What MDT is
The model is described as a masked diffusion transformer that improves how diffusion probabilistic models learn relations between object parts in images.
What you can do with it
- Generate high resolution images
- Work on fast learning in image synthesis
- Use MDTv2 to improve FID scores in image synthesis
Model notes
- Training masks some tokens in latent space
- An asymmetric transformer predicts masked tokens
- The diffusion generation process is kept
Pros & cons
✓ What we like
- The diffusion generation process is kept during training
- Token masking happens in latent space
! What to watch out for
- Prediction relies on the unmasked tokens
- MDTv2 changes the macro network structure and training strategy
FAQ
What does it mask?
The material states some tokens are masked in latent space during training.
What does MDTv2 change?
A more efficient macro network structure and training strategy are named.
Last reviewed: 2026-11-15
More AI image generation tools
View all →-
123RF Stock library with integrated AI image tools Free tools Text to image Image editing Background remover Image upscaler -
360智图 Image search, licensing and AI editing from 360 Free tools Text to image Background remover Product image Model generator -
360鸿图 Image generation aimed at Chinese-speaking users, with prompts written in Chinese Free tools Creator tools Text to image Art generator Image to image -
a1.art Filter-driven image generation with face swap Free tools Creator tools Text to image Art generator -
AI Anime Generator Photos and text into anime-style art Freemium tools Creator tools Text to image Image to image Image to video -
AI Art Generator Text prompts into original artwork drafts Freemium tools Creator tools Text to image Image editing Art generator