Saltar al contenido
Atlas de IA

Stable Video Diffusion

Convierte una imagen fija en un vídeo corto con un modelo de difusión

Stability AI Modelo Pesos abiertos
entradaImagenVídeo

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

QUÉ ES

Stable Video Diffusion (SVD) is an image-to-video model Stability AI released in November 2023 with open weights. It frames image-to-video generation as latent-space diffusion: conditioned on a single still image, it produces a short clip with an adjustable amount of motion. The model generates 14 frames at 576×1024 resolution by default. It shipped as both an image-to-video model and a multi-view model, the latter synthesising views orbiting an object from a single image.

Por qué merece la pena recordarlo

It was one of the few image-to-video models to release open weights, letting “make a short video from one image” run locally or on self-hosted services and advancing open practice in image-to-video.

Especificaciones clave

Resolution
576×1024
Default frames
14 frames
Input
Single image
Open weights
Yes

Capacidades

Conceptos relacionados

Productos similares