Describe subject, a second-by-second action timeline, camera, environment, and audio in one block, with negative constraints, so the shot is controllable instead of a lucky roll.
El prompt
Generate one continuous 8-second cinematic shot. Subject: [SUBJECT]. Action timeline: 0-2s [ACTION], 2-6s [ACTION], 6-8s [ACTION]. Camera: [LENS + MOVEMENT]. Environment: [PLACE + WEATHER]. Audio: [AMBIENCE]. Keep identity, wardrobe, and lighting consistent. No cuts, subtitles, watermarks, or extra limbs.
Reemplaza las variables
[SUBJECT]The main subject.
[LENS + MOVEMENT]e.g. 35mm slow dolly-in.
Qué modelo usar
- Veo 3.1 — Video generation is a Veo capability, not a text-model one.
Entrada de ejemplo
- [SUBJECT] = "a barista finishing a latte". Camera = "slow push-in".
Resultado de ejemplo
Solo publicamos resultados de ejemplo de ejecuciones reales del modelo. Esta plantilla aún no se ha probado formalmente, por lo que no se muestra ningún resultado. Ejecútala tú mismo con la entrada de arriba.
Por qué funciona esta estructura
- A timeline gives the model temporal control instead of one static idea.
- Negative constraints suppress the usual video artefacts.
Fallos comunes y soluciones
Motion is chaotic.
Solución: Simplify to one clear action per time band.
Limitaciones conocidas
- Video output is non-deterministic; expect several tries per usable shot.