Sujeto preciso
¿Quién o qué es el sujeto principal?
Aprende a escribir mejores prompts de Seedance 2.0 para videos cinematográficos, anuncios de producto, UGC, anime, microdramas y videos musicales.
Usa fórmulas de prompts, líneas de tiempo, materiales de referencia y ejemplos prácticos para obtener resultados de video con IA más controlados.
Un buen prompt de Seedance 2.0 debe explicar con claridad quién aparece en el video, qué sucede, cómo se mueve la cámara, qué estilo seguir y qué evitar. En la generación de video, el sujeto y la acción son las partes más importantes. Otros detalles como iluminación, escenario, movimiento de cámara, estilo y restricciones se pueden añadir según tus necesidades.
Prompt original
A man walking in a market.
Prompt optimizado
A young man walking through a lively outdoor street market at golden hour. He holds a small bouquet of flowers and looks surprised when he notices someone off-camera. The camera starts with a close-up of the bouquet, then slowly pulls back to reveal the crowd. Warm sunlight, shallow depth of field, natural motion, stable face, clean hand details, no text, no watermark.
Resultado del prompt optimizado
Un prompt sólido de Seedance 2.0 empieza con un sujeto y una acción claros. Estos dos elementos son obligatorios. También se recomienda incluir otros detalles, como escenario, iluminación, movimiento de cámara, estilo visual, calidad de imagen y restricciones, para que el resultado sea más controlado y coherente.
¿Quién o qué es el sujeto principal?
¿Qué hace el sujeto? ¿Qué cambia con el tiempo?
¿Dónde transcurre la escena? ¿Qué detalles de fondo se incluyen?
¿Qué hora del día, estilo de iluminación, tono de color y atmósfera tiene?
¿Cómo debe moverse la cámara o encuadrar al sujeto?
¿Qué estilo visual debe seguir el video?
¿Qué tan nítido, detallado y pulido debe verse el video?
¿Qué debe evitar el modelo?
Fórmula básica del prompt
Sujeto + Acción + Escenario + Iluminación + Movimiento de cámara + Estilo visual + Calidad + Restricciones
Cuando subes materiales de referencia a Seedance 2.0, puedes usar @mentions en tu prompt para indicarle al modelo cómo debe usar cada archivo. Es especialmente útil en flujos de trabajo de Multirreferencia / Omni Reference. En lugar de dejar que el modelo adivine, las @mentions ayudan a Seedance 2.0 a entender qué referencia controla el personaje, la vestimenta, la escena, el movimiento, el audio o el objetivo de edición.

Referencia de personaje
Use @image1 as the main character reference.
Referencia de vestimenta
Use @image2 as the outfit reference.
Referencia de escena
Use @image3 as the background and environment reference.
Referencia de movimiento
Use @video1 as the motion reference.
Referencia de audio
Use @audio1 as the rhythm or voice reference.
Primer y último fotograma
Use @image1 as the first frame and @image2 as the final frame.
Extender video
Use @video1 as the previous clip and continue the same scene.
Editar video
Use @video1 as the original video reference and change the background, outfit, or style.
Explora ejemplos de prompts de Seedance 2.0 para videos cinematográficos, anuncios de producto, clips para redes sociales, UGC, anime, microdramas y videos musicales.
A dramatic horseback chase through a canyon at golden hour. A rider on a black stallion gallops at full speed along a narrow ledge, red dust billowing behind them. The canyon walls tower on both sides, glowing amber in the low sun. The horse leaps over a gap in the trail, all four hooves off the ground, mane and tail streaming. The camera tracks alongside from a parallel ridge. Rocks crumble from the ledge edge. The rider looks back over their shoulder. Hyper-realistic, epic Western cinematography, 8k, thundering hooves echoing off canyon walls.
(0-3s) Macro shot of a luxury perfume bottle among scattered pink peonies, shallow depth of field, petals floating in warm afternoon light, soft ambient music. (3-7s) Camera glides closer, a feminine hand enters frame from the right, fingers gently touch the glass bottle, the sound of silk rustling. (7-12s) Hard cut to slow-motion spray, golden mist diffuses through the air, particles catching rim light against a dark background, the hiss of the atomizer. (12-15s) Seamless pull-out to hero frame, product centered, volumetric lighting, minimal cream background, elegant silence. Hyper-realistic, 8k, fashion commercial cinematography.
A tight medium shot of two eccentric adults in typical, everyday clothing, one in a slightly oversized trench coat, the other in a weathered denim jacket, deep in a heated, animated conversation on a rainy West Village street corner. The one in the trench coat gestures wildly, the words “SOURDOUGH PRETZEL” appearing in pulsating electric blue: “It’s not just a pretzel, Arthur! It’s a sourdough pretzel!” The second guy says ‘Who cares. A pretzel’s a pretzel!’
A realistic young woman sitting casually in a softly lit bedroom during late afternoon. She is holding her phone very close to her face as if recording a private video or voice note. Framing is tight and slightly imperfect. Expression: thoughtful, slightly shy, natural. Minimal makeup, natural skin texture, relaxed clothing. Lighting: warm natural light fading from a window, soft shadows. Environment: simple bedroom, calm and lived-in. Style: ultra-realistic, looks like a real phone recording, slightly grainy, not cinematic.
Create a 10-second UGC-style fashion video. Use the girl in @Image1 as the main character. Keep her face, hairstyle, body shape, and overall vibe consistent throughout. Use @Image2 as the green top reference, and @Image3 as the handbag reference. [0s-2s] The girl faces the camera and holds up the green top from @Image2, showing it naturally with a cheerful expression. Then quickly transitioned to her wearing the green top. [3s-5s] She starts doing her makeup in front of the camera. [6s-7s] She fixes her hair while looking confident and stylish. [8s-10s] She picks up the handbag from @Image3 and presents it like a model. Keep the character, green top, and handbag consistent. Avoid deformation, outfit errors, hand issues, identity drift, and messy background.
Replace the man in black who is dribbling in @video1 with the girl from @image1. Keep the original scene, camera movement, dribbling motion, body posture, and basketball trajectory from @video1. The girl should closely follow the same movement and timing. Keep her face, hairstyle, and outfit consistent with @image1. No background change, no camera change, no body deformation, no hand errors, no ball clipping.
Use @image1 as the main reference image. Keep the character design, outfit, expression, and cute anime livestream style consistent throughout. Create a 15-second Japanese anime-style livestream video in a cozy bakery kitchen. The main character is a lively young female baker and livestream host, wearing the same outfit and headset style as @image1. Use warm lighting, soft pastel colors, and simple livestream UI elements such as a “LIVE” badge, floating hearts, comment bubbles, and product tags. Keep the UI clean and do not block the character. Include smiling, waving, kneading dough, presenting baked bread, natural Japanese lip sync, smooth camera movement, warm cozy lighting, and cute anime style. Avoid character inconsistency, outfit changes, dark lighting, cluttered UI, and oversized text.
[0-3s] Sweet Wedding: Mr. Mango and Miss Banana stand under a floral arch, smile at each other, and exchange rings in a bright warm wedding hall. [3-6s] The Intruder: Miss Strawberry bursts through the doors and shouts, “You can’t marry her! She’s a rotten banana!” [6-9s] The Reveal: Strawberry pulls down Banana’s dress hem, revealing a rotten blackened banana peel. Banana screams, “Wait! Let me explain!” [9-12s] Mango Runs Away: Mango runs toward the exit while Banana cries out. [12-15s] Final Twist: Sprinkler water pours over Mango, the golden paint melts away, and he is revealed as a potato. Cinematic, absurd, dramatic, clear subtitles only for dialogue.
Use the audio from @Video 1 to drive the protagonist in @Image 1 to generate an MV with multiple shots, change the outfit and background, and create an overall light, lively, and sunny atmosphere. Lip-sync strictly: "Waking up to golden light. Coffee warm and feeling right."
Incluso una buena idea puede dar resultados flojos si el prompt es demasiado vago o los materiales de referencia no están bien explicados.
Al usar Multirreferencia / Omni Reference, las @mentions funcionan como instrucciones para los materiales que subes. Si subes imágenes o videos sin explicar su función, es posible que Seedance 2.0 no sepa cómo usarlos.
Prompt débil
Use this cup to make a video.
Prompt mejorado
Use @image1 as the main subject. Keep its vintage floral pattern and warm ivory color unchanged.
Prompt débil
Subir una imagen y un video sin usar @mentions.
Prompt mejorado
Use @image1 as the main subject and @video1 only as the motion reference. Follow the wrist movement and stirring rhythm from @video1.
Seedance 2.0 funciona mejor cuando las emociones se muestran mediante acciones visibles, expresiones y lenguaje corporal.
Prompt débil
She is sad.
Prompt mejorado
Her lower eyelids are red and swollen, tears gather in her eyes but do not fall.
Prompt débil
He is angry.
Prompt mejorado
He throws the phone onto the sofa, paces back and forth, breathes heavily, and clenches his jaw.
Prompt débil
He is nervous.
Prompt mejorado
His fingers keep rubbing the corner of his shirt, his eyes quickly scan the room, and his breathing becomes shallow and fast.
Regla clave: las emociones deben verse, no solo mencionarse.
Si no describes la cámara, Seedance 2.0 decidirá el plano por su cuenta, lo que puede hacer que el resultado sea más aleatorio.
Prompt débil
A beautiful shot.
Prompt mejorado
Low-angle wide shot with slight lens distortion, blurred foreground, and backlit silhouette.
Prompt débil
Move closer.
Prompt mejorado
Close-up shot focused on the eyes, with clear eyelashes and window reflections in the pupils.
Prompt débil
Sin dirección de cámara.
Prompt mejorado
Medium shot, slow push-in, focus shifts from the character’s face to the object in their hand.
Regla clave: incluye el tamaño del plano, el movimiento de cámara y el punto de enfoque cuando haga falta.
Seedance 2.0 suele funcionar mejor con movimientos fluidos, continuos y naturales. Las acciones muy complejas o rápidas aumentan la probabilidad de deformaciones o resultados inestables.
Prompt débil
Intense fight scene, fast dancing, multiple people jumping and running.
Prompt mejorado
Slow turn, gentle hand movement, hair moving softly in the wind.
Prompt débil
Complex interaction between many people.
Prompt mejorado
Two people stand face to face, make eye contact, and lean forward slightly.
Prompt débil
Fast chase scene.
Prompt mejorado
Slow-motion walking with the coat gently moving in the wind.
Regla clave: busca movimientos fluidos, estables y naturales en lugar de acciones demasiado complejas.
Las restricciones ayudan a reducir problemas habituales del video con IA, como rostros distorsionados, manos inestables, parpadeos o pérdida de identidad.
Prompt débil
Sin restricciones.
Prompt mejorado
Stable face, natural body structure, clean hands, complete fingers, smooth motion, no flickering, no identity drift.
Empieza con un sujeto, una acción, referencias, dirección de cámara y restricciones claras, y crea videos controlados con Seedance 2.0 en SeeGen AI.
Prueba Seedance 2 gratis