StarGAN v2
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
- NAVER,Yonsei University,Swiss Federal Institute of Technology
- Organisation type
- Industry,Academia,Academia
- Country
- Korea (Republic of), Switzerland
- Published
- 4 December 2019
- Authors
- Yunjey Choi, Youngjung Uh, Jaejun Yoo, Jung-Woo Ha
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision, Image generation
- Task
- Image generation, Image-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
- 400,000 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
- Open — downloadable
- Model access
- Open weights (non-commercial)
- Training code
- Open (non-commercial)
https://github.com/clovaai/stargan-v2?tab=readme-ov-file non-commercial
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
- Highly cited,SOTA improvement
- Record confidence
- Unknown
- Citations
- 2,072
"Votes from AMT workers for the most preferred method regarding visual quality and style reflection (%). StarGAN v2 outperforms the baselines with remarkable margins in all aspects." "As shown in Table 2, our method outperforms all the baselines by a large margin in terms of visual quality. For both CelebA-HQ and AFHQ, our method achieves FIDs of 13.7 and 16.2, respectively, which are more than two times improvement over the previous leading method."
Sources
Where this record came from and when it was last checked.
- Reference
- StarGAN v2: Diverse Image Synthesis for Multiple Domains
- Last updated
- 25 May 2026
What the numbers mean
What this model is
StarGAN v2 was published by NAVER,Yonsei University,Swiss Federal Institute of Technology, in the country recorded as Korea (Republic of), during December 2019. The category the publisher falls under is industry,Academia,Academia.
It works in the domain of Vision, Image generation, and is recorded as performing the task of image generation, Image-to-image.
Because its weights were released, nothing about running it depends on a provider staying available — it is yours once downloaded.
How it was trained
Training consumed a corpus of around 400,000 tokens of text.
The reason it appears in this catalogue at all: highly cited,SOTA improvement.
Answers
StarGAN v2 — common questions
StarGAN v2— what is it used for?
It works in the domain of Vision, Image generation, and is recorded as handling the task of image generation, Image-to-image. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
StarGAN v2— where can I download it?
The weights are published, though we do not hold a repository link for it. This site calculates hardware requirements rather than hosting model files.
StarGAN v2— what GPU do I need to run it?
We cannot say. It 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.
StarGAN v2— is it open source?
Its weights are published, so it 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.
StarGAN v2— 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.
StarGAN v2— who created it?
It was published by NAVER,Yonsei University,Swiss Federal Institute of Technology, based in Korea (Republic of), an organisation categorised as industry,Academia,Academia.
StarGAN v2— when was it released?
It was published in December 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.
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.