W.A.L.T

Closed weights Stanford University,Google Research,Georgia Institute of Technology 4.7B parameters December 2023

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Stanford University,Google Research,Georgia Institute of Technology
Organisation type
Academia,Industry,Academia
Country
United States of America
Published
11 December 2023
Authors
Agrim Gupta, Lijun Yu, Kihyuk Sohn, Xiuye Gu, Meera Hahn, Li Fei-Fei, Irfan Essa, Lu Jiang, José Lezama

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Video
Task
Video generation, Text-to-video

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
4.7B

"We train our base model at resolution 17 × 128 × 128 (3B parameters), and two 2× cascaded super-resolution models for 17 × 128 × 224 → 17 × 256 × 448 (L, 1.3B, p = 2) and 17 × 256 × 448 → 17 × 512 × 896 (L, 419M, p = 2) respectively" 3B + 1.3B + 419M = 4.719B

Training data
tokens

"We train W.A.L.T for text-to-video jointly on text-image and text-video pairs (Sec. 4.2). We used a dataset of ∼970M text-image pairs and ∼89M text-video pairs from the public internet and internal sources. "

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
Unreleased
Training code
Unreleased

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Why it is tracked
SOTA improvement

"these design decisions enable us to achieve state-of-the-art performance on established video (UCF-101 and Kinetics-600) and image (ImageNet) generation benchmarks without using classifier free guidance"

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Photorealistic Video Generation with Diffusion Models
Last updated
28 November 2025

What the numbers mean

Where it came from

W.A.L.T was published by Stanford University,Google Research,Georgia Institute of Technology, in United States of America, in December 2023. academia,Industry,Academia is the category the publisher falls under.

It works in Video, and is recorded as doing video generation, Text-to-video.

This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.

What went into building it

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

W.A.L.T — common questions

01

How many parameters does W.A.L.T have?

W.A.L.T has 4.7B parameters. "We train our base model at resolution 17 × 128 × 128 (3B parameters), and two 2× cascaded super-resolution models for 17 × 128 × 224 → 17 × 256 × 448 (L, 1.3B, p = 2) and 17 × 256 × 448 → 17 × 512 × 896 (L, 419M, p = 2) respectively" 3B + 1.3B + 419M = 4.719B. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

02

Who created W.A.L.T?

W.A.L.T was published by Stanford University,Google Research,Georgia Institute of Technology, based in United States of America, categorised as academia,Industry,Academia.

03

When was W.A.L.T released?

W.A.L.T was published in December 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

04

What is W.A.L.T used for?

W.A.L.T works in Video, and is recorded as handling video generation, Text-to-video. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.

05

What GPU do I need to run W.A.L.T?

None. W.A.L.T is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

06

Is W.A.L.T open source?

No. W.A.L.T has not had its weights published, so it exists only as a service controlled by its owner.

Source

Original publication

Record last updated 28 November 2025

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.