{"url":"/method/stylegan2","slug":"stylegan2","name":"StyleGAN2","full_name":"StyleGAN2","full_name_withheld":false,"description_markdown":"**StyleGAN2** is a generative adversarial network that builds on [StyleGAN](https://paperswithcode.com/method/stylegan) with several improvements. First, [adaptive instance normalization](https://paperswithcode.com/method/adaptive-instance-normalization) is redesigned and replaced with a normalization technique called [weight demodulation](https://paperswithcode.com/method/weight-demodulation). Secondly, an improved training scheme upon progressively growing is introduced, which achieves the same goal - training starts by focusing on low-resolution images and then progressively shifts focus to higher and higher resolutions - without changing the network topology during training. Additionally, new types of regularization like lazy regularization and [path length regularization](https://paperswithcode.com/method/path-length-regularization) are proposed.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Analyzing and Improving the Image Quality of StyleGAN","paper":"/paper/analyzing-and-improving-the-image-quality-of","first_author":"Tero Karras","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/analyzing-and-improving-the-image-quality-of"},"source":{"url":"https://arxiv.org/abs/1912.04958v2","title":"Analyzing and Improving the Image Quality of StyleGAN","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/NVlabs/stylegan2","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Adversarial Networks","url":"/methods/category/generative-adversarial-networks","pwc_aliases":[]},{"area":"Computer Vision","area_id":"computer-vision","collection":"Generative Models","url":"/methods/category/generative-models","pwc_aliases":[]}],"n_papers_tagged":49,"archive_num_papers":49,"papers_newest_first":[{"paper":null,"title":"Pose and Facial Expression Transfer by using StyleGAN","date":"2025-04-17","arxiv_id":"2504.13021","n_code_links":0,"syntology":null},{"paper":"/paper/the-gan-is-dead-long-live-the-gan-a-modern","title":"The GAN is dead; long live the GAN! A Modern GAN Baseline","date":"2025-01-09","arxiv_id":"2501.05441","n_code_links":1,"syntology":{"ran":9,"of":11,"unverified":2,"pointer_only":11}},{"paper":"/paper/singular-value-scaling-efficient-generative","title":"Singular Value Scaling: Efficient Generative Model Compression via Pruned Weights Refinement","date":"2024-12-23","arxiv_id":"2412.17387","n_code_links":1,"syntology":null},{"paper":null,"title":"MyTimeMachine: Personalized Facial Age Transformation","date":"2024-11-21","arxiv_id":"2411.14521","n_code_links":0,"syntology":null},{"paper":"/paper/unsupervised-panoptic-interpretation-of","title":"Unsupervised Panoptic Interpretation of Latent Spaces in GANs Using Space-Filling Vector Quantization","date":"2024-10-27","arxiv_id":"2410.20573","n_code_links":1,"syntology":null},{"paper":null,"title":"Stool Recognition for Colorectal Cancer Detection through Deep Learning","date":"2024-10-19","arxiv_id":"2410.17288","n_code_links":0,"syntology":null},{"paper":"/paper/mm2latent-text-to-facial-image-generation-and","title":"MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance","date":"2024-09-17","arxiv_id":"2409.11010","n_code_links":1,"syntology":null},{"paper":null,"title":"Bridging the Gap: Studio-like Avatar Creation from a Monocular Phone Capture","date":"2024-07-28","arxiv_id":"2407.19593","n_code_links":0,"syntology":null},{"paper":"/paper/tr0n-translator-networks-for-0-shot-plug-and","title":"TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation","date":"2023-04-26","arxiv_id":"2304.13742","n_code_links":2,"syntology":{"ran":9,"of":19,"unverified":10,"pointer_only":1}},{"paper":"/paper/ilsgan-independent-layer-synthesis-for","title":"ILSGAN: Independent Layer Synthesis for Unsupervised Foreground-Background Segmentation","date":"2022-11-25","arxiv_id":"2211.13974","n_code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-performance-of-stylegan2-ada","title":"Evaluating the Performance of StyleGAN2-ADA on Medical Images","date":"2022-10-07","arxiv_id":"2210.03786","n_code_links":0,"syntology":null},{"paper":"/paper/are-gan-based-morphs-threatening-face","title":"Are GAN-based Morphs Threatening Face Recognition?","date":"2022-05-05","arxiv_id":"2205.02496","n_code_links":1,"syntology":null},{"paper":"/paper/can-we-find-neurons-that-cause-unrealistic","title":"Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?","date":"2022-01-17","arxiv_id":"2201.06346","n_code_links":1,"syntology":null},{"paper":"/paper/gan-supervised-dense-visual-alignment","title":"GAN-Supervised Dense Visual Alignment","date":"2021-12-09","arxiv_id":"2112.05143","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}},{"paper":"/paper/towards-fine-grained-image-classification","title":"Towards Fine-grained Image Classification with Generative Adversarial Networks and Facial Landmark Detection","date":"2021-08-28","arxiv_id":"2109.00891","n_code_links":1,"syntology":null},{"paper":"/paper/content-aware-gan-compression","title":"Content-Aware GAN Compression","date":"2021-04-06","arxiv_id":"2104.02244","n_code_links":1,"syntology":{"ran":9,"of":16,"unverified":7,"pointer_only":0}},{"paper":null,"title":"On the Applicability of Synthetic Data for Face Recognition","date":"2021-04-06","arxiv_id":"2104.02815","n_code_links":0,"syntology":null},{"paper":"/paper/multi-class-multi-instance-count-conditioned","title":"Multi-Class Multi-Instance Count Conditioned Adversarial Image Generation","date":"2021-03-31","arxiv_id":"2103.16795","n_code_links":1,"syntology":{"ran":3,"of":3,"unverified":0,"pointer_only":3}},{"paper":"/paper/labels4free-unsupervised-segmentation-using","title":"Labels4Free: Unsupervised Segmentation using StyleGAN","date":"2021-03-27","arxiv_id":"2103.14968","n_code_links":1,"syntology":{"ran":0,"of":1,"unverified":1,"pointer_only":1}},{"paper":"/paper/matched-sample-selection-with-gans-for","title":"Matched sample selection with GANs for mitigating attribute confounding","date":"2021-03-24","arxiv_id":"2103.13455","n_code_links":1,"syntology":null},{"paper":"/paper/do-generative-models-know-disentanglement","title":"Learning Disentangled Representation by Exploiting Pretrained Generative Models: A Contrastive Learning View","date":"2021-02-21","arxiv_id":"2102.10543","n_code_links":2,"syntology":{"ran":3,"of":5,"unverified":2,"pointer_only":5}},{"paper":"/paper/traumerai-dreaming-music-with-stylegan","title":"TräumerAI: Dreaming Music with StyleGAN","date":"2021-02-09","arxiv_id":"2102.04680","n_code_links":1,"syntology":null},{"paper":"/paper/generating-images-from-caption-and-vice-versa","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","date":"2021-02-02","arxiv_id":"2102.01645","n_code_links":3,"syntology":null},{"paper":"/paper/towards-faster-and-stabilized-gan-training-1","title":"Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis","date":"2021-01-12","arxiv_id":"2101.04775","n_code_links":7,"syntology":{"ran":8,"of":9,"unverified":1,"pointer_only":9}},{"paper":"/paper/vogue-try-on-by-stylegan-interpolation","title":"TryOnGAN: Body-Aware Try-On via Layered Interpolation","date":"2021-01-06","arxiv_id":"2101.02285","n_code_links":4,"syntology":null},{"paper":"/paper/focal-frequency-loss-for-generative-models","title":"Focal Frequency Loss for Image Reconstruction and Synthesis","date":"2020-12-23","arxiv_id":"2012.12821","n_code_links":1,"syntology":null},{"paper":"/paper/time-travel-rephotography","title":"Time-Travel Rephotography","date":"2020-12-22","arxiv_id":"2012.12261","n_code_links":1,"syntology":{"ran":2,"of":2,"unverified":0,"pointer_only":0}},{"paper":"/paper/this-face-does-not-exist-but-it-might-be","title":"This Face Does Not Exist ... But It Might Be Yours! Identity Leakage in Generative Models","date":"2020-12-10","arxiv_id":"2101.05084","n_code_links":1,"syntology":null},{"paper":null,"title":"Positional Encoding as Spatial Inductive Bias in GANs","date":"2020-12-09","arxiv_id":"2012.05217","n_code_links":0,"syntology":null},{"paper":"/paper/bayesian-image-reconstruction-using-deep","title":"Bayesian Image Reconstruction using Deep Generative Models","date":"2020-12-08","arxiv_id":"2012.04567","n_code_links":2,"syntology":null}],"papers_shown":30,"tasks":[{"task":"/task/image-generation","name":"Image Generation","papers":17},{"task":"/task/data-augmentation","name":"Data Augmentation","papers":5},{"task":null,"name":"Generative Adversarial Network","papers":5},{"task":"/task/image-manipulation","name":"Image Manipulation","papers":5},{"task":"/task/attribute","name":"Attribute","papers":4},{"task":"/task/conditional-image-generation","name":"Conditional Image Generation","papers":3},{"task":"/task/face-generation","name":"Face Generation","papers":3},{"task":"/task/image-reconstruction","name":"Image Reconstruction","papers":3},{"task":"/task/image-restoration","name":"Image Restoration","papers":3},{"task":"/task/image-to-image-translation","name":"Image-to-Image Translation","papers":3},{"task":"/task/translation","name":"Translation","papers":3},{"task":"/task/colorization","name":"Colorization","papers":2},{"task":"/task/disentanglement","name":"Disentanglement","papers":2},{"task":"/task/face-recognition","name":"Face Recognition","papers":2},{"task":"/task/image-morphing","name":"Image Morphing","papers":2},{"task":"/task/medical-image-generation","name":"Medical Image Generation","papers":2},{"task":"/task/segmentation","name":"Segmentation","papers":2},{"task":"/task/super-resolution","name":"Super-Resolution","papers":2},{"task":"/task/high","name":"Vocal Bursts Intensity Prediction","papers":2},{"task":"/task/10-shot-image-generation","name":"10-shot image generation","papers":1}],"tasks_shown":20,"n_tasks":73,"usage_by_year":[{"year":"2019","papers":1},{"year":"2020","papers":23},{"year":"2021","papers":12},{"year":"2022","papers":4},{"year":"2023","papers":1},{"year":"2024","papers":6},{"year":"2025","papers":2}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/stylegan2"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}