XMC-GAN

Closed weights Google Research April 2022

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
14 April 2022
Authors
Han Zhang, Jing Yu Koh, Jason Baldridge, Honglak Lee, Yinfei Yang

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

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

"Models are trained with a batch size of 256. For reporting results in our paper, models are trained for 1000 epochs, and we report the scores corresponding to the checkpoint with the best FID score on the validation set."

Epochs
1,000

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

"XMC-GAN also generalizes to the challenging Localized Narratives dataset (which has longer, more detailed descriptions), improving state-of-the-art FID from 48.70 to 14.12"

Record confidence
Unknown

Sources

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

Reference
Cross-Modal Contrastive Learning for Text-to-Image Generation
Last updated
28 November 2025

What the numbers mean

Where it came from

XMC-GAN was published by Google Research, in United States of America, in April 2022. It comes out of industry.

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

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

XMC-GAN — common questions

01

Who created XMC-GAN?

XMC-GAN was published by Google Research, based in United States of America, categorised as industry.

02

When was XMC-GAN released?

XMC-GAN was published in April 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.

03

What is XMC-GAN used for?

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

04

What GPU do I need to run XMC-GAN?

None. XMC-GAN 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.

05

Is XMC-GAN open source?

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

06

How many parameters does XMC-GAN have?

No parameter count has been published for XMC-GAN, 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.