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

23 Jan 2023  ·  Axel Sauer, Tero Karras, Samuli Laine, Andreas Geiger, Timo Aila ·

Text-to-image synthesis has recently seen significant progress thanks to large pretrained language models, large-scale training data, and the introduction of scalable model families such as diffusion and autoregressive models. However, the best-performing models require iterative evaluation to generate a single sample. In contrast, generative adversarial networks (GANs) only need a single forward pass. They are thus much faster, but they currently remain far behind the state-of-the-art in large-scale text-to-image synthesis. This paper aims to identify the necessary steps to regain competitiveness. Our proposed model, StyleGAN-T, addresses the specific requirements of large-scale text-to-image synthesis, such as large capacity, stable training on diverse datasets, strong text alignment, and controllable variation vs. text alignment tradeoff. StyleGAN-T significantly improves over previous GANs and outperforms distilled diffusion models - the previous state-of-the-art in fast text-to-image synthesis - in terms of sample quality and speed.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Text-to-Image Generation COCO StyleGAN-T (Zero-shot, 64x64) FID 7.3 # 9
Text-to-Image Generation COCO StyleGAN-T (Zero-shot, 256x256) FID 13.9 # 19

Methods


No methods listed for this paper. Add relevant methods here