StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis · HackerPapers discussions

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis — mentioned by godelski

Thu, 14 Dec 2023 23:17:04 GMT

Sorry, I left too much knowledge for inference. I presumed it was safe to let users infer that a 2018 (StyleGAN) or 2019 (StyleGAN2) model was not going to compete with performance of a 2023 model, regardless of architecture. There has in fact been improvements in GANs in the last 5 years. Text conditioning is not unique to diffusion and is rather a subnetwork for conditioning (actually StyleGAN's whole innovation was creating a subnetwork for conditioning synthesis) There are definitely modern GANs that are T2I and computationally cheaper than a latent diffusion model for a comparable…

Paper and discussion history. A mention is not an endorsement.

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis — mentioned by cubefox

Tue, 13 Jun 2023 13:35:17 GMT

I thought for fast text-to-image synthesizer you would need a GAN instead of a diffusion model. GAN models are much faster. Though apparently they aren't quite competitive with diffusion models in terms of quality. See https://arxiv.org/abs/2301.09515

Paper and discussion history. A mention is not an endorsement.

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis — HN submission

Tue, 24 Jan 2023 08:13:42 GMT

StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.