MMDIT

Software / App

A diffusion model where the input is guided by text, not directly reusable as is for image-to-text evaluation tasks.

Mentioned in 1 video

Videos Mentioning MMDIT

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 7 - Evaluation

Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 7 - Evaluation

Stanford Online

A diffusion model where the input is guided by text, not directly reusable as is for image-to-text evaluation tasks.