SAGAN

Closed weights Rutgers University,Google Research June 2019

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
Rutgers University,Google Research
Organisation type
Academia,Industry
Country
United States of America
Published
14 June 2019
Authors
Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena

What it does

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

Domain
Image generation
Task
Image generation

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.

Training data
tokens

" where k = 1, 2, 4, 8 after few training epochs on ImageNet. For memory efficiency, we choose k = 8 (i.e., C¯ = C/8) in all our experiments."

Epochs
8

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
2.2 × 10²⁰ FLOP

Assuming (!) they used V100s: 125000000000000 FLOP / GPU / sec * 336 hours [see training time notes] * 3600 sec / hour * 4 GPUs * 0.3 [assumed utilization] = 1.8144e+20 FLOP

How it was established
Hardware

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
4
Wall-clock time
336 hours (14 days)

"Models were trained for roughly 2 weeks on 4 GPUs each"

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
Open source

Apache 2.0 https://github.com/brain-research/self-attention-gan

How it is classified

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

Record confidence
Likely

Sources

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

Reference
Self-Attention Generative Adversarial Networks
Last updated
28 November 2025

What the numbers mean

What this model is

SAGAN was published by Rutgers University,Google Research, in the country recorded as United States of America, during June 2019. The publishing organisation is categorised as academia,Industry.

It works in the domain of Image generation, and is recorded as performing the task of image generation.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

The training run consumed about 2.2 × 10²⁰ FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.

Answers

SAGAN — common questions

01

SAGAN— who created it?

It was published by Rutgers University,Google Research, based in United States of America, an organisation categorised as academia,Industry.

02

SAGAN— when was it released?

It was published in June 2019. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

03

SAGAN— what is it used for?

It works in the domain of Image generation, and is recorded as handling the task of image generation. 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.

04

SAGAN— how much compute was used to train it?

Training consumed around 2.2 × 10²⁰ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

05

SAGAN— 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.

06

SAGAN— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

07

SAGAN— how many parameters does it have?

No parameter count has been published for it, which is why no memory or speed figure appears on this page.

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.