The training code for StyleGAN-T is out!
github.com/autonomousvision/β¦
Unfortunately, we can not share the weights π«€
On a related note, I will be joining @StabilityAI next month. That means the next generation of large-scale GANs will be fully open-source π
StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis
significantly improves over previous GANs and outperforms distilled diffusion models in terms of sample quality and speed
abs: arxiv.org/abs/2301.09515
project page: sites.google.com/view/stylegβ¦
Apr 7, 2023 Β· 9:04 AM UTC
