Google's New Imagen AI Outperforms DALL-E on Text-to-Image Generation Benchmarks

Researchers from Google's Brain Team have announced Imagen, a text-to-image AI model that can generate photorealistic images of a scene given a textual description. Imagen outperforms DALL-E 2 on the COCO benchmark, and unlike many similar models, is pre-trained only on text data.

ai benchmarks dall-e deep learning generation google image image generation imagen ml & data engineering neural networks news text text-to-image