PG-SWGAN

Closed weights ETH Zurich 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
ETH Zurich
Organisation type
Academia
Country
Switzerland
Published
15 June 2019
Authors
Jiqing Wu, Zhiwu Huang, Dinesh Acharya, Wen Li, Janine Thoma, Danda Pani Paudel, Luc Van Gool

What it does

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

Domain
Image generation
Task
Image generation
Numerical format
FP32

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

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 (non-commercial)

looks like code but no weights, no license specified: https://github.com/musikisomorphie/swd

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

"For fair comparison, we equip the same progressive growing architecture with our proposed SWGAN objective and its dual SWD blocks (PG-SWGAN). As shown in Fig. 3 (Right) and Fig. 5, our PG-SWGAN can outperform PG-WGAN in terms of both qualitative and quantitative comparison on the CelebA-HQ and LSUN datasets"

Record confidence
Unknown
Citations
136

Sources

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

Reference
Sliced Wasserstein Generative Models
Last updated
1 December 2025

What the numbers mean

About this model

PG-SWGAN was published by ETH Zurich, in Switzerland, in June 2019. It comes out of academia.

It works in Image generation, and is recorded as doing image generation.

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

Its inclusion criterion is sOTA improvement.

Answers

PG-SWGAN — common questions

01

How many parameters does PG-SWGAN have?

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

02

Who created PG-SWGAN?

PG-SWGAN was published by ETH Zurich, based in Switzerland, categorised as academia.

03

When was PG-SWGAN released?

PG-SWGAN 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.

04

What is PG-SWGAN used for?

PG-SWGAN works in Image generation, and is recorded as handling image generation. These are the areas it was designed around; they describe intent rather than a hard boundary.

05

What GPU do I need to run PG-SWGAN?

None. PG-SWGAN 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 PG-SWGAN open source?

No. PG-SWGAN has not had its weights published, so it exists only as a service controlled by its owner.

Source

Original publication

Record last updated 1 December 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.