AI engineering glossary · Generative media multimodal
What is diffusion transformer?
Diffusion transformer (also called DiT): A diffusion model whose denoising network is a transformer that processes patches of a latent image as tokens, instead of a convolutional U-Net. It scales predictably with model size and compute and is used in many recent image and video generators.
Diffusion transformer: an example
A latent is cut into 2 x 2 patches, each treated as a token, and a stack of transformer blocks predicts the noise for all patches together.
Related terms
More Generative media multimodal terms
- Discriminator
- Document understanding
- DreamBooth
- Early fusion
- Evidence lower bound
- FastSpeech
- Flamingo
- Flow matching
Where you learn it
Diffusion transformer is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.