{"url":"/sota/image-generation-on-ffhq-256-x-256","task":{"name":"Image Generation","url":"/task/image-generation","note":null},"dataset":{"name":"FFHQ 256 x 256","url":"/dataset/ffhq"},"category":"Computer Vision","categories":["Computer Vision","Medical","Miscellaneous","Natural Language Processing"],"category_note":null,"description":"**Image Generation** (synthesis) is the task of generating new images from an existing dataset.\r\n\r\n- **Unconditional generation** refers to generating samples unconditionally from the dataset, i.e. $p(y)$\r\n- **[Conditional image generation](/task/conditional-image-generation)** (subtask) refers to generating samples conditionally from the dataset, based on a label, i.e. $p(y|x)$.\r\n\r\nIn this section, you can find state-of-the-art leaderboards for **unconditional generation**. For conditional  generation, and other types of image generations, refer to the subtasks.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [StyleGAN](https://github.com/NVlabs/stylegan) )</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["FID","FD","Precision","Recall","bits/dimension","Density","Coverage"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FID":"lower","FD":null,"Precision":"higher","Recall":"higher","bits/dimension":null,"Density":null,"Coverage":null}},"counts":{"rows":51,"rows_with_code":48,"rows_with_paper_page":48,"rows_dated":48,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"StyleSAN-XL","metrics":{"FID":"1.68"},"uses_additional_data":false,"paper_date":"2023-01-30","paper":"/paper/adversarially-slicing-generative-networks","paper_url":"https://arxiv.org/abs/2301.12811v4","paper_title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","code":"https://github.com/sony/san","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":2,"model":"StyleNAT","metrics":{"FID":"2.05"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/stylenat-giving-each-head-a-new-perspective","paper_url":"https://arxiv.org/abs/2211.05770v2","paper_title":"StyleNAT: Giving Each Head a New Perspective","code":"https://github.com/SHI-Labs/Neighborhood-Attention-Transformer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"StyleNAT (Exposing)","metrics":{"Coverage":"0.71","Density":"0.77","FD":"229.42","FID":"2.11","Precision":"0.79","Recall":"0.41"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":4,"model":"StyleGAN-XL","metrics":{"FID":"2.19"},"uses_additional_data":false,"paper_date":"2022-02-01","paper":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse","paper_url":"https://arxiv.org/abs/2202.00273v2","paper_title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","code":"https://github.com/autonomousvision/stylegan-xl","n_code_links":2,"syntology":{"n_ran":14,"n_unverified":5,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"StyleGAN-XL (Exposing)","metrics":{"Coverage":"0.63","Density":"0.68","FD":"240.07","FID":"2.26","Precision":"0.77","Recall":"0.43"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"PDM+CS","metrics":{"FID":"2.57"},"uses_additional_data":false,"paper_date":"2023-12-11","paper":"/paper/compensation-sampling-for-improved","paper_url":"https://arxiv.org/abs/2312.06285v1","paper_title":"Compensation Sampling for Improved Convergence in Diffusion Models","code":"https://github.com/hotfinda/Compensation-sampling","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"HiT-L","metrics":{"FID":"2.58"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/improved-transformer-for-high-resolution-gans","paper_url":"https://arxiv.org/abs/2106.07631v3","paper_title":"Improved Transformer for High-Resolution GANs","code":"https://github.com/google-research/hit-gan","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"Poly-INR","metrics":{"FID":"2.72"},"uses_additional_data":false,"paper_date":"2023-03-20","paper":"/paper/polynomial-implicit-neural-representations","paper_url":"https://arxiv.org/abs/2303.11424v1","paper_title":"Polynomial Implicit Neural Representations For Large Diverse Datasets","code":"https://github.com/rajhans0/poly_inr","n_code_links":1,"syntology":null},{"rank_in_archive_order":9,"model":"R3GAN","metrics":{"FID":"2.75"},"uses_additional_data":false,"paper_date":"2025-01-09","paper":"/paper/the-gan-is-dead-long-live-the-gan-a-modern","paper_url":"https://arxiv.org/abs/2501.05441v1","paper_title":"The GAN is dead; long live the GAN! A Modern GAN Baseline","code":"https://github.com/brownvc/r3gan","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":10,"model":"StyleSwin","metrics":{"FID":"2.81"},"uses_additional_data":false,"paper_date":"2021-12-20","paper":"/paper/styleswin-transformer-based-gan-for-high-1","paper_url":"https://arxiv.org/abs/2112.10762v2","paper_title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","code":"https://github.com/microsoft/StyleSwin","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":11,"model":"StyleSwin (Exposing)","metrics":{"Coverage":"0.64","Density":"0.71","FD":"303.21","FID":"2.89","Precision":"0.79","Recall":"0.28"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":12,"model":"HiT-B","metrics":{"FID":"2.95"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/improved-transformer-for-high-resolution-gans","paper_url":"https://arxiv.org/abs/2106.07631v3","paper_title":"Improved Transformer for High-Resolution GANs","code":"https://github.com/google-research/hit-gan","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"HiT-S","metrics":{"FID":"3.06"},"uses_additional_data":false,"paper_date":"2021-06-14","paper":"/paper/improved-transformer-for-high-resolution-gans","paper_url":"https://arxiv.org/abs/2106.07631v3","paper_title":"Improved Transformer for High-Resolution GANs","code":"https://github.com/google-research/hit-gan","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"InsGen","metrics":{"FID":"3.31"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/data-efficient-instance-generation-from","paper_url":"https://arxiv.org/abs/2106.04566v1","paper_title":"Data-Efficient Instance Generation from Instance Discrimination","code":"https://github.com/genforce/insgen","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":15,"model":"Anycost GAN","metrics":{"FID":"3.35"},"uses_additional_data":false,"paper_date":"2021-03-04","paper":"/paper/anycost-gans-for-interactive-image-synthesis","paper_url":"https://arxiv.org/abs/2103.03243v1","paper_title":"Anycost GANs for Interactive Image Synthesis and Editing","code":"https://github.com/mit-han-lab/anycost-gan","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":16,"model":"CLR-GAN","metrics":{"FID":"3.37","Precision":"0.71","Recall":"0.44"},"uses_additional_data":false,"paper_date":"2024-09-30","paper":"/paper/clr-gan-improving-gans-stability-and-quality","paper_url":"https://link.springer.com/chapter/10.1007/978-3-031-73232-4_12","paper_title":"CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction","code":"https://github.com/Petecheco/CLR-GAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":17,"model":"Projected-GAN (Official)","metrics":{"FID":"3.39","Precision":"0.654","Recall":"0.464"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/projected-gans-converge-faster","paper_url":"https://arxiv.org/abs/2111.01007v1","paper_title":"Projected GANs Converge Faster","code":"https://github.com/autonomousvision/projected_gan","n_code_links":3,"syntology":{"n_ran":38,"n_unverified":11,"n_samples":49,"n_pointer_only_licence":6}},{"rank_in_archive_order":18,"model":"InsGen (Exposing)","metrics":{"Coverage":"0.51","FD":"436.26","FID":"3.46","Precision":"0.64","Recall":"0.13"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":19,"model":"LeCAM (StyleGAN2 + ADA)","metrics":{"FID":"3.49"},"uses_additional_data":false,"paper_date":"2021-04-07","paper":"/paper/regularizing-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/2104.03310v1","paper_title":"Regularizing Generative Adversarial Networks under Limited Data","code":"https://github.com/google/lecam-gan","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":6,"n_samples":9,"n_pointer_only_licence":3}},{"rank_in_archive_order":20,"model":"StyleGAN2 + ADA","metrics":{"FID":"3.62"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/training-generative-adversarial-networks-with-2","paper_url":"https://arxiv.org/abs/2006.06676v2","paper_title":"Training Generative Adversarial Networks with Limited Data","code":"https://github.com/NVlabs/stylegan2-ada-pytorch","n_code_links":28,"syntology":{"n_ran":5,"n_unverified":24,"n_samples":29,"n_pointer_only_licence":4}},{"rank_in_archive_order":21,"model":"Projected-GAN (Exposing)","metrics":{"Coverage":"0.30","Density":"0.31","FD":"589.20","FID":"4.29","Precision":"0.57","Recall":"0.07"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":22,"model":"CIPS","metrics":{"FID":"4.38"},"uses_additional_data":false,"paper_date":"2020-11-27","paper":"/paper/image-generators-with-conditionally","paper_url":"https://arxiv.org/abs/2011.13775v1","paper_title":"Image Generators with Conditionally-Independent Pixel Synthesis","code":"https://github.com/saic-mdal/CIPS","n_code_links":2,"syntology":null},{"rank_in_archive_order":23,"model":"LFM","metrics":{"FID":"4.55"},"uses_additional_data":false,"paper_date":"2023-07-17","paper":"/paper/flow-matching-in-latent-space","paper_url":"https://arxiv.org/abs/2307.08698v1","paper_title":"Flow Matching in Latent Space","code":"https://github.com/vinairesearch/lfm","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":24,"model":"INR-GAN-bil","metrics":{"FID":"4.95"},"uses_additional_data":false,"paper_date":"2020-11-24","paper":"/paper/adversarial-generation-of-continuous-images","paper_url":"https://arxiv.org/abs/2011.12026v2","paper_title":"Adversarial Generation of Continuous Images","code":"https://github.com/universome/inr-gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":25,"model":"SWAGAN-Bi","metrics":{"FID":"5.22"},"uses_additional_data":false,"paper_date":"2021-02-11","paper":"/paper/swagan-a-style-based-wavelet-driven","paper_url":"https://arxiv.org/abs/2102.06108v1","paper_title":"SWAGAN: A Style-based Wavelet-driven Generative Model","code":"https://github.com/rinongal/swagan","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":26,"model":"StyleGAN2-ada (Exposing)","metrics":{"Coverage":"0.39","Density":"0.36","FD":"514.78","FID":"5.30","Precision":"0.59","Recall":"0.06"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":27,"model":"UDM (RVE) + ST","metrics":{"FID":"5.54"},"uses_additional_data":false,"paper_date":"2021-06-10","paper":"/paper/score-matching-model-for-unbounded-data-score-1","paper_url":"https://arxiv.org/abs/2106.05527v5","paper_title":"Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation","code":"https://github.com/Kim-Dongjun/Soft-Truncation","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":8,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":28,"model":"Unleashing Transformers","metrics":{"FID":"6.11"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/unleashing-transformers-parallel-token","paper_url":"https://arxiv.org/abs/2111.12701v1","paper_title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","code":"https://github.com/samb-t/unleashing-transformers","n_code_links":3,"syntology":null},{"rank_in_archive_order":29,"model":"GANFormer","metrics":{"FID":"7.42"},"uses_additional_data":false,"paper_date":"2021-03-01","paper":"/paper/generative-adversarial-transformers","paper_url":"https://arxiv.org/abs/2103.01209v4","paper_title":"Generative Adversarial Transformers","code":"https://github.com/dorarad/gansformer","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":1,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":30,"model":"U-Net GAN","metrics":{"FID":"7.48"},"uses_additional_data":false,"paper_date":"2020-02-28","paper":"/paper/a-u-net-based-discriminator-for-generative","paper_url":"https://arxiv.org/abs/2002.12655v2","paper_title":"A U-Net Based Discriminator for Generative Adversarial Networks","code":"https://github.com/boschresearch/unetgan","n_code_links":3,"syntology":null},{"rank_in_archive_order":31,"model":"GANFormer2","metrics":{"FID":"7.77"},"uses_additional_data":false,"paper_date":"2021-12-01","paper":"/paper/compositional-transformers-for-scene-1","paper_url":"http://proceedings.neurips.cc/paper/2021/hash/4eff0720836a198b6174eecf02cbfdbf-Abstract.html","paper_title":"Compositional Transformers for Scene Generation","code":"https://github.com/dorarad/gansformer","n_code_links":1,"syntology":null},{"rank_in_archive_order":32,"model":"LDM (Exposing)","metrics":{"Coverage":"0.74","Density":"0.83","FD":"226.72","FID":"8.11","Precision":"0.81","Recall":"0.44"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":33,"model":"LDM","metrics":{"FID":"8.11"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"Unleash-Trans (Exposing)","metrics":{"Coverage":"0.53","Density":"0.61","FD":"393.45","FID":"9.02","Precision":"0.76","Recall":"0.24"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":35,"model":"VQGAN+Transformer","metrics":{"FID":"9.6"},"uses_additional_data":false,"paper_date":"2020-12-17","paper":"/paper/taming-transformers-for-high-resolution-image","paper_url":"https://arxiv.org/abs/2012.09841v3","paper_title":"Taming Transformers for High-Resolution Image Synthesis","code":"https://github.com/CompVis/taming-transformers","n_code_links":13,"syntology":{"n_ran":6,"n_unverified":0,"n_samples":6,"n_pointer_only_licence":4}},{"rank_in_archive_order":36,"model":"BigGAN","metrics":{"FID":"11.48"},"uses_additional_data":false,"paper_date":"2020-02-28","paper":"/paper/a-u-net-based-discriminator-for-generative","paper_url":"https://arxiv.org/abs/2002.12655v2","paper_title":"A U-Net Based Discriminator for Generative Adversarial Networks","code":"https://github.com/boschresearch/unetgan","n_code_links":3,"syntology":null},{"rank_in_archive_order":37,"model":"VE (erel=0.01)","metrics":{"FID":"15.67"},"uses_additional_data":false,"paper_date":"2021-05-28","paper":"/paper/gotta-go-fast-when-generating-data-with-score","paper_url":"https://arxiv.org/abs/2105.14080v1","paper_title":"Gotta Go Fast When Generating Data with Score-Based Models","code":"https://github.com/AlexiaJM/score_sde_fast_sampling","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":38,"model":"VE (erel=0.02)","metrics":{"FID":"15.67"},"uses_additional_data":false,"paper_date":"2021-05-28","paper":"/paper/gotta-go-fast-when-generating-data-with-score","paper_url":"https://arxiv.org/abs/2105.14080v1","paper_title":"Gotta Go Fast When Generating Data with Score-Based Models","code":"https://github.com/AlexiaJM/score_sde_fast_sampling","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":39,"model":"Efficient-vdVAE (Exposing)","metrics":{"Coverage":"0.54","Density":"1.04","FD":"514.16","FID":"34.88","Precision":"0.86","Recall":"0.14"},"uses_additional_data":false,"paper_date":"2023-06-07","paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","paper_url":"https://arxiv.org/abs/2306.04675v2","paper_title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","code":"https://github.com/layer6ai-labs/dgm-eval","n_code_links":4,"syntology":{"n_ran":30,"n_unverified":33,"n_samples":63,"n_pointer_only_licence":1}},{"rank_in_archive_order":40,"model":"Efficient-VDVAE","metrics":{"FID":"34.88","bits/dimension":"0.53"},"uses_additional_data":false,"paper_date":"2022-03-25","paper":"/paper/efficient-vdvae-less-is-more","paper_url":"https://arxiv.org/abs/2203.13751v2","paper_title":"Efficient-VDVAE: Less is more","code":"https://github.com/Rayhane-mamah/Efficient-VDVAE","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"LDM (DINOv2)","metrics":{"FD":"112.40","Precision":"0.92","Recall":"0.76"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":42,"model":"StyleNAT (DINOv2)","metrics":{"FD":"229.72","Precision":"0.79","Recall":"0.41"},"uses_additional_data":false,"paper_date":"2022-11-10","paper":"/paper/stylenat-giving-each-head-a-new-perspective","paper_url":"https://arxiv.org/abs/2211.05770v2","paper_title":"StyleNAT: Giving Each Head a New Perspective","code":"https://github.com/SHI-Labs/Neighborhood-Attention-Transformer","n_code_links":2,"syntology":{"n_ran":0,"n_unverified":1,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":43,"model":"StyleGAN-XL (DINOv2)","metrics":{"FD":"240.07","Precision":"0.77","Recall":"0.43"},"uses_additional_data":false,"paper_date":"2022-02-01","paper":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse","paper_url":"https://arxiv.org/abs/2202.00273v2","paper_title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","code":"https://github.com/autonomousvision/stylegan-xl","n_code_links":2,"syntology":{"n_ran":14,"n_unverified":5,"n_samples":19,"n_pointer_only_licence":0}},{"rank_in_archive_order":44,"model":"StyleSwin (DINOv2)","metrics":{"FD":"300.18","Precision":"0.79","Recall":"0.28"},"uses_additional_data":false,"paper_date":"2021-12-20","paper":"/paper/styleswin-transformer-based-gan-for-high-1","paper_url":"https://arxiv.org/abs/2112.10762v2","paper_title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","code":"https://github.com/microsoft/StyleSwin","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":3}},{"rank_in_archive_order":45,"model":"Unleashing Transformers (DINOv2)","metrics":{"FD":"393.45","Precision":"0.76","Recall":"0.24"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/unleashing-transformers-parallel-token","paper_url":"https://arxiv.org/abs/2111.12701v1","paper_title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","code":"https://github.com/samb-t/unleashing-transformers","n_code_links":3,"syntology":null},{"rank_in_archive_order":46,"model":"InsGen (DINOv2)","metrics":{"FD":"436.26","Precision":"0.64","Recall":"0.13"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/data-efficient-instance-generation-from","paper_url":"https://arxiv.org/abs/2106.04566v1","paper_title":"Data-Efficient Instance Generation from Instance Discrimination","code":"https://github.com/genforce/insgen","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":47,"model":"Efficient-VDVAE (DINOv2)","metrics":{"FD":"514.16","Precision":"0.86","Recall":"0.14"},"uses_additional_data":false,"paper_date":"2022-03-25","paper":"/paper/efficient-vdvae-less-is-more","paper_url":"https://arxiv.org/abs/2203.13751v2","paper_title":"Efficient-VDVAE: Less is more","code":"https://github.com/Rayhane-mamah/Efficient-VDVAE","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"StyleGAN2 + ADA (DINOv2)","metrics":{"FD":"514.78","Precision":"0.59","Recall":"0.06"},"uses_additional_data":false,"paper_date":"2020-06-11","paper":"/paper/training-generative-adversarial-networks-with-2","paper_url":"https://arxiv.org/abs/2006.06676v2","paper_title":"Training Generative Adversarial Networks with Limited Data","code":"https://github.com/NVlabs/stylegan2-ada-pytorch","n_code_links":28,"syntology":{"n_ran":5,"n_unverified":24,"n_samples":29,"n_pointer_only_licence":4}},{"rank_in_archive_order":49,"model":"Projected-GAN (DINOv2)","metrics":{"FD":"592.26","Precision":"0.57","Recall":"0.07"},"uses_additional_data":false,"paper_date":null,"paper":null,"paper_url":null,"paper_title":"","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":50,"model":"Very Deep VAE","metrics":{"bits/dimension":"0.61"},"uses_additional_data":false,"paper_date":"2020-11-20","paper":"/paper/very-deep-vaes-generalize-autoregressive-1","paper_url":"https://arxiv.org/abs/2011.10650v2","paper_title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","code":"https://github.com/openai/vdvae","n_code_links":8,"syntology":{"n_ran":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":4}},{"rank_in_archive_order":51,"model":"NVAE w/ flow","metrics":{"bits/dimension":"0.69"},"uses_additional_data":false,"paper_date":"2020-07-08","paper":"/paper/nvae-a-deep-hierarchical-variational","paper_url":"https://arxiv.org/abs/2007.03898v3","paper_title":"NVAE: A Deep Hierarchical Variational Autoencoder","code":"https://github.com/NVlabs/NVAE","n_code_links":10,"syntology":{"n_ran":23,"n_unverified":18,"n_samples":41,"n_pointer_only_licence":23}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":36,"rows_with_any_sample_ran":33,"distinct_papers_with_graph_line":20,"distinct_papers_with_any_sample_ran":18,"samples_over_distinct_papers":{"n_ran":162,"n_unverified":113,"n_samples":275,"n_pointer_only_licence":69,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":435,"n_unverified":410,"n_samples":845,"n_pointer_only_licence":88,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}