Diffusion-GAN

Open weights UT Austin,Microsoft June 2022

No estimate

No hardware requirements for this model

This model's weights are open, but no parameter count has been published for it. Every memory and speed figure starts from that number, so we would rather show nothing than a fabricated estimate.

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
UT Austin,Microsoft
Organisation type
Academia,Industry
Country
United States of America
Published
5 June 2022
Authors
Zhendong Wang, Huangjie Zheng, Pengcheng He, Weizhu Chen, Mingyuan Zhou

What it does

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

Domain
Image generation
Task
Image generation, Text-to-image
Numerical format
FP16

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

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA V100

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
Open — downloadable
Model access
Open weights (unrestricted)
Training code
Open source

MIT license https://github.com/Zhendong-Wang/Diffusion-GAN https://huggingface.co/zhendongw/diffusion-gan/tree/main

Hugging Face
zhendongw

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

Table 1 "We demonstrate the advantages of Diffusion-GAN over strong GAN baselines on various datasets, showing that it can produce more realistic images with higher stability and data efficiency than state-of-the-art GANs." "Quantitatively, Diffusion StyleGAN2 outperforms all the GAN baselines in generation diversity, as measured by Recall, on all 6 benchmark datasets and outperforms them in FID by a clear margin on 5 out of the 6 benchmark datasets."

Record confidence
Unknown
Citations
327

Sources

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

Reference
Diffusion-GAN: Training GANs with Diffusion
Last updated
25 May 2026

What the numbers mean

About this model

Diffusion-GAN was published by UT Austin,Microsoft, in United States of America, in June 2022. academia,Industry is the category the publisher falls under.

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

Published weights mean the model runs on your machine rather than someone else's, which is what makes the hardware question below answerable at all. It is published under the zhendongw organisation on Hugging Face.

Training and provenance

The reason it appears in this catalogue at all is sOTA improvement.

Answers

Diffusion-GAN — common questions

01

Is Diffusion-GAN open source?

Its weights are published, so Diffusion-GAN can be downloaded and run on your own hardware. Note that open weights is not the same as open source in the full sense — it says nothing about the training data, the training code, or the commercial terms attached.

02

How many parameters does Diffusion-GAN have?

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

03

Who created Diffusion-GAN?

Diffusion-GAN was published by UT Austin,Microsoft, based in United States of America, categorised as academia,Industry.

04

When was Diffusion-GAN released?

Diffusion-GAN was published in June 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.

05

What is Diffusion-GAN used for?

Diffusion-GAN works in Image generation, and is recorded as handling image generation, Text-to-image. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

06

Where can I download Diffusion-GAN?

Its weights are published under the zhendongw organisation on Hugging Face. We do not host model files — this site calculates what hardware is needed to run them.

07

What GPU do I need to run Diffusion-GAN?

We cannot say. Diffusion-GAN has open weights, but no parameter count has been published for it, and every memory and speed calculation starts from that number. We would rather show nothing than a fabricated estimate.

Source

Original publication

Record last updated 25 May 2026

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.