Ir para o conteúdo
Atlas de IA

Imagen

Gera imagens fotorrealistas com difusão em cascata e um grande codificador de texto

Google DeepMind Modelo Fechado
entradaTextoImagem

O texto completo é apresentado em inglês; o título e o resumo estão traduzidos.

O QUE É

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 que vale a pena lembrar

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.

Especificações-chave

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

Capacidades

Conceitos relacionados

Produtos semelhantes