Tinta china

Explora prompts de vídeo de Tinta china gratuitos de la biblioteca de prompts de IA de YouMind, agrupados en estilos. Cada prompt está seleccionado de flujos de trabajo creativos reales y listo para copiar, adaptar y reutilizar.

143 promptsDestacados diarios
Seedance 2.0
Ver prompt completo

Task: Dreamina Seedance 2.5 — Omni ReferenceDuration: 30 secondsAspect ratio: 16:9Editorial target: 24fps, F000-F719 [Generation Goal]A high-speed combat battle involving only three characters: @Image1, @Image2, and @Image3. Develop offense and defense over 10 cuts. No weapons; use a combination of rushes, dodges, palm strikes, elbow strikes, kicks, throws, and aerial attacks. Do not fix the expressions of the three characters. Change them to alertness, surprise, irritation, concentration, provocation, exhilaration, and relief in response to the offense and defense. Express specifically through eyes, eyebrows, mouth, gaze, breathing, and head tilt. Return characters to a recognizable form only at moments of stopping, posing, contact, or landing. During high-speed movement, always break down the finished human body and replace it with a small number of liquid brushstrokes, rough watercolor planes, and short afterimages based on each character's color scheme. Do not simply add speed lines or motion blur to a finished figure. The flowing brushstrokes themselves are the character. [Material Roles]@Image1 = Character A. One and the same person. Uses yellow bob hair, cat ears, green eyes, light blue and white clothes, yellow trim, triangular tie decoration, pink backpack, pink boots, light blue tail with a yellow triangular tip as identifying information. @Image2 = Character B. One and the same person. Uses a yellow-green round bob, two leaf-like ears, golden eyes, white puff sleeves, pink bowtie, dark green shorts with suspenders, green boots, a long yellow-green tuft continuing from the back of the head with a round tip as identifying information. @Image3 = Character C. One and the same person. Uses vivid blue long hair and ponytail, two white horns, pointed ears, golden eyes, star-shaped earrings, dark red Japanese-style clothing, black skirt, black belt and back ribbon, black knee-highs, and red geta as identifying information. Do not treat three-view diagrams as clones. Do not swap the faces, hair, costumes, color schemes, ears, horns, tails, back hair, or decorations of the three. However, the expressions in the reference images are not fixed and should change according to the battle situation. Do not use white backgrounds or explanatory text. Do not generate weapons. Do not use the backpack, tail, back hair, horns, or geta as detached weapons. [Environment]A giant festival square based on a white paper surface. A giant vermilion pillar and watercolor stalls on the left, a sequence of vermilion torii gates in the center back, a red lantern shelf on the right, and light blue cubes and firework-like brushstrokes in the sky. Draw the background with translucent watercolors, broken ink lines, pencil composition lines, and wide white margins. Do not enclose the floor, pillars, torii, stalls, or lanterns with closed outlines. The background lines also tremble slightly, changing in density and position, but the amount of variation is weaker than that of the characters. Maintain the background layout in all cuts. Do not include combatants, crowds, or additional characters other than the three. [Unstable Line Rule]Draw the entire video with 'continuously generated lines and watercolors.' Do not clean up each frame from the previous one; redraw each frame as a new rough sketch. Do not create a single outline surrounding the person. Do not enclose the head, shoulders, arms, torso, or legs with continuous lines; always leave 30-60% of the body's outer circumference as white gaps in the paper. Recognize the character's form intermittently through short, broken pencil lines, irregular watercolor boundaries, dry brush marks, eraser marks, and doubled redraw lines. Do not maintain the same line in the same position for more than 3 frames. Lines change in position, thickness, density, length, pressure, and curvature every frame. They break in the middle, split into two, and parts disappear. Do not use a single uniform line width for the whole body. Do not keep line density constant. Irregularly alternate frames with extremely few lines, frames with dense redraw lines, and frames where most of the outer circumference disappears. Do not create a finished outer circumference for the face either. Do not draw both eyes, nose, mouth, jaw, and cheeks clearly at the same time. Leave only the minimum lines to read the expression, such as the outer side of one eye disappearing, the mouth cutting off midway, eyebrows becoming double, or cheek lines melting into watercolor. Do not fit the watercolor accurately inside the lines. Create bleeding, protrusion, white unpainted areas, uneven shading, and misregistration. [Line and Color Delay]Body movement takes the lead, pencil lines follow about 1-2 frames late, and watercolor color planes follow about another 1-2 frames late. Late lines and color planes do not completely overlap the body and remain as short afterimages torn in the direction of movement. Afterimages are not copies of the finished person but brushstrokes and color planes that indicate only the direction of the arms, legs, hair, tail, and costume. Even when stopped, do not return the lines to a clean-up state. The person's face, clothing, and posture become legible, but the gaps in the outer circumference, double lines, watercolor bleeding, and misregistration are maintained. [Mandatory Motion Deformation]Draw only about 60% of the human body for weak actions. Draw only about 30-40% for medium-speed actions. Draw only about 10-20% for high-speed actions. At maximum speed, represent the character with only 3-5 brushstrokes and 2-3 rough color planes. Character A high-speed action = yellow, light blue, white, and pink brushstroke group. Character B high-speed action = yellow-green, dark green, white, and a small amount of pink brushstroke group. Character C high-speed action = blue, dark red, black, and a small amount of golden brushstroke group. During high-speed action, do not connect the head, torso, arms, and legs with a correct human structure. Turn arms into long liquid brushstrokes, kicking legs into extremely elongated color planes, and rotating torsos into crushed arcs, triangles, or twisted watercolor surfaces. Temporarily disconnect limbs during jumps. Compress the torso in the direction of travel during sudden stops. Shift the hips and shoulders in different directions during turns. [Expression Direction]Character A: Starts with alertness, changes to a proud smile upon successful evasion, surprise when an attack is diverted, playful provocation during a melee, strong concentration in the late stages, and finally a satisfied, breathless smile. Character B: Starts with cautious observation, sharp concentration when interrupting, momentary surprise when an attack is dodged, a competitive smile during aerial attacks, a desperate expression in the final stages, and finally a soft, relieved expression. Character C: Starts with calm confidence, smiles slightly after dodging the first attack, furrows eyebrows during a pincer attack, sharp concentration while counterattacking, an exhilarated smile during the three-way melee, and finally a provocative one-sided smile. Do not finish the face during high-speed action. Indicate emotions with a single stroke of the eye, the tilt of an eyebrow, a short line of the mouth, or the direction of head brushstrokes. Make expressions legible only at moments when speed drops. [Cut 1 | 0.0-2.5s | F000-F059 | Triangular Confrontation]Initial state: Fixed wide. Character A is in the left foreground, Character B is in the right foreground, and Character C is in the center back. They form a triangle with each other in sight. Primary event: Show the appearance and positions of the three from F000-F023. A narrows eyes and is wary of C, B looks back and forth between A and C and breathes cautiously. C raises their chin slightly and shows composure with a one-sided smirk. From F024-F041, A lowers their hips, B opens half a step to the side, and C slides their geta to lower their center of gravity. From F042-F059, the three step out simultaneously. End state: The travel directions of the three converge in the center. The expressions and body circumferences are legible, but the lines are not closed and are redrawn every frame. [Cut 2 | 2.5-5.0s | F060-F119 | A vs C First Strike]Initial state: Low angle near the ground. A on the left, C in the center, B in the right back. Primary event: From F060-F075, A breaks down into yellow, light blue, and pink brushstrokes and rushes low from left to right. From F076-F087, A connects a leg sweep to a spinning kick. C breaks down into blue, dark red, and black brushstrokes, rotates, and evades the kick by a hair's breadth. Only just before contact from F088-F095 do A's eyes open wide and C smiles slightly. Do not draw the whole face, show only through fragments of eyes, eyebrows, and mouth. From F096-F119, A passes by C and slides to the right, leaving fragments of a surprised face. End state: A is in the right foreground, C is in the center, B is in the right back. C's composure increases, and A refocuses their expression. [Cut 3 | 5.0-8.0s | F120-F191 | B's Interruption]Initial state: Medium wide horizontal position. C in the center, A on the right, B in the right back. Primary event: From F120-F137, B lowers their eyebrows, breaks down into yellow-green and dark green brushstrokes, and enters from right to left. From F138-F153, B performs a spinning leg sweep passing under both of their feet. From F154-F167, A jumps vertically, and their legs and tail stretch into watercolor bands. The moment the evasion is successful, the corners of A's eyes droop and a smirk forms provocatively. C sinks low, folding their body to dodge B's kick. From F168-F179, B's eyes open wide for a moment, showing surprise at being dodged. From F180-F191, B furrows their eyebrows and concentrates on the next attack while sliding left. End state: B lands on the left, C in the center, and A in the center back. [Cut 4 | 8.0-11.0s | F192-F263 | C's Continuous Counterattack]Initial state: Low diagonal composition. B on the left, C in the center, A in the back. Primary event: From F192-F207, C's smile disappears and eyebrows drop sharply. C breaks down into 3-5 blue, dark red, and black brushstrokes and accelerates rapidly from left to right. From F208-F223, C performs a palm strike on B, an elbow strike on A, and a spinning back kick in one continuous motion. During the attack, C does not return to a finished body. Only a single golden stroke for the eye and a concentrated eyebrow line appear within the brushstroke group. From F224-F239, B evades backwards as a green arc, and A escapes sideways by splitting into short yellow and pink lines. From F240-F251, the arms and legs of the three cross for just a moment. A opens their mouth briefly in surprise, and B grits their teeth. From F252-F263, C passes to the right side and shows an exhilarated one-sided smile. End state: C is on the right, B on the left, A in the center back. All three are standing. [Cut 5 | 11.0-14.5s | F264-F347 | A and B Pincer Attack]Initial state: High diagonal overhead view. C on the right, A in the center back, B on the left. Primary event: From F264-F283, A and B exchange a short look. A shows a confident smile, B shows a focused face with lowered eyebrows. The two run towards C simultaneously; A performs a low flying kick and B performs a spinning kick. From F284-F303, C furrows their eyebrows and changes their body into thin blue, red, and black lines to slip through the gap between the two kicks. From F304-F323, A and B open their eyes wide just before colliding with each other, tuck their legs, and change direction in mid-air. From F324-F347, the three move apart in a circle. C gives a small smile for breaking the pincer attack, A furrows their eyebrows regretfully, and B exhales and gauges the next distance. End state: B on the left, C in the center, A on the right. [Cut 6 | 14.5-18.0s | F348-F431 | Sequence of Grabs and Throws]Initial state: Circling tracking shot. B on the left, C in the center, A on the right. Primary event: From F348-F367, A smiles provocatively and tries to jump onto C's shoulder. C changes to a focused, almost expressionless face, catches A's wrist to change their direction of motion, and throws them low. Make only the contact point briefly legible. From F368-F387, A becomes a group of yellow and pink brushstrokes and falls while rotating. Surprised eyes and an open mouth appear for a moment, then immediately break down into lines. From F388-F407, B throws a heel kick at C while passing in mid-air. B narrows their eyes and shows a competitive smile. From F408-F419, C catches it with their forearm and flows B's leg line outward. C's eyebrows rise slightly, showing surprise at the unexpected strength. From F420-F431, A regains posture just above the floor, clenches their mouth regretfully, and performs a three-point landing. End state: A is in the right foreground, B is in the left foreground, and C is in the center back. [Cut 7 | 18.0-21.5s | F432-F515 | 3D Offense and Defense Using the Background]Initial state: Wide shot showing the left vermilion pillar, center torii, and right lantern shelf simultaneously. Primary event: From F432-F451, B runs to the left pillar. Their expression changes to an exhilarated smile, and they step on the pillar once to bounce off diagonally. From F452-F471, A jumps to the right stall roof, kicks the roof, and reverses to the center. A shakes off the regret and narrows their eyes joyfully. From F472-F491, C anticipates the trajectories of the two and stays out of both attack lines with a low rotation while keeping a sharp gaze. During the high-speed section, the three become brushstroke groups with their own independent color schemes. From F492-F503, only the lanterns and stall cloths shake from the wind pressure. From F504-F515, the three land in the center and open their eyes wide at each other's unexpected movements. Immediately after, all three laugh. End state: The three form a narrow triangle in the central square. Exhilaration for the battle appears in the three. [Cut 8 | 21.5-25.0s | F516-F599 | Six-Beat Close-Quarters Melee]Initial state: Waist-high close-up wide. The whole bodies and feet of the three are visible. Primary event: From F516-F527, A starts from a joyful smile and enters a right roundhouse kick. From F528-F539, C lowers their eyebrows and flows it outward with their forearm. From F540-F551, B clenches their mouth and delivers a low leg sweep. From F552-F563, C opens their eyes in surprise, tucks their knees, and jumps. From F564-F575, A changes to focused eyes and drops a heel from mid-air. From F576-F587, B grits their teeth, pushes A's leg away, and changes the attack direction toward C. From F588-F599, C shows an exhilarated smile and slips behind the two. Replace characters with brushstroke groups for each high-speed action. Recombine only for 1-2 frames for attack blocks and expression changes. End state: A is on the left, B on the right, C in the center back. All three are out of breath, but their fighting spirit has grown stronger. [Cut 9 | 25.0-28.0s | F600-F671 | Simultaneous Three-Way Rush]Initial state: Frontal wide. A on the left, B on the right, C in the center back. Primary event: From F600-F611, the three sink down simultaneously. A removes their smile and looks at the landing point. B furrows their eyebrows strongly and holds their breath. C raises only one side of their mouth, provoking the two. From F612-F635, A (yellow, light blue, pink), B (yellow-green, dark green, white), and C (blue, dark red, black) become minimal brushstroke groups and rush toward the center. Do not show finished faces, hands, torsos, or costumes. From F636-F647, the three brushstroke groups cross in the center. Eyes, eyebrows, and mouths appear briefly as independent short lines, showing the concentration of the three. From F648-F659, opaque watercolors, ink splatters, and dry brush strokes that scrape the paper scatter radially. From F660-F671, the three pass through in the directions they crossed. End state: A, B, and C cross the center and decelerate while facing away from each other. [Cut 10 | 28.0-30.0s | F672-F719 | Recombination and Conclusion]Initial state: Fixed wide. The three are sliding in different directions from the center. Primary event: From F672-F687, brushstrokes shorten and characters return in the order of posture, hair, costume, and watercolor. The body's outer circumference does not close. From F688-F703, A stops on the right, B on the left, and C in the center foreground. A smiles satisfiedly while out of breath. B closes their eyes once, exhales, and smiles softly. C looks at the two over their shoulder and shows a provocative one-sided smile. From F704-F711, the three turn around simultaneously. From F712-F719, they change their expressions back to focused faces and take low combat stances. End state: No conclusion reached. All three can be identified as the same characters from the reference images by their color scheme, hair, and costume. However, line gaps, double lines, watercolor bleeding, and misregistration remain after stopping. [Visual Treatment]Hand-drawn 2D animation on bright white paper. Use ink, pencil, watercolor, dry brush, white unpainted areas, eraser marks, and redraw lines. Do not create a line that goes all the way around the person's outer circumference. Do not enclose the face, hair, clothes, arms, or legs as closed shapes. Lines within the screen change in thickness, density, length, position, pressure, curvature, and gap rate every frame. Do not correct high-speed action body collapse, line gaps, facial omissions, or color plane delays as generation defects. Do not return to smooth vector lines, uniform line width, closed outlines, symmetrical faces, fixed expressions, accurate coloring, 3D-like human interpolation, or processing that only adds effect lines to a finished character. [Audio]High-tempo percussion-based BGM. Character A has light boot sounds, B has soft landing sounds, C has hard geta sounds. Clothing wind noise, short hitting sounds, floor scraping sounds, sounds of kicking pillars and stalls, the sound of lanterns swaying, and breathing. No dialogue. [Maintain Consistency]Only three characters. Do not generate three-view diagrams as clones. Do not swap the color schemes, faces, hair, costumes, ears, horns, tails, back hair, backpacks, or shoes of the three. Do not fix expressions. Change eyes, eyebrows, mouth, gaze, and breathing in response to each attack, dodge, failure, success, surprise, and exhilaration. Do not stabilize lines. Do not make line width constant. Do not maintain the same line in the same position. Do not close the body's outer circumference. Do not fit watercolor accurately inside the lines. Always break down characters during high-speed action. Do not let them run, jump, or attack while maintaining a finished human body. Move the brushstroke groups themselves as the characters. Make them identifiable as the same person at the moment of stopping and contact, but do not return to a clean-up outline. Do not generate weapons. Do not generate additional people, clones, or human-shaped afterimages. Maintain background layout, character movement directions, and triangular positional relationships. Frame numbers are editorial goals; prioritize event order, expression changes, and the end state of each cut. pure video, no subtitles, no dialogue, no watermark.

Generar vídeo
Seedance 2.0
Ver prompt completo

A structured 15-second multi-shot action sequence with explicit hard cuts. [SHOT 1: 0s-4s] Low-angle shot on an empty lantern-lit street. The dark warlord slams his staff into the ground; a single colossal roaring shadowy black ink dragon erupts behind him into the night sky. [HARD CUT TO SHOT 2: 4s-8s] Medium close-up shot of the white-robed female swordswoman with determined eyes, pointing her silver sword forward as a glowing blue magic spell circle expands under her feet. [HARD CUT TO SHOT 3: 8s-15s] Over-the-shoulder view from directly behind the female swordswoman. In front of her at the end of the street, the warlord and his ink dragon stand facing her. She thrusts her sword forward, releasing hundreds of glowing blue spirit swords that shoot FORWARD AWAY FROM CAMERA straight into the ink dragon, shattering it in a massive explosion of light and flying red lanterns.

Generar vídeo
Seedance 2.5
Ver prompt completo

Left side woman: Cold Tide barrier master, blue-white long robe, water-element mage. Uses cold water, barriers, water walls, water rings, water-flow traction, and ink-wash tidal waves in combat. She must maintain distance and must never allow the man to stably close in. Right side man: Crimson-black long robe red-blade swordsman, solid red large blade, black cloak, crimson fire-ink, black ink waves, golden shattered ink. Fighting style is strong assault, breaking formations, charging in, horizontal slashes, aerial heavy chops. He must constantly attempt to close the distance and break through the water walls. Generate a 15-second 16:9 landscape 720P high-definition 2D ink-wash wuxia combat video. Overall high-energy 2D ink-wash combat aesthetic: fierce, fast, explosive actions, strong ink-follow, large-area splash-ink explosions, characters high-definition and clear. No 3D, no live-action, no CG feel, no sketch style, no static illustration. Combat arena: rainy aftermath of shattered water-courtyard ruins, large areas of shallow water covering a green-stone plaza, surrounded by broken bridges, residual pillars, collapsed water pavilions, broken tiles, stone steps, distant ink clouds. The ground must have large water surfaces; character movement produces water splashes, ripples, reflections, and ink-wash ripples. During combat the water surface is split by blade energy, water walls are shattered, residual pillars are broken by water waves, green stone is cleaved by the red blade, broken tiles are swept up by water flow and shockwaves. Core combat relationship: The woman is a mid-to-long-range water mage who actively controls the field and suppresses. The man is a close-range red-blade fighter who must constantly charge to break distance. The woman always uses the water surface, barriers, water walls, and spatial displacement to keep 3–8 meters distance. The man constantly uses ground-hugging dashes, diagonal charges, aerial downward chops, and spinning horizontal slashes to forcibly close the gap. Every time the man is about to get close, the woman must use water walls, water rings, surging waves, mirror-position swaps, sliding-water retreats, or barrier rebounds to interrupt. She cannot stand still to cast; she must cast while sliding, spinning, retreating, or leaping on water. Absolute real-time high-speed combat. No slow motion, no variable frame rates, no speed ramps, no static charging, no one-move-one-stop, no idle time after collision. From the first frame to the last frame continuously. At least 3 effective offense-defense exchanges per second: water-wall blocking, red-blade breaking walls, water-wave counter-push, charge dodging, barrier rebound, pursuit avoidance happening continuously. Ink-wash special effects must be extremely strong. All of the woman’s actions carry cyan-blue ink, water splashes, cold white flying white, water-ripple barriers, transparent water walls, vortex water rings. All of the man’s actions carry crimson fire-ink, large red blade arcs, black cloak ink waves, golden shattered ink. Water and fire-ink must contrast sharply: cyan-blue tides suppress red-black blade waves; when the red blade splits a water wall, red-blue colliding splash-ink explodes. Ordinary exchanges occupy one-third of the frame with ink effects, heavy strikes occupy half the frame, final explosion is full-screen ink-wash detonation. 0–3 s: Low camera close to the water surface rapid tracking. Woman slides backward on water, sleeves roll out three cyan-blue water rings, semi-transparent water wall rises from the surface. Man charges violently from the distance hugging the ground, red blade dragging and splitting the water surface, crimson fire-ink and water splashes exploding simultaneously. Man horizontal-slashes the first water wall; woman sideways slides on water to change position; second water wall rolls up from his side and deflects his slash momentum. Camera stays low on the water surface chasing, water splashes hitting the lens. 3–6 s: Medium-close rapid cuts. Man consecutive three-stage strong assault: diagonal charge horizontal slash, spinning upward lift, aerial downward chop. Woman retreats while casting without pause: water sleeves flick to form an arc water shield, foot vortex shifts her body sideways three meters, both hands form seals to raise two water walls for pincer attack. Red blade shatters the water shield, shattered water turns into cyan-blue splash-ink rain; woman uses the water wave to push herself sliding to the side of the broken bridge, maintaining distance. 6–9 s: Large-scale spatial displacement. Man stomps and shatters green stone, leaps across the water channel, black cloak trailing red-black ink waves, red blade chopping down from above. Woman does not hard-block; she leaps on water, water column underfoot lifts her into a side flip, circular water-ripple barrier appears behind her. Blade energy chops into the barrier, water surface explodes into a ring-shaped giant wave, man is forced half a step back by water pressure. Woman lands on top of a residual pillar on the opposite side and immediately flings three water blades from different angles to seal the man’s pursuit path. 9–12 s: Pursuit and counter-suppression. Man forcibly breaks through the water blades, ground-hugging rapid charge, red blade continuously splitting the water surface forming three crimson blade scars. Woman high-speed retreats along the water surface, both sleeves trailing long cyan-blue ink tails, spins and summons a row of water walls pushing forward like a tidal wave. Man uses the large blade to continuously break the walls; his body is repeatedly shocked back, slides, then forcibly charges forward again; water surface underfoot is stomped and explodes, red-blue splash-ink continuously detonating. Camera rapidly switches between weapon close-ups, water-wall shattering close-ups, and full-body chase shots; cuts never interrupt the action. 12–15 s: Final high-intensity explosion. Man finally charges into close range, aerial heavy chop, red blade carrying a crimson fire-ink giant wave pressing down. Woman instantly slides back on water and spins; large area of water underfoot rises into a ring-shaped water tornado, three layers of transparent water walls stack continuously. Man shatters the first layer with one chop, spins horizontal slash to tear open the second layer, lands dragging the blade upward to crash into the third layer. Woman pushes both hands forward; the water tornado contracts into a huge cyan-blue ink-wash shockwave. Man’s red blade hard-blocks; red-black blade wave and cyan-blue tide collide head-on, full-screen splash-ink, water flowers, flying white, shattered ink, golden shattered ink explode. After the explosion the man is blasted sliding backward several meters, blade tip plowing the water surface; woman slides back on water to a distance, water rings still rotating behind her; both remain in residual combat momentum, not a static pose. Camera requirements: Tsui Hark-style rapid camera work combined with high-energy 2D ink-wash combat. 70% medium-close and water-surface tracking shots, 20% full-body medium shots showing large displacements, a small amount of long shots showing the water-courtyard ruins and large water surface. Must include low water-surface camera, blade-splitting water-wall close-ups, water-splash explosion shots, woman’s water-sliding side-move tracking, man’s charging whip-pan, overhead water-ring barrier shots, low-angle aerial downward chop shots, final frontal explosion collision. Cuts must continue the same movement direction—no breaking of moves, no stuttering. Character force feedback must be strong. Every time the man shatters a water wall he must be counter-shocked by water pressure: shoulders lean back, feet slide, cloak explodes open. Every time the woman is forced clos

Generar vídeo
Seedance 2.5
Ver prompt completo

A continuous 15-second cinematic action shot. An extraordinarily beautiful ancient Chinese female swordswoman with a high ponytail and long legs, wearing a stylish white and ice-blue flowing silk Hanfu with dynamic side slits, sprints with athletic agility across dark gray tiled roofs in ancient Chang'an at sunset. Three black-masked assassins closely chase her, roof tiles shattering underfoot. Suddenly, she leaps into mid-air, drawing her glowing silver sword in slow motion as white silk dress flutters softly. One assassin jumps to strike her; their weapons collide violently in mid-air with bright orange sparks and shockwaves. She smoothly parries the strike, executes a mid-air backflip, and lands lightly on a lower roof in a graceful low crouch, eyes focused on enemies.

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

[Generation Mode] Seedance 2.0 [Video Specifications] Strict total duration 15 seconds, 16:9 aspect ratio. [Overall Style] Cinematic realistic texture, pure ancient Chinese Xianxia aesthetics, blending classical stealth suspense, restrained deadpan comedy, moonlit ink blue and lantern warm gold tones, symmetrical architectural composition, fine film grain, and directional spatial sound. Through narrative misdirection, a seemingly dangerous sect forbidden area mission is reversed into an embarrassing mundane matter. [Character Locking] Character A | Sword Immortal Sister: Use @Image 1 to strictly lock Character A. 25–30 year old East Asian female, oval face, fair natural skin, dark apricot eyes, black long hair half-tied with white jade hairpin, tall and slender, wearing white embroidered silk Hanfu, translucent layered wide sleeves, silver belt, jade pendant, and white cloth boots. Character B | Junior Sister: Use @Image 2 to strictly lock Character B. 20–25 year old East Asian female, round expressive face, black braided hair, petite build, wearing green linen Hanfu, dark cloth belt, wooden hairpin, and black cloth shoes, holding a sealed bamboo scroll. [Scene Setting] Outside the sect's Sutra Pavilion at midnight. Wet stone floor, dark tiled roof, carved wooden pillars, paper windows, two stone lions, slowly drifting incense smoke, and three bronze alarm bells hanging on red strings establish a stable spatial relationship. [Core Props] The same bamboo scroll, the same three bronze alarm bells, and the same old wooden scroll return box. [Shot 1 | 0-5s | Low-angle wide tracking shot] Outside the Sutra Pavilion, the two characters advance cautiously through deep shadows. The senior sister observes the closed pavilion while the junior sister clutches the scroll; accompanied by tense wooden percussion and night sounds. [Shot 2 | 5-10s | Medium cowboy shot tracking] The senior sister raises two fingers to instantly freeze the swinging bronze bells, whispering: 'Remember, do not alert the Sutra Elder.' They pass under the silent bells towards the return box. [Shot 3 | 10-15s | Close-up reveal to extreme close-up] Junior sister places the scroll in the box. An invisible elder's voice says: 'Sword Mastery for Beginners, three days overdue.' Junior sister asks: 'Sister, are you still a beginner?' Sister replies: 'Reviewing the old to know the new.' One bell rings on its own. Extreme close-up of the sister's dignified smile stiffening. [Technical Requirements] Strict 15s duration, 16:9 ratio, native Mandarin lip-sync, stable characters, realistic physics for silk/hair/smoke/bells, no subtitles, only two visible characters. [Negative Prompts] 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

Generar vídeo
gemini-omni
Ver prompt completo

A pure white background fills the frame. Thick black ink drops fall in slow motion, splashing outward like blooming flowers. The camera is perfectly static, focusing on the fluid motion. As more ink spreads, the shapes subtly transform into mountains, rivers, and trees. Color seeps in—deep blues and greens—until the ink fully becomes a miniature landscape painting. The final second holds on the completed world, perfectly still. Style: abstract beauty | fluid motion | artistic transformation Camera: static macro → slow reveal Length: 10 seconds Lighting: soft studio light, high clarity

Generar vídeo
Seedance 2.5
Ver prompt completo

[STYLE + CAMERA + ATMOSPHERE] Opulent Qing-dynasty palace drama television look, shot on ARRI Alexa with warm amber candlelit tones mixed with cool jade accents, refined ceremonial atmosphere. Slow circling crane shots combined with graceful tracking movements, elegant restrained pacing throughout. [CHARACTERS] A young elegant woman with an elaborate traditional updo adorned with pearl and jade ornaments, dressed in a flowing pale silk gown with wide draping sleeves, moving with graceful controlled fluidity. Seated nobility and officials in formal Qing-dynasty attire watching intently from surrounding cushioned seats. [LOCATION] Grand imperial palace hall with red lacquered pillars, intricate carved wooden screens, warm lantern light glowing against dark polished floors, silk banners hanging from high ceilings. [TIMELINE] 0-6s: [Wide crane shot descending into the hall] The woman stands center stage in the flowing pale gown, arms raised gracefully as soft instrumental music implied through her poised stillness, seated guests watching with anticipation. 6-12s: [Slow circling tracking shot around her] She begins moving through a series of fluid controlled poses, wide sleeves trailing through the air like wings, jade ornaments catching the lantern light. 12-18s: [Low tracking shot following her sleeve movements] Her long sleeves sweep low and rise again in perfect synchronization with her turning steps, silk fabric rippling elegantly with each motion. 18-24s: [Medium shot capturing a dramatic spin] She executes a graceful spinning turn, sleeves flaring outward in a wide circular arc, expression serene yet intensely focused, seated guests leaning forward in admiration. 24-30s: [Wide pull-back crane shot] She settles into a final elegant pose, sleeves draping gently to the floor, the entire hall falling into a moment of hushed appreciation before quiet approving murmurs ripple through the seated guests. [STYLE & QUALITY BOOSTERS] Exact period production texture of premium Qing-dynasty court drama, coherent silk fabric and sleeve physics, stable character continuity, warm lantern-lit color grading, no modern digital sharpness, refined ceremonial grace throughout.

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

[Mode] Seedance 2.0 Fast. 15s, 16:9. [Style] Cinematic realism mixed with ancient Chinese mural aesthetics. Symmetrical staging with contrasts between warm lamp light and cold shadows. [Scene] Ancient mountain temple mural hall with stone floors, wooden pillars, and a massive unfinished dragon mural on the wall. [Characters] Character A: Senior sword fairy (@Image 1), 25-30, white Hanfu. Character B: Junior sister (@Image 2), 20-25, green Hanfu. [Shot 1 (0-5s)] They work on the dragon mural together. The senior draws an elegant horn; the junior draws a crooked, over-branched horn. [Shot 2 (5-10s)] They dot the eyes. Thunder rolls, and the ink dragon detaches from the wall, becoming a 3D spirit while keeping its one elegant and one crooked horn. [Shot 3 (10-15s)] The dragon lowers its head and asks in Mandarin: 'Who drew these two horns?' Both women point at each other simultaneously. Freeze frame on their expressions as the dragon sighs. [Technical] 15s, native Mandarin audio, no subtitles, stable character faces and clothing.

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

[Generation Mode] Seedance 2.0 Fast [Video Specifications] Strictly generate a 15-second video, 16:9 aspect ratio, with three clear shots. [Overall Style] Poetic Xianxia visual illusion comedy, realistic cinematic high-definition texture. Uses classical Chinese negative space composition, restrained deadpan performance, soft morning light, low-saturation jade green and ivory white tones, and fine film grain. Borrows from Buster Keaton-style spatial illusions, revealing the truth through controlled camera rotation rather than relying on failed magic for laughs. The entire film is set in a pure ancient Chinese world with no modern elements. [Character Locking] Use @Image 1 and @Image 2 to strictly lock character identity, face, hairstyle, body proportions, clothing, shoes, and accessories. Character ID A | Senior Sister Sword Immortal An East Asian female aged 25-30, oval face, natural fair skin tone, dark almond eyes, black long hair half-tied and fixed with a white jade hairpin, tall and slender build. Wearing white embroidered silk Hanfu with semi-transparent layered wide sleeves, silver waist seal, jade pendant, and white cloth boots. Character ID B | Junior Sister An East Asian female aged 20-25, rounded and agile face, black hair in braids, petite build. Wearing bluish-green linen Hanfu, dark belt, wooden hairpin, and black cloth shoes. [Shot 1 | 0-5s | Wide Shot or Long Shot] The frame is intentionally rotated 90 degrees clockwise, making a steep mountain wall appear horizontally as the ground. Character ID A: Senior Sister, appearing in full from head to toe, seems to be walking upright and calmly along the vertical cliff with hands behind her back, while her hair and sleeves naturally hang toward the vast abyss in the frame. Character ID B: Junior Sister seems to be hanging onto an ancient pine tree below. [Shot 2 | 5-10s | Medium Shot or Cowboy Shot] The same Junior Sister in green linen Hanfu looks up and asks: "Senior Sister, is this 'Treading the Wall to Heaven'?" The same Senior Sister in white silk Hanfu continues walking calmly and replies indifferently: "If the heart is upright, heaven and earth will naturally be level." The background remains the same mountain wall, pine tree, floating mist, stone platform, and distant roofed water pavilion; the incorrect vertical orientation must be maintained without altering character anatomy. [Shot 3 | 10-15s | Close-up or Extreme Close-up] The camera smoothly rotates 90 degrees counter-clockwise to restore the true horizontal line, revealing that the Senior Sister is simply walking on a flat stone platform next to a low wall, while the Junior Sister is just casually leaning against the pine tree. Junior Sister says expressionlessly: "Senior Sister, the world is level, but the camera is crooked." Extreme Close-up: The Senior Sister's hard-maintained dignified smile instantly freezes, one eyebrow twitches slightly, and she then replies as if nothing happened: "This is to test your eyesight." Ends with a dry pluck of a guqin string and the sound of a pine cone falling onto the stone slab. [Technical Requirements] Strict total duration of 15 seconds, 16:9 aspect ratio, three clear shots, original Mandarin dialogue, stable character faces and clothing, continuous scene geometry. Physics of mist, silk fabric, hair, pine trees, and gravity must be realistic and consistent. Do not generate on-screen subtitles. Only two visible characters should appear throughout. [Negative Prompts] 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

Generar vídeo
Seedance 2.0
Ver prompt completo

A young woman in a modern traditional Chinese outfit performs a powerful Wushu-inspired calligraphy dance, wielding a giant dragon-engraved brush through a misty ink-wash mountain landscape. She moves barefoot through pools of black ink, creating dramatic splashes, swirling ink ribbons, and elegant circular strokes. Martial arts poses blend with graceful brush movements as golden dragon details shine on the brush, while the ink gradually transforms into a massive mythical Chinese dragon rising into the sky. Cinematic, ultra-detailed, slow-motion, monochrome shanshui aesthetic with dramatic lighting and fluid ink dynamics.

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

[Generation Mode]\n\nSeedance 2.0 Fast\n\n[Video Specifications]\n\nStrictly generate 15 seconds of video, 16:9 aspect ratio, three clean and clear shots.\n\n[Overall Style]\n\nPoetic Xianxia identity reversal comedy, realistic cinematic high-definition texture, using grand classical Chinese landscape composition, restrained stoic performances, warm sunrise penetrating cold mountain mist, low-saturation ivory white, cinnabar red, and jade green tones, and fine film grain. The reversal is not about the senior sister looking foolish due to a magic mishap, but about the seemingly clumsy junior sister revealing truly astonishing power quietly. The entire film is set in a pure ancient Chinese world without any modern elements.\n\n[Characters]\n\nCharacter ID A | Senior Swordswoman Sister\n\nSenior sister @Image 1, East Asian female aged 25–30, oval face, fair complexion, dark almond eyes, black long hair partially tied up with a white jade hairpin, tall and slender figure, wearing a white embroidered silk Hanfu with translucent wide sleeves, a silver waistband, jade pendant, and white cloth boots.\n\nCharacter ID B | Junior Sister\n\nJunior sister @Image 2, East Asian female aged 20–25, round and lively face, black hair in braids, petite figure, wearing a turquoise linen Hanfu, dark belt, wooden hairpin, and black cloth shoes.\n\n[Core Scene and Props]\n\nA stone platform for sect talisman assessment above the sea of clouds, featuring grey stone flooring, carved stone railings, old pine trees, bronze incense burners, fluttering prayer ribbons, a low wooden desk, an ink slab, a calligraphy brush, a yellow talisman paper with crooked lines, distant tiled-roof halls, and a massive mountain peak blocking the morning sun.\n\n[Shot 1 | 0-5s | Low-angle wide shot with slow tracking]\n\nThe stone platform above the sea of clouds establishes a clear and stable spatial relationship. The senior sister examines the crooked talisman and calmly remarks: 'The lines are scattered; it cannot form a great spell.'\n\n[Shot 2 | 5-10s | Medium cowboy shot]\n\nThe junior sister in the turquoise Hanfu calmly sticks the same crooked yellow talisman onto the stone railing and whispers: 'Then just move it a step.'\n\nA low rumble echoes from the massive mountain in the distance as it shifts several yards horizontally along the ground. The previously blocked sunrise is instantly revealed; cliff dust falls, birds scatter in alarm, and prayer ribbons snap taut as golden morning light pours onto the platform.\n\nThe senior sister in white embroidered silk Hanfu slowly looks up, speechless for the first time.\n\n[Shot 3 | 10-15s | Close-up to extreme close-up]\n\nThe camera shifts focus to reveal the sunlight perfectly illuminating a rear courtyard where several sets of ancient quilts and robes are being dried.\n\nThe junior sister smiles with satisfaction and says: 'Senior sister, the quilts in the backyard finally got some sun.'\n\nExtreme close-up: The senior sister silently folds and puts away the bamboo scroll of criticism, one eyebrow twitching slightly before she forces herself to remain calm and says: 'This talisman... wins on practicality.'\n\nEnds with the sound of a calligraphy brush dropping onto the ink slab.\n\n[Technical Requirements]\n\nStrict total duration of 15 seconds, 16:9 aspect ratio, three clean and clear shots, native Mandarin audio, stable character faces and clothing, realistic physics for talisman paper, silk fabric, sunlight, dust, and mountain movement, no subtitles, and only two visible characters throughout.\n\n[Negative Prompts]\n\nblurry, 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

Generar vídeo
Seedance 2.5
Ver prompt completo

7 seconds, 9:16, one shot to the end, sweet ancient style OOTD short video. The 7-second audio plays in full, accompanying the character's dance. Strictly use the adult female in @CharacterReferenceImageCharacterSettingImage as the only character: use the right-side face close-up as the character's look reference, and the left-side front view and middle back view as the reference for clothing, hairstyle, and back structure. Completely maintain her small oval face, delicate facial features, red flower mark on the forehead, deep brownish-black high classical bun, light gold flower and leaf hairpin, pearl tassels, and hanging bead chains on both sides; completely maintain the light champagne white and pale peach pink ancient style dance clothes, embroidered tube top inner layer, light apricot transparent long-sleeved gauze clothing, light gold waist seal, metal chain ornaments, and multi-layered draping long skirt. Changing the face, changing clothes, changing hairstyles, or adding/removing accessories is prohibited throughout the process. Only refer to the action trajectory, posture, rhythm, shot variation, and composition of the @VideoCharacter, and do not inherit the face, hairstyle, clothing, color, or material of the original video character. Pure white shadowless studio, high camera angle slightly looking down, ultra-wide angle slightly perspective, the camera is basically fixed, and the character always maintains a clear full body or large half body in the shot. 0–1 second, the character walks in lightly from the right side of the screen holding a small amount of the skirt, and the long skirt and thin gauze sleeves naturally swing; 1–2 seconds, the character approaches the camera, the upper body leans forward slightly, eyes look up at the camera, with a sweet and restrained expression; 2–3 seconds, both hands lightly rest on the waist, forming a natural waist-cinching posture, and the head tilts slightly playfully; 3–4 seconds, elegantly turns half a circle sideways, showing the back of the clothes, the bun, and the waist seal structure, then looks back at the camera; 4–5 seconds, turns back to the front with a light smile, both arms naturally stretch to both sides of the body, and the light gauze sleeves slowly drop; 5–6 seconds, hands are lightly placed behind the back, first lowering the head to adjust the posture, then slightly tilting the head to look at the camera; 6–7 seconds, lightly resting on the waist again, the character first turns their head to look at the side front at a 90° angle to the camera, the gaze first focuses on somewhere far away outside the lens, and then turns to the lens, ending with a sweet, confident, and dignified ancient style pose. The movements are naturally coherent, light and restrained, and do not perform large-scale dance moves. The skirt, thin gauze sleeves, bead chain tassels, and hair strands near the ears produce slight real inertia with the movements, avoiding exaggerated flying. Bright soft light, clear and high brightness, soft light champagne tone, high-end texture combining ancient costume film and television advertisements with Korean fashion short films, fast-paced, no dialogue, with light and ethereal national style pop music. The character identity, facial features, hairstyle, clothing patterns, and accessory positions are stable throughout, the face is clear and stable, real skin texture, 4K quality, clear details. Do not use the blank face covering in the left-side front view as the character's face; the character's looks must come from the right-side face close-up; do not inherit the face, hairstyle, or clothing of the original character in the video; do not add new characters, do not change clothes, do not jump cut, do not move or shake the camera significantly, do not rotate quickly, do not shake sleeves violently, do not cover the face with the skirt, do not deform limbs, repeat arms, extra fingers, hand sticking, clipping, sudden changes in clothing, disappearing accessories, changes in hairstyle, or changes in background.

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

[Overall Style] Master-level cinematic realistic style combined with exquisite ancient costume fashion catalog aesthetics, realistic real person, strictly referring to uploaded images. The scene is a light gray-white seamless cyclorama studio, the background and ground naturally merge into one. Uses soft and transparent front-top diffused light, preserving delicate skin texture and light semi-transparent fabric texture. Camera is a 9:16 vertical screen fixed high-angle front shot, tilted down about 30–35 degrees. [Main Character Setting] A 20–24 year old East Asian young woman, tall and well-proportioned, cool and gentle temperament, oval face, cool white skin tone, large almond eyes, straight eyebrows, small nose tip, soft pink lips, black ancient long hair, semi-tied hairstyle, silver flower hairpin headpiece, pearl drooping earrings. Initial outfit is the same woman wearing a white outer large-sleeved robe, blue embroidered cross-collar inner layer, light blue long skirt, silver waist accessory with tassels, and the skirt expands toward the bottom of the frame. [Fixed Sticker Setting] Four complete character stickers are fixed and suspended around the screen throughout, which are precise cutouts of real body contours with clear white dotted outlines, not rectangular thumbnails: Top left is white top + light blue pleated long skirt + blue belt; Top right is white inner layer + blue sleeveless vest-style long skirt with silver embroidery; Left middle is light blue inner skirt + deep blue cross-collar layering + white outer long-sleeved robe; Bottom left is light gray-purple outer robe + off-white inner layer + deep blue embroidered lower skirt. [Scene Segment 1 | 0.00–2.95s] The same woman in the initial outfit gently approaches the camera from the bottom right of the frame, body leaning slightly forward, wide sleeves and skirt swaying naturally, looking up at the high-angle lens; A white hand-shaped mouse pointer clicks the top-left sticker, a duplicate character cutout flies from the top left diagonally to the center and enlarges rapidly. During the enlargement, the white dotted outline stays close to the character's contour. At about 1.25s, it perfectly overlaps with the head, shoulders, waist, and movement. The central woman seamlessly changes into the top-left white-top light-blue-skirt outfit while continuing her approach; Then she naturally rests one hand in front of her waist, the other hand slightly lifts the sleeve, with a faint smile, slowly turns to the left, gradually revealing the side and semi-back view, hair and headpiece swaying gently. [Scene Segment 2 | 2.95–5.40s] The white mouse clicks the top-right sticker, the duplicate cutout flies from the top right into the center. At about 2.95s, the woman switches to the white inner + blue sleeveless vest long skirt. Background stays the same light gray-white studio, the four original stickers remain fixed; The woman continues turning in the same direction, then turns back to the front, skirt and hair naturally fall back, body briefly dips, arms slightly expand to the sides to let the sleeves open, then the mouse clicks the left-middle sticker. The duplicate flies to the center, and at about 4.40s, the woman seamlessly changes into the light blue inner + deep blue layering + white outer robe outfit, face, hair, and body proportions remaining identical. [Scene Segment 3 | 5.40–8.00s] The woman keeps hands in front, bows head and sways shoulders, tilting head naturally left and right, then looks at the camera, then turns her gaze to the bottom-left sticker character; The mouse clicks the bottom-left sticker, the cutout flies from bottom left to top right into the center and enlarges. At about 6.55s, it overlaps perfectly with the center character, completing the fourth outfit change into the light gray-purple robe + deep blue embroidered skirt; Then she rests one hand on her lapel, the other hand naturally hanging down, looks to the side, then back to the front, tilts head naturally, looks directly up at the high-angle lens, ending in an elegant, cool, and strong ancient style posture, with sleeves and skirt gently falling naturally at the end. [Change Timing] The four outfit change points are strictly at: 1.25s, 2.95s, 4.40s, 6.55s. [Technical Requirements] Fixed camera throughout, no push-pull, no panning, no tilting, no rotation, no zooming; outfit changes must be achieved only by the stickers flying in, enlarging, and overlapping. No separate clothes flying in, character afterimages, double characters, or overlapping clothes; sound only preserves mouse clicks, sticker flying sounds, and clear transition sounds, plus slight fabric friction, no background music. [Negative Prompts] 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

Generar vídeo
Seedance 2.5
Ver prompt completo

[Task] Generate a complete 30-second Chinese ancient style character biography short film. Strictly follow the timeline, multi-modal material mapping, character isolation, and reference audio execution, without freely modifying camera angles or plot. [Reference Binding] - Depth Video: Only controls three core dance segments at approximately 0–5s, 10–18s, and 25–30s. - Multi-view Headshot + Full-body image: Only locks the main dancer.

Generar vídeo
gemini-omni
Ver prompt completo

Camarones en estilo aguada saltando hacia una ciudad futurista: un trozo de papel de arroz se despliega entre rascacielos nocturnos, ocho camarones en tinta blanca y negra saltan desde la superficie del papel, sus cuerpos aún conservan el trazo de pincel 'blanco volador' y los degradados de tinta. Los bigotes de los camarones se transforman en vías urbanas brillantes y las gotas de tinta se convierten en lluvia de neón; la escena presenta un gran contraste de escala, una fuerte profundidad, iluminación cinematográfica y un espectáculo que captura la mirada al instante. Sin texto, sin marcas de agua.

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

[Estilo] Comedia poética de inversión al estilo Xianxia con humor seco, calidad cinematográfica realista de alta definición. Presenta una composición espacial de arquitectura china clásica, actuación contenida, niebla de montaña fría, iluminación de contorno cálida al atardecer, tonos verde jade y blanco marfil de baja saturación, y grano de película fino. La inversión se logra a través de la narración sonora: 'planteamiento - distracción - remate fuera de cámara'. Diseñado específicamente para Seedance 2.0 con bloqueo de imagen de referencia, generación continua de múltiples lentes y audio espacial sincrónico. Solo dos personajes visibles, mundo chino antiguo puro sin elementos modernos. [Personajes] Personaje A: Bloqueado en @Image 1. Hermana inmortal (Jianxian) del este asiático de 25-30 años, rostro ovalado, piel clara, ojos almendrados oscuros, cabello negro largo parcialmente recogido con una horquilla de jade blanco. Alta y esbelta, viste un hanfu de seda blanca bordada con mangas translúcidas en capas, sello de cintura de plata, colgante de jade y botas de tela blanca. Personaje B: Bloqueado en @Image 2. Hermana menor del este asiático de 20-25 años, rostro redondeado y vivaz, cabello negro en trenzas, menuda, viste hanfu de lino verde, cinturón de tela oscura, horquilla de madera y zapatos de tela negra. [Plano 1 | 0-3s | Plano panorámico amplio en ángulo bajo] Una tranquila plataforma de piedra de la secta sobre un mar de nubes. Barandillas de piedra, un antiguo muro de eco, nueve campanas de bronce colgantes, pinos antiguos retorcidos, banderas de oración ondeando y palacios con techos de tejas a lo lejos establecen una relación espacial clara. La hermana mayor vestida de blanco está junto a la hermana menor vestida de verde, mirando a su alrededor con cautela y una expresión de confianza mientras se prepara para compartir un secreto. El viento de la montaña mueve su cabello, mangas, banderas y la niebla. [Plano 2 | 3-6s | Plano medio de dos personas] La hermana mayor levanta dos dedos para formar un pequeño sello manual de transmisión de sonido junto a su boca, susurrando: "Déjame contarte un secreto, el Maestro robó tres trozos de pastel de osmanthus anoche". Una fina onda sonora azul claro vuela con precisión hacia el oído de la hermana menor; ella abre los ojos al instante, cubriéndose la boca para contener la risa. [Plano 3 | 6-10s | Plano medio revelado a primer plano extremo] La onda sonora no se detiene, pasa a la hermana menor y golpea el muro de eco, luego rebota a través de las nueve campanas de bronce, haciendo eco del susurro por todo el valle: "El Maestro robó tres trozos de pastel de osmanthus anoche—". Las campanas vibran en secuencia, los pájaros en el techo del palacio se dispersan. Se escucha una tos desde la dirección del salón principal, seguida por un anciano invisible preguntando con calma: "El cuarto trozo, ¿quién se lo comió?". Ambos personajes se congelan. Primer plano extremo: los dos dedos levantados de la hermana mayor se curvan lentamente, una ceja se contrae mientras mira a la hermana menor; las mejillas de la hermana menor están claramente infladas. Termina con un sonido de deglución muy suave y culpable. [Requisitos técnicos] Duración estricta de 10 segundos, pantalla panorámica 16:9, tres planos claros, diálogo en mandarín nativo, sincronización labial precisa, movimiento de sonido direccional, capas de eco claras, rostros/ropa consistentes, dirección de movimiento coherente, física natural para la niebla, seda, cabello, campanas y ondas sonoras. Sin subtítulos, sin otras personas visibles. [Prompts negativos] borroso, mala calidad, baja calidad, baja resolución, ruidoso, artefactos jpeg, marca de agua, texto, error; deformado, mutado, mala anatomía, manos mal dibujadas, mala composición, fuera de encuadre, desfigurado; personaje inconsistente, cambio de ropa, transformación facial, cambio de fondo, cortes con fallos, accesorios que desaparecen

Generar vídeo
Por @Soran
Seedance 2.0
Ver prompt completo

Wuxia poético × Comedia seca | Las grullas reconocen el arroz, no la cítara [Estilo] Fotorrealismo cinematográfico, realismo de acción real. Una fusión de estética wuxia poética y contenida, comedia de observación inexpresiva, composición clásica china elegante, iluminación suave de atardecer, tonos verde jade y blanco marfil de baja saturación, grano de película fino y coordinación grupal controlada de grullas espirituales. El núcleo del giro: los instintos animales derrotan fácilmente a la majestad inmortal. La primera mitad crea un espectáculo de alto nivel, solemne y etéreo de "música de cítara que atrae grullas", mientras que la segunda mitad utiliza un pequeño accidente cotidiano para un desenlace cómico. Toda la película se desarrolla en un mundo chino antiguo puro, sin elementos modernos. [Enfoque de generación] Optimizado para las capacidades de Seedance 2.0: bloqueo de identidad de imagen de referencia, narrativa continua de múltiples tomas, estabilidad de personajes duales, coordinación grupal de animales y sincronización audiovisual nativa. [Duración] Estrictamente 10 segundos. [Relación de aspecto] Pantalla panorámica 16:9, 24 fps. [Estructura de tomas] Tres tomas limpias y claras. I. Bloqueo de personajes Personaje A | Hermana mayor espada inmortal: Bloqueada mediante @Image 1 (rostro, peinado, proporciones corporales, ropa, zapatos, accesorios). Configuración: mujer de Asia oriental de 25 a 30 años, rostro ovalado, tono de piel natural claro, ojos almendrados oscuros, cabello largo negro medio recogido con una horquilla de jade blanco, alta y esbelta. Ropa: Hanfu de seda bordada blanca, mangas anchas translúcidas en capas, sello de cintura plateado, colgante de jade, botas de tela blanca. Temperamento: Fría, tranquila, digna, segura, esforzándose por mantener la majestad inmortal. Personaje B | Hermana menor: Bloqueada mediante @Image 2. Configuración: mujer de Asia oriental de 20 a 25 años, rostro redondo y vivaz, cabello negro trenzado, complexión pequeña. Ropa: Hanfu de lino cian, cinturón de tela oscura, horquilla de madera, zapatos de tela negra. Accesorio: Sostiene una pequeña cesta de bambú con grano. Temperamento: Natural, sincera, admira a la hermana mayor, calma inexpresiva. II. Bloqueo de animales Grupo de grullas: Estrictamente 3 grullas blancas durante todo el video. Deben mantener plumas blancas, físico esbelto, temperamento espiritual y movimiento natural. Primera mitad: elegante y ordenada. Segunda mitad: instintiva, ansiosa y ruidosa debido al grano. III. Configuración de la escena Una plataforma de piedra en el borde de un acantilado sobre un mar de nubes. Incluye: pino antiguo, barandilla de piedra, pabellón de madera, quemador de incienso de bronce, banderas de oración, suelo de losas, mar de nubes, niebla y una cítara antigua. Relación espacial fija: hermana mayor en la cítara, hermana menor junto al pabellón, grullas dando vueltas y luego aterrizando detrás de la hermana mayor, grano derramándose entre la cítara y la hermana menor. IV. Diseño de tomas - Toma 1 (0–3s): Toma completa con seguimiento horizontal en ángulo bajo. Establece la relación estable entre los personajes, la cítara, las grullas y el pabellón. La hermana mayor toca la cítara mientras 3 grullas vuelan en círculos arriba. Sonido: Cítara, viento, gritos de grullas lejanos, fricción de seda. - Toma 2 (3–6s): Toma lateral media. La hermana mayor termina una frase y dice: "Cuando la cítara suena, cien pájaros rinden homenaje". Las 3 grullas aterrizan con gracia detrás de ella. La hermana menor muestra admiración. Sonido: Final de cítara, alas, diálogo en mandarín con sincronización labial precisa. - Toma 3 (6–10s): Primer plano revelador a primerísimo primer plano. La cesta de la hermana menor se inclina, el grano se derrama. Las 3 grullas abandonan instantáneamente la formación, pasando junto a la hermana mayor para picotear el grano. Una grulla pisa la cítara, creando una nota discordante. La hermana menor dice sin expresión: "Hermana mayor, ellas reconocen el arroz". Primerísimo primer plano de la hermana mayor congelada, ceja temblando, una pluma blanca aterrizando en su horquilla. Sonido: Grano derramándose, pasos de grulla, picoteo, nota discordante, diálogo en mandarín. V. Secuencia de acción (últimos 4s): 1. La cesta se inclina -> 2. El grano se derrama -> 3. Las grullas se sienten atraídas -> 4. Las grullas se apresuran -> 5. La grulla pisa la cítara -> 6. La hermana menor habla -> 7. Corte a primerísimo primer plano -> 8. La hermana mayor se congela/ceja tiembla -> 9. La pluma cae. VI. Requisitos de actuación: La hermana mayor debe ser verdaderamente elegante durante 6s, luego mostrar un colapso silencioso. La hermana menor permanece tranquila y sincera. Las grullas pasan de ser elegantes a instintivas. VII. Física/Continuidad: Movimiento natural para alas, tela y grano. Estrictamente 3 grullas, sin personas adicionales, rasgos de personaje y posiciones de escena estables. VIII. Sonido: Mandarín nativo sincronizado, capas ambientales cinematográficas, sin subtítulos, sin sonidos modernos. IX. Técnico: 10s, 3 tomas, 16:9, 24fps, bloqueo Seedance 2.0. X. Prompts negativos: borroso, mala calidad, baja calidad, baja resolución, ruidoso, artefactos jpeg, marca de agua, texto, subtítulos, leyendas, logotipo, error; deformado, mutado, mala anatomía, manos mal dibujadas, mala composición, fuera de encuadre, desfigurado; personaje inconsistente, cambio de ropa, cambio de peinado, transformación facial, rostro inestable, cambio de fondo, cortes con fallos, accesorios que desaparecen; personas adicionales, cuerpo duplicado, grulla duplicada, más de tres grullas, menos de tres grullas, continuidad rota, sincronización labial incorrecta; objetos modernos, arquitectura moderna, detalles de ropa moderna, sonidos electrónicos, subtítulos generados, movimiento de aves poco realista.

Generar vídeo
Cargando más prompts

Preguntas frecuentes

¿De dónde salen los prompts de YouMind?
YouMind selecciona ejemplos de prompts de IA de gran valor procedentes de comunidades de creadores y flujos creativos públicos. La biblioteca se centra en prompts que merece la pena examinar, reutilizar y adaptar.
¿Cómo se organizan las categorías de prompts de vídeo?
Los prompts de vídeo se agrupan por casos de uso, estilos y temas. Los casos de uso cubren el objetivo de producción, los estilos cubren el lenguaje de movimiento o renderizado y los temas describen la escena o entidad principal.
¿Cómo se asignan los prompts a las categorías?
YouMind usa IA para analizar cada prompt de vídeo, su título, sus metadatos y el resultado generado cuando está disponible, y luego le asigna las categorías más cercanas. El equipo editorial puede afinar las categorías a medida que evoluciona la taxonomía.
¿Qué es YouMind?
YouMind es un espacio de trabajo con IA para convertir investigaciones, ideas y referencias creativas en resultados aprovechables. La biblioteca de prompts es una parte pública de ese flujo de trabajo, pensada para ayudar a los creadores a aprender más rápido de buenos ejemplos.