NGC | Catalog
CatalogModelsStyleGAN3 pretrained models

StyleGAN3 pretrained models

Logo for StyleGAN3 pretrained models
Description
StyleGAN3 pretrained models for FFHQ, AFHQv2 and MetFaces datasets.
Publisher
NVIDIA
Latest Version
1
Modified
December 11, 2023
Size
3.58 GB
Field Response
Intended Application(s) & Domain(s): Content generation (such as Adobe Photoshop) for generating images of people, animals, etc.
Model Type: Generative Adversarial Network (GAN)
Intended Users: Intended for reproduction of results.
Output: Outputs image
List the steps explaining how this model works: Recognizes different classes of objects
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: Not Applicable
Technical Limitations: Discriminator is not equivariant. Operators in sRGB color space (after tone mapping).
Verified to have met prescribed NVIDIA standards: Yes
Performance Metrics: Fréchet inception distance (FID)
Potential Known Risks: None Known
End User License Agreement: https://github.com/NVlabs/stylegan3/blob/main/LICENSE.txt