# Unified Architecture

MMaDA is a novel class of multimodal diffusion foundation models, excelling in various domains such as text reasoning, multimodal understanding, and text-to-image generation.

MMaDA is a novel multimodal diffusion foundation model that excels in text reasoning, multimodal understanding, and text-to-image generation.

OmniGen is a unified image generation model supporting multimodal prompts, designed with simplicity, flexibility, and ease of use in mind.