MaskGIT (ImageNet)
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
- Google Research
- Organisation type
- Industry
- Country
- United States of America
- Published
- 8 February 2022
- Authors
- Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, William T. Freeman
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Image generation, Image-to-image
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
- 227M
- Training data
- tokens
- Epochs
- 300
227M Table 1
"For each dataset, we only train a single autoencoder, decoder, and codebook with 1024 tokens on cropped 256x256 images for all the experiments. The image is always compressed by a fixed factor of 16, i.e. from H ˆW to a grid of tokens in the size of h ˆ w, where h=H{16 and w=W{16. We find that this autoencoder, together with the codebook, can be reused to synthesize 512ˆ512 images." "All models are trained on 4x4 TPU devices with a batch size of 256. ImageNet models are trained for 300 epochs …
The training run
What it physically took to train: which chips, how many, for how long, and what that drew from the wall.
- Chips used
- 16
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
- Record confidence
- Confident
"Our experiments demonstrate that MaskGIT significantly outperforms the state-of-the-art transformer model on the ImageNet dataset, and accelerates autoregressive decoding by up to 64x"
Sources
Where this record came from and when it was last checked.
- Reference
- MaskGIT: Masked Generative Image Transformer
- Last updated
- 11 February 2026
What the numbers mean
About this model
MaskGIT (ImageNet) was published by Google Research, in the country recorded as United States of America, during February 2022. It comes out of an organisation categorised as industry.
It works in the domain of Image generation, and is recorded as performing the task of image generation, Image-to-image.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
How it was trained
The reason it appears in this catalogue at all: sOTA improvement.
Answers
MaskGIT (ImageNet) — common questions
MaskGIT (ImageNet)— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
MaskGIT (ImageNet)— how many parameters does it have?
It has a parameter count of 227M. 227M Table 1. 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.
MaskGIT (ImageNet)— who created it?
It was published by Google Research, based in United States of America, an organisation categorised as industry.
MaskGIT (ImageNet)— when was it released?
It was published in February 2022. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
MaskGIT (ImageNet)— what is it used for?
It works in the domain of Image generation, and is recorded as handling the task of image generation, Image-to-image. 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.
MaskGIT (ImageNet)— what GPU do I need to run it?
None. This 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.
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.