knuckles. Nami smiles like she's already planning something. Boa Hancock looks away, offended by existence itself. Mikasa doesn't react. At all. Erza stands like a judge. Nico Robin smiles politely—dangerously. Rukia tilts her head, curious. Gintoki points. "First match. Try not to destroy the universe before lunch." Two tunnels ignite. From the left: Saitama walks out slowly, hands in pockets, face empty. He looks around. "Huh. This again." From the right: Goku steps forward, serious, focused, sensing something deeply wrong. "You're strong… but you look like you don't care." Close-ups alternate. Dust rises. Energy crackles. Gintoki stands between them. "Alright. Bald guy who's bored versus spiky guy who lives for this." Lights drop. Power surges. Comedy and catastrophe collide.

0:16

VFXCharacterDramaticCinematic

Forcing Thanos to apologize before a Spider-Man-led group assault

0:15

VFXCharacterCinematicSci-FiDynamic

Use #Seedance 2.0 to create an exciting fight scene between Spider-Man and Octopus Man.

0:10

CharacterFantasyEtherealDark

A dark, fantastical female figure, with flowing long hair and an intricate metal crown topped with sharp, antler-like points, her eyes closed, her expression serene, her pale skin softly glowing. Her forearms and torso are transformed into smooth, black liquid metal with reflective chrome details, and sharp, claw-like fingers extend from the darkness. Dramatic backlighting creates a halo effect around her head, a cool blue-toned misty atmosphere, cinematic lighting, rich detail, surreal yet elegant—a dark fantasy aesthetic.

0:15

CharacterAnimeCinematicFantasy

"Sailor moon jumping onto the bed and screaming "Girls, we did it!". Sailor Venus appears and says: "How many were there? 6? 7?". Sailor Jupiter laughs and says "6 7!""

0:17

VFXCharacterDramaticCinematic

Man in green suit with logo fighting with man in black, in style of spy movies, X man beaten on the floor screaming elooooon! in the end

0:22

CharacterFashionBright

Scene 1 (0–5 sec) A bright, cozy bedroom with warm sunlight streaming through the window. A cheerful young woman is on a phone call, smiling. She says, “I’ll be ready in 10 minutes! See you soon!” She hangs up, excited to meet her friends. Scene 2 (5–10 sec) She opens her large wardrobe filled with colorful dresses and stylish outfits. Looking unsure, she pulls out one outfit after another, checks each in the mirror, and tosses it onto the bed, searching for the perfect look. Scene 3 (10–16 sec) After trying several options, she spots a gorgeous yellow dress tucked neatly in the wardrobe. Her face lights up with excitement. Holding it up, she smiles and says, “This one is perfect!” She quickly changes into the beautiful yellow dress. Scene 4 (16–21 sec) Dressed and ready, she admires herself in the mirror. As she turns around, she notices the bed completely covered with the clothes she threw out earlier. She sighs dramatically and laughs, saying, “Oh no… how am I going to clean this mess now?” Scene 5 (21–25 sec) She grabs her handbag, gives the messy room one last amused glance, shrugs with a smile, and walks out the door to meet her friends. The camera lingers on the colorful pile of clothes before fading out, ending with a fun, lighthearted vibe.

0:15

CharacterCinematicSci-Fi

A beautiful stylish Korean woman field scientist, identical appearance throughout: long dark hair tied loosely, safety glasses pushed into her hair, khaki field shirt with rolled sleeves over a fitted tank top, cargo trousers, a utility belt with scientific vials and a flashlight, and a lab coat tied around her waist. Maintain the same face, outfit, proportions, and hairstyle in every shot. LOCATION: An overgrown ruined jungle laboratory with cracked glass specimen tanks strangled by vines, flickering fluorescent tubes, overturned equipment, a shattered observation window revealing jungle mist, and sparking severed cables. CREATURE: A colossal praying mantis, roughly 4 meters tall, with glossy green-and-brown segmented chitin, massive spiked raptorial forearms, a triangular head with large black compound eyes, and twitching antennae moving in sharp insectile jerks. Action (15 seconds, three clear beats, no clutter): (0–5s) The scientist backs between the lab benches with her flashlight as the colossal mantis slowly unfolds from the shadows beside the shattered observation window, its spiked forearms raised and its head tilting toward her. (5–10s) The mantis slams one forearm downward as she dives beneath a steel bench while the spike tears through the metal. She grabs a chemical beaker and hurls it into the mantis's eyes as it rears back screeching in pain. (10–15s) She sprints toward the exit, rips a sparking severed cable from the wall, and jams it against the mantis's leg. Electricity erupts across its body as it convulses violently while she escapes through the doorway as shattered tanks collapse around it. CAMERA (Technical): Beat 1 — Slow controlled push-in on the scientist illuminated by her flashlight, followed by a smooth crane reveal of the unfolding mantis. Beat 2 — Controlled low-angle shot as she dives beneath the bench while the mantis shatters it, followed by a smooth 90-degree arc movement and rack focus onto the chemical splash striking its eyes. Beat 3 — Smooth cinematic tracking shot toward the exit, illuminated by the sparking cable before a slow push-in to a medium close-up of her face. 35mm anamorphic lens, gentle handheld weight, realistic motion blur, smooth fluid 24fps cinematic motion, consistent natural frame rate, no stutter, no dropped frames, no chaotic camera shake, no strobing. LIGHTING: Flickering cold fluorescent key light mixed with green jungle spill, deep cinematic shadows, hot sparking-cable highlights, electric arc accents, and atmospheric haze. COLOR GRADE: Sickly green and teal palette, Kodak Vision3 500T film emulation, subtle 35mm grain, halation, and anamorphic lens flares. Inspired by tense 1980s jungle laboratory creature thrillers. AUDIO: Flickering fluorescent buzz, dripping water, insectile chittering clicks of the mantis, chitin scraping as it unfolds, steel tearing apart, shattering glass, the mantis's piercing screech, electric crackles and zaps from the cable, the scientist's panicked breathing, and a tense low orchestral-synth pulse. VISUAL REQUIREMENTS: Ultra-photorealistic live-action cinematic quality. Maintain consistent character identity and wardrobe throughout. Realistic creature physics, smooth continuous action, authentic lighting interactions, cinematic depth of field, and seamless motion. No animation, cartoons, subtitles, narration, outfit changes, scale inconsistencies, or choppy motion.

0:15

CharacterVintageLandscape

One original female character with identity perfectly locked across the entire video. The same face, hairstyle, body shape, clothing, and accessories remain completely consistent. She has short chestnut hair tucked behind one ear, wears a mustard-yellow oversized hoodie, black athletic shorts, white crew socks, vintage running shoes, and a simple digital wristwatch. Location: a quiet countryside railway crossing at sunrise. Empty train tracks stretching into the distance, open grassy fields, wildflowers, old wooden fences, a small railway signal, morning mist, scattered birds, and distant hills. No houses, no streets, no vehicles, no city elements, no shops, and no crowds. The camera feels like an old consumer camcorder from the early 2000s. Unpredictable handheld movement, accidental zooming, exposure constantly adjusting, delayed autofocus, washed-out colors, visible digital noise, tape compression artifacts, soft image quality, slight motion blur, and completely unstabilized footage. It should feel like an amateur family recording, never cinematic. She begins sitting on the railway platform edge, tying her shoelaces while looking toward the empty tracks. She stands and slowly walks through tall grass, brushing wildflowers with her fingertips. A gust of wind lifts her hoodie as she laughs naturally. She discovers a paper airplane on the ground, unfolds it, smiles with curiosity, and gently tosses it into the air. The camera struggles to keep focus as it drifts away. She then stands beside the crossing signal, closes her eyes for a brief moment, taking in the morning breeze. In the final shot she walks away across the open field, turns once with a bright genuine smile, gives a small wave without speaking, and the recording suddenly stops mid-motion as if the camcorder battery died. Natural audio only: birds singing, insects, distant wind across the fields, grass rustling, soft footsteps, occasional railway signal clicking, and ambient countryside sounds. No music, narration, artificial effects, or post-production audio.

Subject & Pose:
Young woman taking a mirror selfie in a bedroom, standing in front of a bed, holding — AI image prompt — Seedream 5

CharacterFashion

Subject & Pose: Young woman taking a mirror selfie in a bedroom, standing in front of a bed, holding a phone in her right hand at chest level, her left hand holding an iced drink near her lips while sipping through a straw, relaxed casual pose, slight head tilt. Clothing: Fitted cream off-white ribbed knit tank top with thin straps and low scoop neckline, light wash high-waisted straight-leg denim jeans, showing a small strip of midriff Accessories: Olive green New York Yankees baseball cap worn forward, silver over-ear headphones (AirPods Max style) worn over the cap, large chunky gold hoop earrings, delicate gold cross pendant necklace, multiple gold rings on fingers, stacked gold bangle bracelets on both wrists Items: iPhone with pink floral rose pattern phone case, iced matcha green tea latte in clear plastic cup with dark green straw Hair & Makeup: Long brown wavy hair flowing past shoulders, natural glam makeup, nude lip Background: Minimalist white bedroom, white textured bedding, black woven leather shoulder bag laying on bed, distressed white vintage nightstand with white ceramic lamp, glimpse of leopard print pillow Technical: Soft diffused natural window lighting, warm color tones, vertical 9:16 aspect ratio, lifestyle photography, influencer aesthetic, high resolution, shot on iPhone, realistic skin texture

A straight-on medium-wide cinematic shot at eye-level, static locked frame, 4:5 vertical, captures a — AI image prompt — Seedream 5

CharacterCinematicBright

A straight-on medium-wide cinematic shot at eye-level, static locked frame, 4:5 vertical, captures a sun-bright late-morning inside a Lake Como villa courtyard room, camera perpendicular to the wall plane with no tilt, the atmosphere crisp and alive like the minute before heading out for gelato, the wall behind the scene a warm hand-troweled sable butter-yellow lime plaster slightly uneven with soft sun-bleach along the upper right edge, the floor matte burnt-terracotta chili tile grounding the frame, grout lines aged and dusty. Centered lower in the frame, a fully restored 1965 Vespa Primavera in glossy melon-orange lacquer parked on its side stand parallel to the camera, full profile visible, polished chrome Vespa badge on the legshield catching light, round chrome headlamp glinting, chrome handlebars and mirrors, aged cognac brown leather saddle, a silk twill scarf in marine navy, chili orange, cream and cognac pattern loosely tied around the right handlebar with tails cascading down, a small wicker basket bag on the left handlebar spilling a baguette and green grapes. The subject is a stunning World Cup beauty in her mid-twenties, with radiant sun-kissed skin and natural healthy glow, long silky dark chestnut brown hair loosely pulled into a soft low bun with gentle face-framing waves, striking hazel eyes with bright lively spark looking directly into the camera, high cheekbones, full lips in a soft warm cognac-rose shade with corners gently lifted in quiet joy. She is seated sideways on the Vespa saddle, body in a bright open three-quarter twist toward the camera, both legs crossed at the ankles on the same side, knees angled toward the lens, one hand resting lightly on the chrome handlebar, the other arm relaxed behind her on the rear of the saddle. Shoulders open and relaxed, natural breathing pose. She wears a fitted cream football jersey with subtle gold embroidery and thin spaghetti straps, tucked into a flowing cream bias-cut midi skirt that falls mid-calf, a slim cognac leather belt at the waist, flat cognac leather Roman sandals with ankle ties, stack of thin gold bangles on one wrist, delicate gold chain with small gold-and-coral pendant, small gold hoop earrings. Miu Miu oval sunglasses with thin gold frames and warm cognac lenses pushed up on her head. A cream quilted Miu Miu matelassé crossbody bag with gold chain slung across her torso. Natural skin texture with soft luminosity, gentle sheen on nose and lips, crisp morning sunlight, cinematic color grading, highly detailed, photorealistic, Slim Aarons style with modern World Cup energy.