NodeValid

Published video-model weights, licences and hardware notes

Diffusion transformer, named in a count

A diffusion transformer is the component that turns noise into a latent video over many steps. When a card labels part of its parameter count DiT, it is naming the architecture at the same time as the size. As of 2026-09-22.

What the label tells a readerA labelled count says what kind of model this is before a reader has opened a paper, and it says which component a memory figure is dominated by.A labelled breakdownA single figureSizeStated per componentStated onceArchitectureNamed by the labelsNot indicatedWhich part dominates memoryInferableNot inferableQuantising targetObviousGuessworkThe label is free information
Fig. 1 Two counts with names beat one count without, at the same length.
What the label adds to a parameter count. Recorded 2026-09-22.
QuestionAnswered by the label
What kind of model is thisYes
Which part is largeYes
How many denoising stepsNo
How long a clip it producesNo

Inclusion rule. Questions a labelled count can and cannot answer. A question it cannot answer is kept, because the label is often over-read. Order. The two it answers first, then the two it does not.

1Labels are not marketing

DiT and VAE are specific terms with specific meanings. A reader who knows them knows roughly how the run behaves, which part quantising would help, and where the memory will go.

Compare a card that states a single round figure. Same order of magnitude, far less to go on, and no way to reason about the memory statement beside it.

2What the label still does not settle

Step counts, scheduler choices, attention implementation and training data are all outside it, and all of them affect both output and runtime.

The register records the labels the vendor used because they are part of the published value. It does not classify releases by architecture, because that would be a reading rather than a quotation.

3Where the label appears here

One card in the register labels part of its parameter count DiT, which is the only place in this column where the architecture is named inside the value rather than left to a paper.

The rest of the column holds counts without labels, so a reader who wants to know what kind of model a release is has to go elsewhere. The register quotes what was published rather than classifying releases itself.

A reading note, not an entry: no vendor value appears on this page. Where the register records this term for a particular release, it is on the size column and on that family's own page. Nearby terms: Peak memory, Memory floor.