{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/stylegan-t-unlocking-the-power-of-gans-for","title":"StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis","arxiv_id":"2301.09515","date":"2023-01-23","proceeding":null,"authors":["Axel Sauer","Tero Karras","Samuli Laine","Andreas Geiger","Timo Aila"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2301.09515v1","url_pdf":"https://arxiv.org/pdf/2301.09515v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"stylegan-t-unlocking-the-power-of-gans-for","repo_url":"https://github.com/autonomousvision/stylegan-t","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"StyleGAN-T (Zero-shot, 64x64)","rank_in_archive_order":17,"of":69,"metrics":{"FID":"7.3"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"StyleGAN-T (Zero-shot, 256x256)","rank_in_archive_order":38,"of":69,"metrics":{"FID":"13.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2301.09515","atlas_url":"https://app.syntology.ai/?focus=2301.09515","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}