Imagen

About

Imagen by Google is a text-to-image diffusion model with an unprecedented degree of photorealism and a deep level of language understanding.

• Transformer-based text encoding for deep language understanding
• Diffusion model architecture for high-fidelity image generation
• Zero-shot generation for novel, unseen prompts
• Photorealistic output with accurate lighting and textures
• Benchmark-leading performance on COCO and similar datasets