NodeValid

Published video-model weights, licences and hardware notes

SVD states 576x1024 as a property of training

The card states that the model was trained to generate 25 frames at resolution 576x1024, given a context frame of the same size. Output and input are the same shape, and the size is described as a training property. As of 2026-09-22.

Stable Video Diffusion in the resolution column, as publishedAn image-conditioned release has to match its context frame, so the resolution here is a constraint on what a reader feeds in as much as on what comes out.Output size576x1024sizes the memoryfigureMemory it sizesAbout 180s on an A10080GB cardheld over thismany framesClip length25 frames, 4sec or lessThe context frame has to matchWhat the model was trained to generate
Fig. 1 Input shape and output shape are the same value on this card, by construction.
Stable Video Diffusion in the resolution column, with the columns that qualify it. Read from huggingface.co/stabilityai on 2026-09-22.
ColumnWhat the pages state
Resolution, in the vendor's own words576x1024
The detail published beside itWhat the model was trained to generate
Hardware, from the same pagesAbout 180s on an A100 80GB card
Length, from the same pages25 frames, 4sec or less

Inclusion rule. The value this page is about, the detail the vendor attached to it, and the two columns that change how it should be read. A column the vendor left empty keeps its row and says so. Order. This column first, then its detail, then the two columns that qualify it.

1The input side is the part that catches people

A context frame of the same size means source images have to be prepared at 576x1024 before anything else happens. That is a pipeline requirement, not just an output description.

Releases that generate from text alone have no such constraint, so this row is a different kind of value from most of the column.

2Trained to generate is narrower than supports

The phrasing describes what the training did, not what the code accepts. Other sizes may run and were not what the weights learned, which is a real distinction for output quality.

Another release in the register uses the word supports for its sizes. The register keeps both wordings rather than normalising them into one column heading.

3Twenty-five frames, and a candid note about it

The same card describes the generated videos as rather short, at four seconds or less. That is written as a limitation rather than as a specification, and it is unusually frank for a model card.

So the output is fully described in both dimensions and one of them comes with an apology. The register records the size, the frame count and the wording.

4Sources

Output sizes above appear on huggingface.co/stabilityai, checked 2026-09-22. The full entry is at this family's page; what counts as a stated size is on resolution. Nearby: No frame size given, One size per checkpoint.