Saltar al contenido
Atlas de IA

Veo

Genera clips de vídeo en 1080p con planos coherentes

Google DeepMind Modelo Cerrado
entradaTextoImagenVídeo

El texto completo se presenta en inglés; el título y el resumen están traducidos.

QUÉ ES

Veo is a text-to-video model Google DeepMind announced in May 2024. It accepts text or image input, generates 1080p video longer than a minute, and supports several cinematic styles and camera controls. Veo is also used in product settings such as YouTube’s short-form tools. Its weights are not open.

Por qué merece la pena recordarlo

It put high resolution, longer duration and controllable camera work into a single video model and fed it directly into Google’s product line, making it a major entry in the 2024 text-to-video race.

Especificaciones clave

Resolution
1080p
Duration
Over 60 seconds (first disclosure)
Input
Text, image
Open weights
No

Capacidades

Conceptos relacionados

Productos similares