Multimodal Diffusion Transformer

Software / App

An architecture coined in the Stable Diffusion 3 paper, relying on joint attention of different modalities for image generation, overcoming limitations of DiT.

Mentioned in 1 video

Videos Mentioning Multimodal Diffusion Transformer

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 5 - Architectures

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 5 - Architectures

Stanford Online

An architecture coined in the Stable Diffusion 3 paper, relying on joint attention of different modalities for image generation, overcoming limitations of DiT.