Genera videos a partir de indicaciones de texto
Transforma imágenes estáticas en videos dinámicos
Generación de video multimodal (texto, imagen, video y audio)
Genera imágenes a partir de texto
Transforma y edita imágenes con IA
Un conjunto seleccionado de clips de nuestra biblioteca de demostración. Haga clic en cualquier tarjeta para comenzar a generar con una vibra similar.
Una barbería de toda la vida del barrio está a punto de cerrar. Fuera ha anochecido y la calle se tiñe de azul; dentro, una cálida luz amarilla ilumina fotografías antiguas, un viejo diploma de barbero y retratos descoloridos de clientes. El barbero y su cliente se tratan con la confianza de dos vecinos que se conocen desde hace años, con interpretaciones naturales y contenidas. … [Extracto; se han omitido unos 1250 caracteres]
Un cortometraje cinematográfico de época china de 30 segundos, inspirado en la atmósfera de «La noche de los faroles», en formato horizontal y ambientado durante una noche de la Fiesta de los Faroles en Lin’an, bajo la dinastía Song del Sur. La arquitectura y el vestuario deben ser fieles al periodo: calles de piedra mojada, edificios de madera superpuestos, aleros sobrios y restaurantes y casas de té adornados con faroles palaciegos de seda, faroles vidriados y luminarias con formas de peces y dragones. … [Extracto; se han omitido unos 1200 caracteres]
[Edición de vídeo] Cambia el fondo por un viñedo francés. Sustituye los vasos de café para llevar que llevan ambas personas por copas de vino. Viste a la mujer con un vestido cruzado francés de flores y añade un bolso pequeño de tirante fino. Mantén todo lo demás sin cambios.
[Edición de audio] Elimina la música de fondo de este vídeo y añade una voz en off que encaje con las imágenes.
[Generación con referencias] Monta todo el vídeo al ritmo de la música y aplica una textura granulada de cinta VHS. Usa el Audio 1 como banda sonora completa y sincroniza los labios de todas las protagonistas con la canción. Comienza con un primerísimo plano del ojo de la mujer de pelo corto de la Imagen 1 justo cuando lo abre. Corta a un plano general de una azotea donde las cuatro mujeres cantan, bailan y cambian de formación. Llegan cuatro helicópteros e iluminan la azotea con focos; las gotas de lluvia quedan suspendidas en el aire. Rodea la torre con una toma FPV, acércate a las cuatro mujeres y funde a negro. … [Extracto; se han omitido unos 280 caracteres]
Usa el vídeo de referencia del modelo 3D sin texturas como única fuente para el movimiento de cámara, el ritmo de los planos, los cambios de encuadre, las trayectorias de los personajes y su puesta en escena. Combina las imágenes de referencia de los fotogramas clave de cada etapa para crear una animación 3D cinematográfica de 30 segundos, con una atmósfera de cuento cálida y onírica y una mirada llena de asombro infantil. Mantén la apariencia de cada personaje fiel a los fotogramas clave de su etapa, pero deja que sus emociones faciales evolucionen con la escena. … [Extracto; se han omitido unos 1000 caracteres]
Conserva a la mujer y la escalera cubierta de musgo del metraje con croma, y sustituye el fondo verde por un entorno de cuento imaginativo que encaje con la escalera. Árboles centenarios forman una bóveda natural, gruesas enredaderas descienden desde lo alto y el suelo está cubierto de musgo suave, helechos y pequeñas flores silvestres. Añade columnas de piedra semienterradas, arcos derruidos, setas luminosas y puntos de luz flotantes para evocar una entrada mágica olvidada por el tiempo. … [Extracto; se han omitido unos 650 caracteres]
Un monólogo cinematográfico de 14 segundos en un teatro de caja negra. Una actriz española ocupa el centro de un escenario minimalista, con una vieja silla de madera, un cañón de seguimiento y el patio de butacas a oscuras. La cámara avanza lentamente hasta un primerísimo plano. Ella contiene las lágrimas en silencio: le tiemblan los labios, traga saliva, le tiembla el mentón y su mirada pasa de la determinación al dolor. Una risa quebrada da paso a una lágrima; después se endereza, lista para hablar. La interpretación debe ser sincera, delicada, contenida y demoledora, sin gritos ni melodrama. … [Extracto; se han omitido unos 980 caracteres]
A premium, highly cinematic 30-second 3D motion-graphics sequence in a refined steampunk and retro-miniature style, built around continuous, fluid orbiting and push-through camera moves. [0–10s]: Begin with an extreme close-up of an antique brass clock face that miraculously unfolds into interlocking rings of rotating gears and volumetric mist. The camera dives through the machinery as a mechanical ornithopter spirals upward from a miniature canyon formed by stacks of weathered books. [10–20s]: Track forward along the ornithopter’s flight path and pass seamlessly through an ornate brass zoetrope spinning at high speed, where the moving silhouettes of mechanical horses race inside. The light figures leap from the drum and the scene instantly becomes a brass levitating cable car gliding along glowing copper rails through a forest of mechanical gears, bathed in cinematic golden-hour light. [20–30s]: The camera glides gracefully downward to reveal an intricate wind-up wooden sailing ship beneath the car, cutting through rolling waves made of deep-blue glass. The end of the sea transforms seamlessly into a vast glowing moon. Silhouetted explorers carrying swaying lanterns struggle along a crystal-veined ridge beneath a star-filled sky. The camera spirals smoothly backward through ethereal clouds and returns to the monumental ticking brass clock face. In the final second, reveal the logo using @Image1 as reference. Technical specifications: hyper-real mechanical textures, rich brass and gold tones, cinematic shallow depth of field, smooth and continuous seamless transitions, and an epic fantasy-adventure atmosphere.
Create one uninterrupted take. The camera smoothly follows a person in a black coat, based on @Image1, moving from left to right through six connected rooms with distinct color palettes and moods. Every room shares the same architecture—white walls, a light herringbone wood floor, French double floor-to-ceiling windows, and white sheer curtains, based on @Image2—while the view outside and the atmosphere inside change completely. The protagonist walks at a constant pace and passes through each open doorway. 0–5s: The first room is a comic-book fight. The protagonist enters and fights the character from @Image3, who is defeated. 5–10s: The second room is warm and rendered in felt. Outside is the sunflower field from @Image4; soft orange light fills the room as a painter paints the sunflowers from @Image5. The protagonist also turns into felt upon entering. 10–15s: The third room represents sadness in black-and-white comic stop motion. Rain falls outside; cold gray light fills the room. A lone person sits in the center of the empty floor, head lowered and knees held close, beside a phone showing an unanswered call. When the protagonist enters, the lights switch off and immediately back on: the room becomes colorful and flowers burst into bloom everywhere. 15–20s: The fourth room represents joy and is completely submerged, based on @Image6. As the protagonist swims in, they become transparent, surrounded by beautiful coral and schools of fish. 20–25s: The fifth room represents surprise. Fireworks fill the night sky outside, based on @Image7, casting shifting colors across the room. A crowd gathers around the protagonist and pulls them into the celebration. 25–30s: Finally, the protagonist enters an empty white room, stands in the center, and snaps their fingers with a synchronized snapping sound. The image cuts to black and “seedance” appears in the center, based on @Image8. The entire piece should feel cinematic and resemble a luxury fashion campaign. Lighting must be driven entirely by each exterior scene to create strong emotional contrast. No other on-screen text.
Create a 30-second educational short tracing the evolution of football across three thousand years. The same ball remains the visual thread throughout the film, continually rolling, traveling, and transforming as it links civilizations and historical eras from antiquity to the present. Keep the pace tight and the imagery premium, blending historical-documentary storytelling with artful transitions around the central idea: “One ball, three thousand years.” The voice-over should be concise and powerful. Opening: an ancient ball slowly emerges from darkness, its surface marked by time, then rolls into a cuju scene in China during the Warring States period. Shift into the ink-wash style of @Image1. In an ancient courtyard, people in period dress play cuju with elegant movements as the ball bounces lightly at their feet. Voice-over: “The story of football began with cuju.” The ball continues forward and the scene transitions naturally into an ancient Greek ball game. Use the classical oil-painting style of @Image2, clearly showing stone columns and a public square. People in Greek robes kick the ball in a weighty, historical composition. Voice-over: “The Greeks also loved ball games.” The ball then rolls into medieval Europe while the oil-painting style continues. A village, muddy ground, and ordinary people chasing the ball create a lively, rugged scene, suggesting how folk football kept the tradition alive. Voice-over: “In Europe, folk games carried the tradition forward.” The ball is kicked away and the image switches to the black-and-white documentary style of @Image3, arriving in England in 1863. Gentlemen, clubs, and a grass pitch gradually appear, marking the formal birth of modern football. For the first time, the ball becomes a standard modern football. Voice-over: “In 1863, modern football took shape.” The film rapidly enters the modern era. The football spins through the air, revealing milestones in succession: floodlights, stadiums, crowds, trophies, and matches from around the world, showing how football grew from a local pastime into a global sport. Ending: the ball rests quietly at the center of a modern pitch as cheers and crowds from across the world gather in the background, creating the feeling that one ball connects the entire planet. Make the final image grand and epic. Voice-over: “Today, football connects the world.”
Create a bright, colorful commercial starring fruit-filled cookies in strawberry, apple, grape, and orange flavors. Use @Image1 for the strawberry variety. Arrange each cookie with its matching fruit in disciplined geometric grids, keeping the frame clean, premium, and rhythmically bold. Open by snapping attention to the fruit with the composition of @Video1 as the music drops on a heavy beat. Cut to orderly rows of the different flavors, then move into close-ups using the motion and camera work of @Video2. At the peak, break one cookie and drop into slow motion as the fruit filling bursts outward, crumbs scatter, and the juicy texture and particle impact are magnified with the force of @Video3. Send the cookies across a horizontal array in a rhythmic arc inspired by @Video4, emphasizing order and product variety, then return quickly to fast-paced editing. End with the English line “One bite of crispness, a heart full of delight,” revealing each phrase in rapid succession with strong typographic motion and a product freeze-frame inspired by @Video5. Resolve on a confident brand image as cookies and fruit radiate outward like @Video6, creating a youthful, energetic, delicious, shareable atmosphere.