Skip to content

StyleGAN3-T

NVIDIAAalto UniversityImage generationOpen weights

The StyleGAN3-T model is an open-weights image generation model from NVIDIA,Aalto University with 2230000.0 parameters.

About StyleGAN3-T

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner. This manifests itself as, e.g., detail appearing to be glu

Details

Provider
NVIDIA,Aalto University
Task
Image generation
Parameters
2230000.0
Released
2021-06-21
Open weights
Yes
View model source

Explore

FAQ