Concept
Diffusion Transformers
Diffusion Transformers (DiTs) are denoising diffusion models that use a Transformer as the backbone instead of the U-Net that older image diffusion models relied on. The generative process is the same as any diffusion model: start from noise, predict and remove noise over…
The rest of “Diffusion Transformers” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.
Log in to unlock→