GigaGAN
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
- POSTECH,Carnegie Mellon University (CMU),Adobe
- Organisation type
- Academia,Academia,Industry
- Country
- Korea (Republic of), United States of America
- Published
- 19 June 2023
- Authors
- Minguk Kang, Jun-Yan Zhu, Richard Zhang, Jaesik Park, Eli Shechtman, Sylvain Paris, Taesung Park
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Image generation
- Task
- Text-to-image, 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.
- Parameters
- 1B
- Training data
- 1,960,000,000 tokens
1B (Table 2)
[IMAGES] 0.98B of training images (table 2)
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
- 3.9 × 10²² FLOP
- How it was established
- Hardware
"GigaGAN and SD-v1.5 require 4,783 and 6,250 A100 GPU days" 312*10^12 FLOP / sec / GPU * 4783 GPU-days * 24 hours / day * 3600 sec / hour * 0.3 [assumed utilization] = 3.8680312e+22 FLOP
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.
- Record confidence
- Confident
Sources
Where this record came from and when it was last checked.
- Reference
- Scaling up GANs for Text-to-Image Synthesis
- Last updated
- 28 November 2025
What the numbers mean
About this model
GigaGAN was published by POSTECH,Carnegie Mellon University (CMU),Adobe, in the country recorded as Korea (Republic of), during June 2023. The publishing organisation is categorised as academia,Academia,Industry.
It works in the domain of Image generation, and is recorded as performing the task of text-to-image, Image generation.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Training and provenance
Producing it required arithmetic totalling around 3.9 × 10²² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
Training consumed a corpus of around 1,960,000,000 tokens of text.
Answers
GigaGAN — common questions
GigaGAN— how much compute was used to train it?
Training consumed around 3.9 × 10²² 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.
GigaGAN— 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.
GigaGAN— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
GigaGAN— how many parameters does it have?
It has a parameter count of 1B. 1B (Table 2). 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.
GigaGAN— who created it?
It was published by POSTECH,Carnegie Mellon University (CMU),Adobe, based in Korea (Republic of), an organisation categorised as academia,Academia,Industry.
GigaGAN— when was it released?
It was published in June 2023. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.
GigaGAN— what is it used for?
It works in the domain of Image generation, and is recorded as handling the task of text-to-image, Image generation. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
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.