La lista de tomas que usamos, palabra por palabra. Cópiala en una herramienta de video IA que acepte fotos de referencia, o sube tu foto aquí y nosotros nos encargamos.
Las tomas
Cinco tomas, diez segundos
Cada toma sigue un momento de la tendencia, con los tiempos ajustados para terminar con la celebración.
00:00Dedos a la cámara, vaso en la otra mano
00:02Mano en el cuello de la ropa, mentón arriba, cantando cada palabra
00:04Gira y señala a sus amigos
00:06Los amigos se acercan y la animan
00:08Ríe y vuelve a señalarte mientras todos celebran
Copia el prompt
Dos versiones
Adjunta tu foto como imagen de referencia, pega el prompt y elige 10 segundos de duración.
Para una persona
A vertical 9:16 party clip, exactly 10 seconds, photoreal live action in full colour, handheld phone camera close to the lead in the middle of a packed crowd. No text, no subtitles, no logos, no watermarks.
Setting: a dim private dining room at night, ornate crystal chandeliers glowing gold on the ceiling, picture frames outlined in green neon on the walls, long tables with white cloths, warm amber light.
The lead is the person from your reference photo, standing in the centre of the frame: their face, hair, skin tone, build and the exact clothes they wear in the photo, sharp and recognisable in every shot. They hold a silver metal cup (a cup, not a can).
The lead is surrounded by a tight crew of eight to ten friends in streetwear and caps, packed shoulder to shoulder on both sides and behind, all hyped: dancing, raising silver cups, pointing at the lead, laughing and cheering. Every friend is a generic extra with their own face and nobody resembles a famous person.
The lead raps along the whole time: mouth moving in time with the beat, full of swagger, playing to the lens.
0-2s: close-up, the lead points finger guns at the camera, cup in the other hand, friends bouncing behind.
2-4s: rests a hand on their collar, chin up, eyes half closed, mouthing every word.
4-5.5s: turns to the friends at their side and points at them.
5.5-7.5s: the friends crowd in around the lead, pointing at them and hyping them up, a hand swings past the lens.
7.5-10s: the friends fill the frame around the lead, the lead covers their face laughing, then waves at the camera with the cup while everyone around throws their hands up and cheers.
Sound: an original hip-hop beat with a rap vocal that matches the lead’s lips, the crowd cheering. Not any real or recognisable song.
Para una mascota
A vertical 9:16 party clip, exactly 10 seconds, photoreal live action in full colour, handheld phone camera close to the lead in the middle of a packed crowd. No text, no subtitles, no logos, no watermarks.
Setting: a dim private dining room at night, ornate crystal chandeliers glowing gold on the ceiling, picture frames outlined in green neon on the walls, long tables with white cloths, warm amber light.
The lead is the animal from your reference photo, sitting up in the centre of the frame: its breed, size, coat colour and markings exactly as in the photo, sharp and recognisable in every shot. It wears a small black bow tie.
The lead is surrounded by a tight crew of eight to ten friends in streetwear and caps, packed shoulder to shoulder on both sides and behind, all hyped: dancing, pointing at the lead, laughing and cheering. Every friend is a generic extra with their own face and nobody resembles a famous person.
The lead bobs its head to the beat the whole time, full of swagger, playing to the lens.
0-2s: close-up, the lead lifts one front paw toward the camera, friends bouncing behind.
2-4s: chin up, eyes half closed, bobbing to the beat.
4-5.5s: turns its head to the friends at its side.
5.5-7.5s: the friends crowd in around the lead, pointing at it and hyping it up, a hand swings past the lens.
7.5-10s: the friends fill the frame around the lead, it shakes its head and ears with a flourish, then looks back at the camera while everyone throws their hands up and cheers.
Sound: an original hip-hop beat, the crowd cheering. Not any real or recognisable song.
Consejos
Cómo conseguir un buen resultado
01Usa una foto clara: un rostro mirando a la cámara, con buena luz. El modelo copia lo que ve.
02Mantén el orden y los tiempos de las tomas. Los modelos siguen mejor una lista cronometrada que una descripción general.
03Conserva la indicación sobre los extras. Evita que copien tu rostro o se parezcan a alguien famoso.
04Pide una voz de rap que coincida con los labios y luego agrega Burning Bridges al resultado, o elige el audio oficial al publicar.
¿Con qué herramientas funciona el prompt de Burning Bridges?+–
Con cualquiera que genere video a partir de una imagen de referencia y un prompt. Pega el texto, adjunta tu foto y elige 10 segundos si la herramienta lo permite. Las que solo aceptan texto no pueden conservar tu rostro.
¿Por qué el prompt divide las tomas por tiempos?+–
Los modelos siguen mejor una lista de tomas cronometradas que una descripción general. Cada toma es un momento de la tendencia, para que el video pase por los cinco en orden.
¿El prompt agrega la canción?+–
No. Pide un ritmo original con una voz de rap que siga los labios. En TryBurningBridges agregamos Burning Bridges al video terminado; en otra herramienta, añádela al editar o publicar.
¿Necesito el prompt para usar TryBurningBridges?+–
No. Sube una foto en el inicio y nosotros escribimos y ejecutamos el prompt.