AI Foundations
Diffusion transformer
A type of generative AI that combines repeated noise removal with attention to relationships between pieces of information.
Example
An image AI repeatedly clears noise while comparing relationships between parts of the picture.
Why people use it
It uses transformer-style processing as part of an image or other media generator.
What you'll hear
“The image generator uses transformer blocks.”
What this means for you
Ask what the design changes in actual image quality, speed or cost.
Can you control it?
Developer-only
The people building or running the AI choose this setup. An everyday user generally needs their help to change how this part works.
Common questions
- Is a diffusion transformer the same as a text-generating transformer?
- No. Shared design ideas can support different goals and generation processes.
- Does the name tell us how good the images are?
- No. Training, examples and the complete design affect quality.
- Can different diffusion transformers behave differently?
- Yes. Sharing a broad design does not mean identical training or capabilities.