# Multimodal Diffusion

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.

This model combines large language models with video diffusion technology, supporting text-to-video generation and allowing control over video content through bounding box conditional input.

AltDiffusion-m9 is a multilingual text-to-image generation model based on the Stable Diffusion framework, supporting 9 languages and powered by the AltCLIP-m9 multilingual CLIP model.