Kenerate AI

Prompt Library

AI Prompt Library

Curated image, video and web design prompts from creators around the world. Copy any prompt, swap the subject or style, and generate with the latest models.

15,630 prompts · Updated daily · 100% free

209 prompts

Coffee Run Fashion Film Prompt
Seedance 2.0

Coffee Run Fashion Film Prompt

FORMAT: 16:9 landscape, 15 seconds, photorealistic live-action, cinematic lifestyle fashion film. CHARACTER CONSISTENCY: Use the uploaded character sheet as the master character reference. Keep the girl’s face, facial proportions, long wavy brown hair, hairstyle, hair clip, gold earrings, body proportions, burgundy pinstriped fitted shirt, wide-leg dark denim, and white sneakers exactly consistent throughout every shot. Do not change her outfit, hairstyle, age, or appearance. SHOT 1 — 0:00–0:05 A cozy rustic café in warm afternoon sunlight. The girl enters naturally carrying a small shoulder bag. Camera follows her from behind at waist height as her long wavy brown hair moves gently while she walks. She approaches a small wooden table near a sunlit window. Camera: smooth handheld tracking shot, natural movement, shallow depth of field. SHOT 2 — 0:05–0:10 She sits comfortably, crosses one leg over the other, picks up a simple white ceramic coffee cup, and takes a relaxed sip. Cut to intimate close-ups of her gold earrings, fingers around the cup, burgundy striped shirt, and flowing hair. Camera: subtle push-in, realistic handheld micro-movement, warm sunlight across her face and hair. SHOT 3 — 0:10–0:15 Side-profile shot as she looks peacefully toward the café window. She notices something outside, gives a tiny natural smile, then stands and walks toward the door. Final shot follows her from behind as she exits into warm daylight, her hair moving naturally. VISUAL STYLE Soft feminine lifestyle aesthetic, cozy European café atmosphere, warm beige and brown surroundings, natural sunlight, realistic skin texture, detailed hair strands, subtle film grain, authentic candid expressions, understated fashion editorial feeling. IMPORTANT: No exaggerated posing, no slow motion, no beauty-filter effect, no outfit changes, no face changes, no additional accessories, no cartoon/CGI appearance. Keep the performance natural and effortless. 16:9 LANDSCAPE • 15 SECONDS • PHOTOREALISTIC • CINEMATIC • NATURAL CAMERA MOVEMENT

@Caden Flux
Gothic Cathedral Knight King Scene
Grok Imagine

Gothic Cathedral Knight King Scene

Create a photorealistic cinematic full-body scene in the same dark gothic cathedral with dramatic volumetric light rays and stone columns. The mysterious armored knight king in black ornate armor, golden crown, red velvet hooded cloak with gold embro...

@Cyperpienso
Animate Ghost Decoration in Kitchen
Grok Imagine

Animate Ghost Decoration in Kitchen

animate this exact image , A light-up ghost decoration in a cozy kitchen at night, captured in a slow, dreamlike twirl… … The white sheet is mid-motion, soft and flowing, but the movement is gentle and unhurried, like the ghost is remembering a dance...

@Alicia McNatt
Seaside Table Setting Video Prompt
Grok Imagine

Seaside Table Setting Video Prompt

Table set with a pot of soup cornbread wedge of cheddar cheese glass of water with lemon wedge window over looks the sea hummingbird feeder with hummingbird outside the window

@Lindy Hawkinson
Epic Ocean Staircase Future Vision Prompt
Seedance 2.0

Epic Ocean Staircase Future Vision Prompt

An enormous staircase emerges from the middle of the ocean and rises into the clouds. People gather in disbelief. A young explorer begins climbing. Each step reveals Earth further into the future. First step: futuristic cities. Next step: forests growing on skyscrapers. Next: oceans filled with floating civilizations. Higher: giant orbital rings surrounding Earth. Higher: cities drifting through the atmosphere. Higher: humanity traveling among stars. The climb becomes faster and more dangerous. Thousands follow behind. The staircase stretches beyond the clouds and into space. The explorer reaches the final visible step. Beyond it lies a future so vast and magnificent it cannot fully be understood. A brilliant light floods everything. The staircase disappears. Leaving only the ocean below. Epic science fiction adventure, continuous upward motion, escalating future visions, breathtaking scale, emotional wonder, photorealistic environments, cinematic camera movement, dynamic action, masterpiece visuals, 16:9.

@Alexandra Aisling
Cyberpunk Woman Walking Neon Alley
Seedance 2.0

Cyberpunk Woman Walking Neon Alley

Ultra-realistic cinematic cyberpunk scene of a fierce young woman walking confidently through a dark neon-lit city alley at night. She has long dark hair, an intense expression, and wears a futuristic white oversized jacket over a red cropped top, black tactical pants, gloves, and utility accessories. Wet streets reflecting red and warm city lights, atmospheric mist, glowing signs, dramatic shadows, shallow depth of field, cinematic bokeh, dynamic camera movement, realistic skin and fabric textures, high detail, moody action-film atmosphere, 85mm lens, f/1.4, HDR, 8K, photorealistic, vertical 9:16 composition.

@AIwithMinal
Renaissance Maiden Bridge Scene
Grok Imagine

Renaissance Maiden Bridge Scene

Create a image overnight and shining on carrying a maiden across a broken bridge renaissance. She will be fine. She’s just bruised on her outer ego.

@Maria Of Mars
Sci-Fi Car Wash Klein Bottle
Grok Imagine

Sci-Fi Car Wash Klein Bottle

They immediately developed self-cleaning optics for all of their systems and they start to have a massive car wash in an infinite-dimensional Klein bottle

@The 555 RGB Dimension
Forest Passage Under Stars
Grok Imagine

Forest Passage Under Stars

A quiet passage through a forest glowing beneath the stars A hidden lake, a sky full of stars, and just a trace of light along the shore. Sometimes the most magical places are the quietest. ✨🌌

@Nagarjuna Creates
Grok Imagine Video Prompt: Elon Musk Silent Movie Parody
Grok Imagine

Grok Imagine Video Prompt: Elon Musk Silent Movie Parody

Please create another parody silent movie about {argument name="character" default="Elon Musk"}, using any topic demonstrating behaviors in humans that confuse Artificial Intelligence models. The audio is only old-timey music like they used to have in the old days.

@TheAric
Ink Wash Style Wuxia Video Prompt
Seedance 2.0

Ink Wash Style Wuxia Video Prompt

[0–3s] Camera: Rapid push-in from a close-up of the blade's glint, while the camera rotates clockwise at 180°/s, cutting into the silhouette of a bamboo hat (douli). Visuals: Close-up of ink-wash blade light, particle sparks bursting outward; the douli silhouette emerges from billowing ink clouds. Effects: Motion blur, ink brushstroke trails, particle effects. [3–6s] Camera: High-speed 360° orbit centered on the character (270°/s), following the trajectory of the sword swing. Visuals: Medium shot of the character swinging the blade, robes billowing, ink brushstrokes flowing with the motion. Effects: Dynamic ink smoke, motion blur on the robes, visual drag caused by the rotation. [6–9s] Camera: High-speed lateral tracking shot (left → right), while the camera tilts and rotates counterclockwise at 90°/s, locked onto the blade's path. Visuals: The blade's trajectory line, particle sparks bursting outward, ink brushstroke trails. Effects: Motion blur, particle effects, ink ghosting trails. [9–12s] Camera: Low-angle upward shot with a fast crane-up, while the camera spirals at 225°/s, rising from the ink marks on the ground to the character's upper body. Visuals: Ink marks on the ground, the character mid-swing (upper body), rolling ink clouds in the background. Effects: Dynamic ink clouds, motion blur during the rise, ink-colored vortex created by the rotation. [12–15s] Camera: Slow-motion close-up, with the camera rotating slowly clockwise at 15°/s as the blade light freezes in place. Visuals: Close-up of the blade light, crisp and clear particle effects, the character's gaze beneath the shadow of the douli (optional). Effects: Slow motion, particles dissipating, subtle camera shake.

@Zidan 子丹
Funny Ancient Chinese Flying Cloud Video Prompt
Seedance 2.0

Funny Ancient Chinese Flying Cloud Video Prompt

10 seconds, 9:16 aspect ratio, realistic funny short video. At an ancient Chinese architecture scenic spot, a young Asian woman wearing traditional ancient costumes stands on a white cloud, about 2 meters above the ground, slowly flying forward stepping on the cloud. First 4 seconds: The girl and the white cloud move stably and synchronously forward, with the girl looking relaxed and natural. Starting from the 4th second, a sudden lateral strong wind blows, moving the girl's hair and sleeves. The white cloud under her feet is slowly blown to the right side alone, while the girl does not follow the cloud. After the white cloud completely leaves the girl's feet, she remains suspended in the original position for half a second. She first looks down at her feet, then looks up at the drifting cloud, showing a confused expression. Then the girl loses support and falls vertically out of the frame. The white cloud continues to drift leisurely into the distance. Key points: The cloud is blown away horizontally by the wind, leaving the person in place; after the cloud leaves, the character suspends for half a second before falling. Do not include complex magical effects.

@Adam也叫吉米
Realistic Fitness Vlog with DV Aesthetic
Seedance 2.0

Realistic Fitness Vlog with DV Aesthetic

Create a 30-second, 4:3 horizontal aspect ratio, highly realistic personal fitness Vlog that captures the feel of a friend casually recording a daily workout with a early-2000s home DV camcorder. It is not a fitness ad or a polished cinematic short. The 30 seconds is an edited summary of the fitness process, connecting leaving home, preparation, training, and ending through natural jump cuts; do not rush the character to complete everything in 30 seconds, and do not use speed-ups. [Character & Clothing] Use the uploaded full-body image of the person in grey sportswear [@Image1] as the sole character reference. The protagonist is the adult female from the reference image, strictly maintaining her facial features, face shape, eyes, nose, lips, thin-framed glasses, hairline, and overall age appearance. She must remain the same person from different angles, during exercise, speaking, and smiling; she cannot become another similar-looking face. The reference image is only used to determine identity, clothing, and body appearance; do not reuse the white studio background or the fixed standing pose from the original image. The character has a natural, healthy fitness physique with moderate muscle definition in shoulders, arms, waist, abdomen, and legs, showing real muscle contraction and stable body control during movement. Maintain the overall height and body proportions from the reference image; do not exaggerate muscles, overly cinch the waist, or lengthen legs. Keep skin fair and delicate but with natural texture; slight redness may appear after exercise, but no excessive smoothing or plastic look. Wear the same set of sportswear from the reference image throughout: heather grey wide-neck short-sleeve T-shirt with the neckline naturally tilted, exposing her right shoulder (left side of the frame when facing front); the hem tied at the same-side waist forming a cropped style exposing the waist/abdomen, keeping the original pink-purple print on the chest; underneath is a pink-purple thin-strapped sports bra with straps and edges naturally visible; bottom wears heather grey high-waisted tight sports shorts, paired with white ribbed mid-calf sports socks and the same white lace-up sneakers as in the reference image. Clothes should have real wrinkles and slight displacement due to movement, but cannot change style, color, material, knot position, or exposed shoulder direction. Do not change into black tops, long leggings, blue socks, or boots. When leaving, keep the loose black long hair from the reference; tie it into a ponytail by hand before entering the gym, then maintain the same ponytail throughout, keeping natural bangs and sideburns; do not suddenly change bangs or hair volume. Glasses are worn throughout, maintaining reasonable position during exercise. Props are fixed: a small black gym bag, a transparent water bottle with a white cap, and a small white towel; do not change their appearance across shots. [Shot Flow] 0–3s | Going to nearby gym. Quiet community street, natural daylight. Friend films from her side-front while walking; she wears the aforementioned grey sportswear, carrying a small black gym bag on one shoulder, walking towards the nearby gym. Black long hair sways gently with steps. She briefly looks at the camera with a natural small smile, then continues looking at the road, not posing deliberately. Camera has slight undulation from walking, composition slightly off, like casual recording. 3–6s | Tying hair. Stops near gym entrance, side medium close-up. She raises hands to gather long hair, ties it into a neat ponytail with a black hair tie, then adjusts glasses and bag strap. Natural jump cuts may skip part of the tying process, but viewers must see the actual action from loose hair to ponytail; hairstyle cannot change magically. Movements are relaxed and skilled, contact between fingers and hair is realistic. 6–9s | Putting things down, simple warm-up. Cut to ordinary community gym, black rubber floor, dumbbell rack, bench, wall mirrors, environment realistic with traces of life usage, not luxurious empty commercial studio. She places black gym bag next to bench against wall, puts water bottle and white towel on one end of bench. Natural jump cut to her lightly moving shoulders, stretching arms, adjusting breathing. Camera feels like friend shooting casually from side, not deliberately showcasing body. 9–15s | Simple strength training. Two normal-speed training clips: first film her doing light dumbbell curls, fully presenting smooth lift, brief pause, controlled lowering; shoulders don't shake wildly, palms grip dumbbells realistically, arms show natural muscle lines with effort; then cut to side-front medium-full shot filming her completing one bodyweight squat, from standing to squatting and back up stably, feet contact ground, knee and hip movement reasonable, torso stable. She focuses on breathing, exhales softly when exerting force, doesn't pose for fitness camera. Sportswear shows natural stretch and wrinkles, ponytail swings slightly with movements. 15–20s | Treadmill jogging. Side-front handheld medium shot, she jogs easily on treadmill, stride moderate, left and right feet alternately contact belt, arms swing naturally, ponytail sways rhythmically with steps. Breathing becomes slightly heavier, small amount of sweat appears gradually on forehead, nose wings, and neck sides, not suddenly soaking wet. She glances at camera, smiles lightly with expression tired yet amused. Then natural cut to treadmill slowing/stopping, she confirms stability before stepping down, does not jump off running belt. 20–25s | Drinking water, wiping sweat. Returns to same bench, unscrews same water bottle, takes two small sips, then presses small white towel gently on forehead and neck sides. Towel has real contact and occlusion with skin, does not pass through glasses, does not wipe away all sweat directly. She accidentally sees sweaty self in mirror, laughs lightly, a real relaxed reaction after exercise, not exaggerated acting. Reflection's actions, clothing, and position must accurately correspond to person. 25–30s | Done working out. Sits on bench, breathing still slightly rapid, shoulders rising/falling with breath, holding towel. Friend brings camera closer, she looks up at camera, says naturally in Chinese tone with smile: "Today's workout felt pretty good!" Voice carries post-exercise breath, mouth shapes accurate, ends with light laugh. Finally natural cut to her carrying same black gym bag towards exit, ponytail swinging lightly, camera follows half-beat slow, ending in lifelike action, no advertising freeze-frame. [Photography & Visual Quality] Entire segment presents early-2000s consumer MiniDV recording quality: slight handheld shake, imperfect composition, occasional delayed follow-focus, slight autofocus search, brief exposure/white balance changes when moving outdoors to indoors, soft digital details, slight shadow noise, normal motion blur, and one unskilled small zoom. These flaws should be restrained and random, not every shot intentionally out-of-focus or violently shaking. Character's face always clear enough to recognize same person from reference. Primarily eye-level medium shots, medium-full shots, and natural facial close-ups; training shots retain necessary body/equipment info, no deliberate close-ups on chest/buttocks. No stabilizer-smooth moves, blockbuster grading, slow-mo, lens flares, film burn, exaggerated grain, or fake tape glitches. DV device itself does not appear in frame. [Audio] Only ambient sounds: community footsteps, slight street noise, door push, bag strap/cloth friction, gym AC hum, distant blurred conversation, light dumbbell placement, shoe-ground contact, treadmill motor sound, gradually heavier breathing, bottle opening/drinking, towel friction, natural laughter, and final character dialogue. Audio quality has slight noise/space sense from home DV mic, no studio vocals. No BGM, no narration, no subtitles. [Negative Constraints] Prohibit identity drift, face changing, glasses disappearing/deforming, hairstyle switching without reason, clothes changing color/style, exposed shoulder flipping left/right, body proportion changes, exaggerated muscles, plastic skin, beauty filters, abnormal skin texture, unreasonable sweat, distorted palms, extra fingers, equipment deformation, dumbbells passing through hands, foot sliding, distorted running motions, items floating/teleporting, wrong mirror reflections, duplicate protagonists, props appearing suddenly. Except for existing prints/marks on reference clothing, do not add brand logos, watermarks, date/timestamps, UI text, or other screen text.

@疯狂的田螺君
Rainy Night Bus Stop Anime Video
Seedance 2.0

Rainy Night Bus Stop Anime Video

Rules: - Budget-scale theatrical anime quality, Japanese high-end figure-like matte 3DCG - Multi-shot - Fast cuts, many frames per second. Prioritize speed and impact - Professional-grade VFX - Change camera work every shot (no repetition of same movement) - No BGM; ambient sound/SFX only - No subtitles - All dialogue in Japanese - Pacing: Take time to show quiet acting, move quickly during showcase moments - Rain is fine, fast, real rain. Physically accurate depiction of splashes on the ground, light reflections on wet pavement, weight of wet hair and cloth - Night rain. Reflect warm colors from streetlights and neon on wet pavement; do not let the screen sink into gray - Keep the protagonist large in the frame; face and outfit clearly visible. Do not make them tiny in long shots - No text, logos, or numbers on screen @ Image1: Subject - Akane [Consistency] Maintain Akane's face, long hair transitioning from salmon orange to silver tips, red and white round hair ornaments, and red long coat with round buttons and white circular patterns throughout. Only one Akane. The red umbrella belongs to Akane. [Generation Goal] Rain Sound Orchestra (5 stages, 1 continuous video. From a rainy night bus stop to conducting rain across the city) [S1] Rainy night bus stop. The moment a raindrop hits the round button on @ Image1 Akane's coat, a piano note 'Poon' sounds, and a ring of light expands from the button. Camera: Extreme close-up of the button. Capture the instant the raindrop hits. [S2] Akane, sitting alone looking bored on a bench, suddenly looks up. Flicking the button again produces another sound. Akane smiles mischievously. Camera: Front view of bus stop, medium shot. [S3] Akane stands up and waves her closed red umbrella like a conductor's baton. Rain falling on tin roof becomes drums, gutters become xylophones, puddles become cymbals; each raindrop impact creates colorful droplets of light. Camera: Fast cuts zooming in sequentially on roof, gutter, puddle. [S4] Conducting grows larger, rain across the street glows with light, turning the gray night city into a shining colorful rain. Akane's long hair flows from orange to silver. Camera: Orbiting around Akane while rising. [S5] With the final wave, all raindrops stop in mid-air, floating like glowing musical notes. Akane lowers her umbrella and bows; the stopped rain falls all at once, creating applause-like rain sounds. Camera: Front view of bowing Akane, bust shot through glowing raindrops. Akane (shyly) says: {I kind of like rainy days}

@妖精アーヤ
Initial Singularity and E=mc2 Visualization
Grok Imagine

Initial Singularity and E=mc2 Visualization

Create for me what the "Initial singularity" might have looked like and contrast that with the cooling of the Universe as the energy condensed into matter. Present for me a pictorial of Einstein's theory: E = mc2 No text on the picture Grok

@Kim Maria
Dark Fantasy Warrior Sequence
Grok Imagine

Dark Fantasy Warrior Sequence

Create a 15-second cinematic vertical 9:16 dark-fantasy action sequence, inspired by high-budget Asian fantasy cinema. Scene 1 — 0–3s: A mysterious white-haired warrior stands in a misty ancient mountain forest, surrounded by shallow reflective water. Long white hair moves naturally in the wind, wearing elegant black-and-white fantasy robes. The camera slowly pushes toward the warrior as blue-white energy begins swirling around them. Scene 2 — 3–7s: Several shadowy black-armored warriors emerge through the mist and rush forward. The white-haired warrior suddenly moves with supernatural speed, creating a powerful circular wave of glowing blue water and energy. Cinematic slow motion, realistic cloth and hair physics, flying water droplets. Scene 3 — 7–11s: Close-up combat. The white-haired warrior blocks an enemy weapon with a glowing energy blade. A bright blue-white shockwave explodes between them, sending water droplets and particles through the air. Dynamic camera orbit, dramatic impact, detailed facial expressions. Scene 4 — 11–15s: The warrior releases one final concentrated energy strike. A huge arc of blue-white energy sweeps across the water, knocking the shadow warriors backward. End with the white-haired warrior standing calmly in the mist as glowing particles fall around them. Visual style: photorealistic cinematic fantasy, ultra-detailed characters, realistic skin and hair, physically accurate water, volumetric fog, dramatic moonlight, deep shadows, blue-white magical energy, realistic particle effects, anamorphic cinematic lighting, shallow depth of field, smooth camera motion, high-budget VFX, epic atmosphere. No text, no subtitles, no logos, no watermark, no cartoon look, no distorted faces, no extra limbs, no blurry characters. Maintain consistent character appearance throughout the entire video.

@Rizi
Ice Monster Attack in Ski Lodge
Seedance 2.0

Ice Monster Attack in Ski Lodge

Cinematic horror-thriller short film set at a mountain ski resort lodge during a snowstorm, opens with an immediate hook, grounded realistic style, maximum dynamic camera work. Setting: a cozy wooden lodge interior with a fireplace, large windows looking out to falling snow, guests relaxing with hot drinks. CHARACTER LOCK: the main character is a lodge staff member, a woman in her late 20s, red ski jacket, consistent in every shot. Muted cold-toned color grading, natural diegetic sound throughout, tension score entering immediately. > > **[0-1s]** Hard cut: the large lodge window frosts over instantly from outside, ice crystals spreading unnaturally fast across the glass. > > **[1-2s]** It shatters inward, a humanoid creature of jagged ice and frost crystal stepping through, breath visible as steam in the sudden cold. > > **[2-3s]** Nearby guests gasp, backing away from their tables near the fireplace. > > **[3-4s]** It moves toward the nearest guest, a thin layer of frost spreading across anything it touches. > > **[4-5s]** He stumbles back, his sleeve frosting over where it brushed him. > > **[5-6s]** Panic spreads through the lodge, guests scrambling toward the far end of the room. > > **[6-7s]** The staff member grabs a fire poker from beside the fireplace, stepping between the creature and the fleeing guests. > > **[7-8s]** It turns toward her, crystalline features catching the firelight. > > **[8-9s]** She swings the poker; it connects, a crack splintering across its icy shoulder. > > **[9-10s]** It recoils, frost receding slightly from the point of impact. > > **[10-11s]** A second staff member grabs a thermos of hot water, flinging it directly at the creature. > > **[11-12s]** Steam erupts where the water hits, the ice visibly weakening at the contact point. > > **[12-13s]** It staggers, momentarily destabilized, frost patterns flickering across its form. > > **[13-14s]** The staff member presses the advantage, striking again with the poker. > > **[14-15s]** Wide shot: guests reach the far hallway, a few glancing back in fear. > > **[15-16s]** The creature lunges toward her, icy claws reaching out. > > **[16-17s]** She ducks low, narrowly avoiding the strike, rolling toward the fireplace. > > **[17-18s]** She grabs a burning log directly from the fire with gloved hands. > > **[18-19s]** SLOW MOTION insert: she swings it in an arc toward the creature's chest. > > **[19-20s]** Contact sends a shockwave of cracking ice through its entire body. > > **[20-21s]** It freezes mid-motion, fractures spreading rapidly across its crystalline form. > > **[21-22s]** SLOW MOTION: it shatters apart into scattering ice fragments and swirling cold mist. > > **[22-24s]** Wide shot: the fragments melt quickly near the fireplace's warmth, leaving only a damp patch on the floor. > > **[24-26s]** She stands breathing hard, log still smoking slightly in her hand, snow drifting in through the broken wi

@auqib
Village Around Giant Tree Timelapse
Seedance 2.0

Village Around Giant Tree Timelapse

Create a 30-second vertical 9:16 ultra-photorealistic miniature construction time-lapse: a spectacular village physically built around ONE enormous ancient tree. Hundreds of tiny realistic adult workers are visible continuously, working simultaneously with tools, ladders, ropes, carts and miniature cranes. Fast but readable construction, macro cinematic photography, natural sunlight, realistic wood, stone, soil, moss and vegetation, 4K HDR, live-action realism. 0–2s: Workers clear the ground, mark foundations and dig around the giant tree roots. 2–4s: Foundation stones and wooden floor beams are placed; workers erect the first timber posts. 4–6s: Wall panels, floorboards and support beams are assembled piece-by-piece. 6–8s: Workers lift rafters, build pitched roofs and place wooden shingles one-by-one. 8–10s: Teams climb the trunk and construct elevated platforms around the massive branches. 10–12s: Treehouses rise as workers install walls, windows, doors, balconies and roofs. 12–14s: Workers build wooden bridges and spiral staircases connecting the treehouses. 14–16s: More cottages are physically constructed outward from the giant tree, foundation-to-roof. 16–18s: Hundreds of workers lay stone pathways, fences and a small wooden stream bridge. 18–20s: A marketplace is assembled beneath the tree with stalls, counters and storage huts. 20–22s: Higher platforms, balconies and connected treehouses expand through the branches. 22–24s: Workers install railings, ladders, rope bridges, lantern posts and flower boxes. 24–26s: Teams place stones, plant flowers and trees, create gardens and finish winding paths. 26–28s: Final construction details are secured while hundreds of workers continue moving materials and working across the entire village. 28–30s: Golden-hour reveal. Tiny villagers cross bridges and paths as the camera smoothly pulls backward and rises, revealing the enormous ancient tree surrounded by the completed multi-level village. KEY RULE: Every 2 seconds introduces a NEW visible construction stage while previous teams continue working. Buildings must visibly progress foundation → beams → walls → roof → details. No instant completion. NEGATIVE: cartoon, toy, plastic, CGI look, magical construction, instant appearance, morphing, teleportation, floating objects, disappearing materials, duplicated workers, giant humans, children, anatomy glitches, changing tree, inconsistent architecture, empty scenes, text, logos, watermark.

@Maverick | AI
Seedance 2.0 Mini Cinematic Escort Battle Prompt
Seedance 2.0

Seedance 2.0 Mini Cinematic Escort Battle Prompt

Cinematic photorealistic texture, pure ancient Chinese Xianxia action film, 15 seconds, 16:9, Seedance 2.0 Mini. This round is not a stationary duel, nor does it continue to repeat the old pattern of "switch to a new weapon → protagonist studies → counter → sword stops at throat". The core action motif is: A mobile escort battle occurring on the real high-altitude imperial road shown in the current reference image. The same Senior Sister and Junior Sister must continuously advance forward while protecting the injured Master, disciples, and ordinary people evacuating behind them. The enemies' true goal is not necessarily to defeat the two protagonists. What they want to do is: Break through the defensive line formed by the two protagonists; Cut into the evacuating crowd; Seal off the path for continued advancement. Therefore, the core of this entire battle is: **Break the blockade ahead Block pursuers behind The two protagonists continuously swap front and back positions Always reopen the path.** Actions pursue silkiness but must never be soft. Silkiness means: The previous action naturally leads to the next; Characters are always moving; Attack and defense never reset to zero; Weapon direction and character direction are always understandable; After cuts, one still knows who is in front, who is behind, and who is attacking from where. Power comes from: Sudden initiation; Obvious acceleration; Real collisions; Center of gravity changes; Force offsets; Imbalance; Inertia; Counter-grabs; Hard stops; Immediate restarts. Prohibit soft, dance-like swordsmanship. Prohibit resetting poses after striking once. Enemies must have real judgment. After the first strategy fails, they must change targets, attack routes, pursue, seal paths, flank, or actively separate the two protagonists. Prohibit enemies lining up to offer attacks. [Core Character Lock] Strictly lock only @Image 1 and @Image 2 as the two core protagonists along with their respective primary weapons. @Image 1 is always the same Sword Immortal Senior Sister as before: Same adult East Asian female identity; 25–30 years old; Same face; Black long hair half-tied; White jade hairpin; Tall and slender proportions; White embroidered silk Hanfu; Semi-transparent layered wide sleeves; Silver waist sash; Jade pendant; White cloth boots; The only silver straight sword in the entire film. @Image 2 is always the same Junior Sister as before: Same adult East Asian female identity; 20–25 years old; Same face; Black braided hair; Petite proportions; Cyan-green linen Hanfu; Dark belt; Wooden hairpin; Black cloth shoes; The only dark steel sword in the entire film. Enemies, Masters, disciples, ordinary people, and bystanders are all merely functional supporting characters. Do not waste generation attention strictly locking supporting characters' faces, hairstyles, and complex clothing. Just ensure that character types, positions, weapons, and action functions remain logically continuous within the shot. [Round-Specific Scene Hard Anchor | Highest Priority] The uploaded background reference for this round already displays a complete, highly recognizable location. Therefore, this round directly enters: HARD LOCATION ANCHOR. The reference image is not style inspiration. The entire video must truly take place on the same high-altitude celestial palace imperial road shown in the reference image. Prohibit redesigning it into a "similar Xianxia location". Must continuously maintain the following location identities: The central axis of the frame always contains the same extremely long, straight, pale white high-altitude imperial road, extending from the foreground towards the distant center. The imperial road always maintains obvious narrow depth; characters primarily move along the front-back direction; prohibit expanding it into a circular arena, huge courtyard, or wide plaza. The left and right sides of the imperial road always maintain the same massive high-altitude drop, milky white sea of clouds, and continuous large waterfalls. The mid-ground left and right continue to contain the same group of huge traditional palaces, maintaining original left-right positions, volume, and spatial relationship with the imperial road. The left foreground continues to retain the same extremely prominent large dark cantilevered wooden structure building; dense wood structures must not disappear or shrink into ordinary small buildings. Below the imperial road and under the mist, continue to maintain the same scale of dense ancient city. The farthest center continues to contain the same giant mountain body / superstructure. The distant center continues to retain the same huge ring-shaped gate / ring building. Characters are always much smaller than the imperial road, palaces, waterfalls, underlying city, and distant superstructures. Maintain the same bright cool white-grey, pale warm gold, low saturation daytime/morning light, milky white air haze, and huge depth as the original reference image. The distant huge ring must always remain very far away. Prohibit suddenly pulling it closer to become an ordinary mountain gate. Prohibit regenerating the current imperial road into: Circular arena; Ordinary courtyard; Wide plaza; Another cloud bridge; New floating platform; New mountain gate; New floating island; New cliff; New palace entrance; New large staircase. Prohibit suddenly widening the imperial road for convenient combat. Prohibit day turning into night. Prohibit replacing current soft weather with stormy dark clouds. All actions and cameras must adapt to the current real imperial road. Prohibit redesigning the scene for the sake of action. [Background Dynamics | Must be alive, but default non-participatory in plot] Scene continuously moves naturally. Distant clouds slowly move. Huge waterfalls continuously fall realistically downwards. Water mist at the bottom of waterfalls continuously swirls and merges with the existing sea of clouds. Cloud layers and fog layers at different distances maintain slightly different speeds, creating realistic parallax. High-altitude natural wind continuously affects the black hair, wide sleeves, hem, tassels, and accessories of the two protagonists. Thin mist between the distant ancient city and palaces continuously moves slowly. Atmospheric perspective continuously produces subtle changes. A few distant figures can naturally move within areas already existing in the reference image. However: The environment is narratively neutral by default. Waterfalls cannot suddenly help anyone. Mist cannot actively obscure enemies. Wind cannot change sword paths. Buildings cannot collapse on their own. The imperial road cannot break. The distant ring cannot suddenly activate spells. The environment cannot actively resolve combat. Only when characters truly step, hard stop, or collide with weapons, allow slight stone dust, scratches, metal sparks, fabric displacement, and sole friction debris. Already appearing obvious traces should reasonably persist. [0–5s | Hook: Cannot Retreat] 0.0–1.0s. Use 24mm ultra-wide angle central axis grand panorama. First reproduce the location; location priority is higher than complex action. The first glance must confirm: The same long white imperial road; Same huge waterfalls on left and right; Same large palaces on left and right; Same huge wooden structure on the left; Same ancient city below; Same huge distant ring. The two protagonists maintain small scale within the huge environment. Senior Sister is in front. Junior Sister is half a step behind. Further back at a distance, an injured elderly Master, several disciples, and a few ordinary people are continuing to advance along the same imperial road. Two enemy swordsmen block the path ahead. The leading enemy blocks the effective passage area with a horizontal sword: "Protecting them, you can't pass." Senior Sister does not stop at all: "Who said we were retreating?" As soon as the last word falls. The enemy launches without warning. The camera immediately transitions from fixed grand panorama to approx. 32–35mm tracking shot retreating along the imperial road axis. The first enemy quickly seizes Senior Sister's center line. Senior Sister never retreats backwards. Until the last moment, she only shifts diagonally by half a body width, using the same silver straight sword to complete a short, hard, real collision, pushing the enemy sword out of the imperial road's central axis. No follow-up strike. No posing. She immediately continues forward past the enemy's shoulder. Almost simultaneously. The second enemy cuts towards Junior Sister from the opposite direction, trying to bypass her to attack the crowd behind. Junior Sister does not chase enemies wildly. She directly rushes into the position between the enemy and the evacuating crowd, only briefly changing the opponent's attack line with the dark steel sword, then continues forward. An enemy passes quickly near the camera, body instantly filling the screen, forming the first natural hidden cut. By the end of 0–5 seconds, the audience must clearly understand: They are not staying to win. They are reclaiming the path. [5–10s | Upgrade: Enemies Start Attacking True Targets] Maintain completely identical imperial road, left/right palaces, waterfalls, distant ring, and world scale. Use approx. 35mm medium shot tracking moving along the bridge axis. After the first attack fails, enemies must proactively change strategy. The enemy leader no longer insists on winning head-to-head against Senior Sister. He suddenly changes target, actively trying to bypass Senior Sister, cutting between Junior Sister and the evacuating crowd. Another enemy simultaneously presses Senior Sister from the opposite direction, trying to truly separate the two protagonists. Actions form a continuous causal chain: Enemy horizontal slash forces Senior Sister to briefly deviate from the imperial road center line; Senior Sister only performs one brief force release, not continuing entanglement; The impact inertia already invested by the enemy causes their body to slightly overshoot the optimal attack position; Junior Sister continues forward. The leading enemy suddenly cuts diagonally from Junior Sister's right front. Junior Sister catches the first strike. The enemy does not pause, immediately changing to a second low-position attack. Junior Sister is forced to shrink half a step towards the imperial road center line. Just at the moment the enemy judges she has been sealed off —— Senior Sister suddenly rushes fast from behind Junior Sister to the other side. The two complete the first extremely fast front-back position exchange. Not a double rotation. Not a synchronized pose. But a compact shoulder-crossing position swap while maintaining forward motion. Senior Sister directly takes over the enemy originally pressing Junior Sister. Junior Sister continues forward along the half-path opened up, becoming the new front position. The camera only performs a short lateral move due to the two's real position swap. An enemy sword grazes past the lens, forming a natural occlusion transition. Prohibit unreasoned orbiting. At this moment. High-speed pursuit footsteps come from behind. A functional pursuer originally falling further back has arrived. Someone blocking the path ahead. Someone pursuing from behind. The two women are truly trapped for the first time in the most dangerous situation of the narrow imperial road: Front and rear pincer attack. [10–15s | Flip: Don't Guard People, Guard the Path] Re-widen to approx. 28–32mm moving medium shot. Use nearly 1 second to fully explain current space: Junior Sister is in front; Senior Sister is about one body length behind; Front enemy leader reoccupies center line; Rear pursuers approaching fast; Evacuating Master, disciples, and ordinary people are still moving in safer positions further away. Everyone remains on the same real imperial road from the reference image. Prohibit suddenly cutting to other platforms. Front enemies and rear pursuers launch almost simultaneously. Junior Sister instinctively wants to turn back. Senior Sister only says: "Don't guard me." Junior Sister stops turning back. Senior Sister immediately follows with: "Guard the path." The two explode almost simultaneously. Junior Sister does not turn back to save Senior Sister. She continues forward, using a short and hard dark steel sword collision to forcibly push the front enemy's blade edge out of the imperial road's central axis. Senior Sister simultaneously handles the rear pursuer. She intentionally yields half a step, letting the enemy truly enter attack range. Just at the moment the opponent's body strength has been invested, she suddenly cuts diagonally out of the attack axis. The pursuer's own forward momentum causes their body to overshoot by half a body length. Senior Sister does not chase. Immediately accelerates forward again. At this moment, Junior Sister has already pushed the front enemy half a body length away from the center line. The two protagonists approach at high speed. Shoulder lines graze at extremely close distance. Complete the second front-back position exchange. This time, they don't look at each other at all. Junior Sister naturally falls to the rear position, taking over the enemy who has turned around to pursue again. Senior Sister becomes the front position again, facing the leading enemy still blocking the path. An enemy sword sweeps across the camera foreground, instantly filling the screen, forming the most explicit weapon-occlusion hard cut of the whole film. Cut to a slightly lower reverse camera position. Senior Sister only performs one extremely short, extremely fierce outward deflection with the silver sword. The leader's sword path is thoroughly pushed out of the imperial road's central axis. Because his body weight was already invested forward, his own inertia carries his body sideways by about two body lengths. Enemies cannot fall off the bridge. Cannot be exaggeratedly blown away. Do not need to completely lose combat ability. Just opening the path is enough. Senior Sister and Junior Sister absolutely do not stop to deliver finishing blows. The two pass directly between the enemies, continuing along the same white imperial road towards the distant huge ring. The rear evacuating crowd also begins to advance along the reopened route. The enemy leader turns back and shouts angrily: "You can't win!" Do not cut to heroic frontal close-ups. The camera continues to follow the two women advancing from the side-rear. Junior Sister is still adjusting her breathing: "We were never here to win." Senior Sister always looks at the road ahead: "As long as the road is there, that's enough." Leave only an extremely short beat. Deeper down the same distant imperial road, several functional enemies originally existing in the distant figure layer begin to slowly spread out, entering next-round path-blocking positions. Prohibit generating them from thin air in the mist. Prohibit refreshing them suddenly from buildings. They existed in the real distance from the beginning, only revealing hostility through movement at this moment. The two protagonists do not slow down at all. Silver sword and dark steel sword maintain natural low-position readiness. The camera continues to retreat along the imperial road axis. Black hair, hems, waterfalls, mist, clouds, distant palaces, and the huge world always move naturally. In the state where the two are still actively walking towards the next batch of enemies: Direct cut to black. [Camera & Editing] Three narrative segments, but absolutely not mechanically equal to three shots. The whole film uses a small amount of truly functional cuts. Main camera routes: 24mm central axis grand panorama confirming real location → 32–35mm tracking retreating along existing imperial road axis → Human body passing lens forms hidden cut → Weapon grazing lens forms occlusion cut → When front-rear pincer occurs, re-widen shot to explain space → Finally side-rear continuously following two protagonists advancing towards distant ring. All cuts can only be triggered naturally by the following events: Character occlusion; Weapon occlusion; Real weapon collision; Obvious change in movement direction; Obvious body imbalance; Sudden change in speed. Prohibit mechanical fragmented cutting. Prohibit camera being more restless than the action. Prohibit meaningless ORBIT. Prohibit changing positions of imperial road, palaces, waterfalls, and distant rings for camera movement. Action drives the camera. The camera cannot drive scene deformation. [Sound] Opening first establishes: High-altitude natural wind; Low-frequency rumble of huge waterfalls existing continuously at a distance; Footsteps on light-colored stone imperial road; Extremely distant ancient city environmental noise floor. After combat explosion add: Short sharp sword wind-breaking; Hard, sharp metal collisions; Shoe sole friction; Silk fabric twitching; Fast footsteps of pursuers; Gradually heavyening character breathing. When front-rear pincer forms, temporarily lower music and wide environmental sound field. Highlight: Footsteps; Breathing; Weapon directions. After the path is reopened, combat sounds gradually fade behind the characters. Final dialogue must be clear: "We were never here to win." "As long as the road is there, that's enough." After dialogue ends: Waterfall; High-altitude wind; Continuous forward footsteps Reoccupy the main sound field. Music must never overpower action details and dialogue. [Seedance 2.0 Mini Generation Priorities] P0: The location identity of the uploaded background reference image absolutely cannot change. P0: Identity stability of @Image 1 and @Image 2 core characters. P1: Attribution and continuity stability of silver straight sword and dark steel sword. P1: Clear front-back spatial relationship on the same imperial road. P1: Continuous character forward direction, enemy attack direction, and camera axis. P2: Specific faces and complex clothing of enemies, Masters, disciples, and ordinary people. If model complexity needs reduction: First reduce supporting character details; Then reduce extra attack moves; Next reduce decorative visual effects. Absolutely cannot sacrifice: Reference image location identity; Core protagonist identity; Action causality; Spatial continuity. [Negative Constraints] Prohibit turning current high-altitude imperial road into circular arena. Prohibit changing to ordinary courtyard. Prohibit changing to wide plaza. Prohibit adding another cloud bridge. Prohibit adding independent mountain gate. Prohibit adding floating island. Prohibit adding combat platform. Prohibit deleting left/right huge waterfalls. Prohibit deleting left/right large palaces. Prohibit deleting left huge cantilevered wooden structure. Prohibit deleting underlying dense ancient city. Prohibit deleting distant huge ring structure. Prohibit pulling distant huge ring closer to become ordinary gate tower. Prohibit changing relative positions of distant palaces and mid-ground buildings. Prohibit day suddenly turning into night. Prohibit stormy dark clouds replacing current soft weather. Prohibit widening imperial road for action. Prohibit changing imperial road width after cuts. Prohibit environment actively participating in plot. Prohibit sudden broken bridge. Prohibit buildings collapsing on their own. Prohibit mist actively obscuring enemies. Prohibit waterfall suddenly changing attack. Prohibit wind suddenly changing sword path. Prohibit characters teleporting without trajectory. Prohibit two protagonists swapping positions out of nowhere. Prohibit random large-area sword qi. Prohibit energy waves colliding. Prohibit light pollution. Prohibit enemies lining up to offer attacks. Prohibit enemies being passive for long periods. Prohibit long-duration weapon shoving. Prohibit characters stopping to wait after one move. Prohibit meaningless rotations. Prohibit meaningless Poses. Prohibit slow motion. Prohibit bullet time. Prohibit hit-stop. Prohibit severe Motion Blur obscuring characters and weapons. Prohibit frantic camera shaking. Prohibit continuous facial close-ups instead of real action. Prohibit arm, finger, and weapon clipping through models during action. Prohibit protagonist weapon duplication. Prohibit character face swapping. Prohibit random costume changes. Prohibit background sudden drift. Prohibit subtitles. blurry, bad quality, low quality, low resolution, noisy, jpeg artifacts, watermark, text, error; deformed, mutated, bad anatomy, poorly drawn hands, bad composition, out of frame, disfigured; inconsistent character, changing clothes, face morphing, background shift, glitching cuts, disappearing props

@Soran
Seedance 2.0 Fake Duel Trap Action Prompt
Seedance 2.0

Seedance 2.0 Fake Duel Trap Action Prompt

Cinematic photorealistic texture, pure ancient Chinese Xianxia high-tension swordsmanship action film. Completely break from previous patterns: Switch weapon for senior sister to counter Breakthrough all way Dual complementary blind spots Core becomes: Senior and junior sisters appear to be in genuinely dangerous duel, actually using it to force lurking assassins to reveal themselves. Three-Layer Narrative Goals Layer 1 Hook: Make audience believe they're really fighting Layer 2 Twist: Reveal they've been controlling space via mutual sword momentum Ending Hook: Leave suspense that second batch of enemies hasn't appeared yet General Action Principle Actions must be smooth, but never soft. Smoothness Defined as: Previous action naturally creates next Movement direction continuously extends Clear causality between camera, body, sword path Power Sense Defined as: Sudden start Violent contact Force deflection Body imbalance Inertia continuation Abrupt stop Character & Weapon Lock Only strictly lock @image 1 and @image 2 core characters and exclusive weapons. @image 1 | Sword Immortal Senior Sister Same @image 1 Senior Sister always maintains: Same adult East Asian female face 25–30 age appearance Black long hair half-tied White jade hairpin Tall slender proportions White embroidered silk Hanfu Semi-transparent wide sleeves Silver waist sash Jade pendant White cloth boots Unique silver straight sword @image 2 | Junior Sister Same @image 2 Junior Sister always maintains: Same adult East Asian female face 20–25 age appearance Braided black hair Petite proportions Blue-green linen Hanfu Dark belt Wooden hairpin Black cloth shoes Unique dark steel sword Other Characters Assassins, master, disciples, passersby are functional only, no strict face/clothe lock like protagonists. Round Scene Control | Highest Priority Uploaded background clearly shows complete, highly recognizable location. Enter HARD LOCATION ANCHOR mode. Reference image is actual story location, not visual inspiration. Must Maintain Original Spatial Elements Huge foreground stone platform Continuous stone railings at edge Large-scale low-fog depth beyond railings Mid-ground dense ancient city rooftops Central hall Distant high-position huge palace complex Strong distance hierarchy between city and far palace Cool gray-blue sky and low fog Warm light from far palace Macro scale: tiny characters, huge city/palace Key Hard Constraints Distant highest palace must always remain: Very far away Very huge visual scale. Forbidden pulling far palace close to behind characters as nearby gate during mid-shots. Venue Limitation Entire 15s fight strictly occurs on: Huge stone platform explicitly present in reference And directly connected areas Forbidden generating: Floating stone bridges Cloud bridges Independent gates Islands New cliffs New palace entrances New stairs New combat platforms Any large building changing location identity Spatial Continuity Requirement After every cut, these relations stable: Platform Railings City layers Central buildings Far palace Skyline Actions/cameras adapt to platform. Never change platform shape for text-described actions. Background State Background lives naturally: Large low fog moves slowly between city layers High clouds change naturally Far palace warm light affected by air/fog Hair/silk hems move with platform wind Air depth, reflections, few distant figures micro-move Only on real: Stepping Weapon collision Fast clothing pass Allow local feedback: Minor stone dust Sparks Hem displacement Strictly Forbidden Fog suddenly hiding enemies Railings breaking Palaces changing themselves Background helping any side complete twist Segment Structure 0–5s | Fake Duel: Trick Audience 0.0–1.0s Use 24mm fixed wide shot. Must keep: Huge stone platform Full far palace/city depth Audience knows same location from reference. Same white-robed senior and blue-robed junior sisters face off meters apart. Safe area in distance has: Few disciples Ordinary spectators Same elderly master But they are background only. Dialogue Junior sister whispers: "Will they really bite?" Senior sister replies: "Trick them first." Last word falls, both burst simultaneously without warning. Camera enters ~35mm moving mid-shot from fixed wide. First Round Fake Duel Senior sister's first sword fast enough to look like hitting junior Junior grazes outside sword edge until last moment Then low counter with dark steel sword Senior rotates to avoid Silver and dark steel swords have first very brief, hard real metal collision Key Requirements Neither poses Reverse into next move immediately after collision White wide sleeves sweep fast past camera, forming first barely noticeable natural hidden cut. Effect Required Make audience doubt: Are they acting or really fighting? 5–10s | Layer 1 Twist: Real Enemies Appear Keep: Identical platform City Far palace scale Sword ownership Use 35–40mm lateral tracking, fight develops horizontally/diagonally on foreground platform, no new locations. Continuous Offense/Defense Sisters complete high-speed but spatially clear sequence: Senior thrusts Junior deflects Junior immediately counter-slips along side exposed by senior Senior ducks under sword High-speed cross, swapping original positions Action Rules All moves chain naturally. Previous strike creates next. No resetting stance after one move. First Assassin Revealed Just as swords cross <0.5s, functional assassin mixed in distant crowd breaks out, attacking from senior's blind spot. Key Requirements Never pause fake duel. Senior notices danger only via junior's brief eye change. Junior continues swinging as if attacking senior. Senior ducks under junior's sword at last moment. Junior's sword sweeps past shoulder, violently knocking away assassin's weapon coming from behind. This second must make audience realize: Duel was bait. Second Assassin Revealed Almost no breath. Second assassin rushes junior from opposite. Senior uses rotational inertia from cross, cuts past junior's shoulder, one brief silver sword collision alters second assassin's path. Result Fake duel naturally converts to real four-way fight during motion. Strictly Forbidden Anyone stopping to explain Assassins queuing Master silently observing from distance 10–15s | Layer 2 Twist: No Holds Barred Between Them Two assassins change strategy upon exposure. Accelerate from two directions, trying to truly separate women. Use slightly wider moving shot. Show complete positional relationship of four on huge platform, background still shows ancient city/far palace. Dual Cross Swap Sisters don't retreat outward. Charge toward each other at high speed. Shoulder lines graze closely at full speed, instantly swapping front/back. Cross must be smooth, seamless. At graze moment: Junior takes assassin attacking senior's blind spot Senior takes assassin charging at junior No eye contact throughout. One assassin's weapon sweeps camera frame violently, forming clearest natural weapon-obscured hard cut. Cut to new reverse axis. Protagonists fully swapped. Final Break Moves Each performs one extremely short, direct reverse counter. Strictly Forbidden Huge sword qi Pretty spins Slow motion Results: One assassin's weapon path altered by junior, body slides outward due to own inertia Other's attack axis altered by senior's silver sword, forced past optimal range Both assassins alive, just lost this round's chance. Sound Cutoff Battle sound narrows suddenly. Only: Four people's breathing Slight vibration of two protagonists' swords

@Soran

Some prompts are collected from creators on X. Copyright belongs to the original authors.