Saltar al contenido
Atlas de IA

Imagen

Genera imágenes fotorrealistas con difusión en cascada y un gran codificador de texto

Google DeepMind Modelo Cerrado
entradaTextoImagen

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

QUÉ ES

Imagen is a text-to-image model Google announced in May 2022. Its key move is to use a frozen large language model (T5-XXL) as the text encoder and to generate with cascaded diffusion: a base image at low resolution is produced first, then a series of super-resolution diffusion models enlarge it step by step. The paper showed that scaling the text encoder improved image–text alignment more than scaling the image generator alone. Imagen did not release its weights and was not offered directly to the public.

Por qué merece la pena recordarlo

It showed that the size of the text encoder is a key lever for text–image alignment and pushed the cascaded-diffusion route to the frontier of photorealistic generation, shaping the design of later models.

Especificaciones clave

Text encoder
Frozen T5-XXL
Generation
Cascaded diffusion (base + super-resolution)
Output resolution
1024×1024
Open weights
No

Capacidades

Conceptos relacionados

Productos similares