{"url":"/dataset/ffhq","name":"FFHQ","full_name":"Flickr-Faces-HQ","description_markdown":"**Flickr-Faces-HQ (FFHQ)** consists of 70,000 high-quality PNG images at 1024×1024 resolution and contains considerable variation in terms of age, ethnicity and image background. It also has good coverage of accessories such as eyeglasses, sunglasses, hats, etc. The images were crawled from Flickr, thus inheriting all the biases of that website, and automatically aligned and cropped using dlib. Only images under permissive licenses were collected. Various automatic filters were used to prune the set, and finally Amazon Mechanical Turk was used to remove the occasional statues, paintings, or photos of photos.\r\n\r\nSource: [Flickr-Faces-HQ Dataset (FFHQ)](https://github.com/NVlabs/ffhq-dataset)\r\nImage Source: [https://github.com/NVlabs/ffhq-dataset](https://github.com/NVlabs/ffhq-dataset)","description_withheld":null,"homepage":"https://github.com/NVlabs/ffhq-dataset","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-style-based-generator-architecture-for","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","first_author":"Tero Karras","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://github.com/NVlabs/ffhq-dataset/blob/master/LICENSE.txt"},"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Generation","url":"/task/image-generation","datasets_with_task":"/datasets/task/image-generation"},{"name":"Image Super-Resolution","url":"/task/image-super-resolution","datasets_with_task":"/datasets/task/image-super-resolution"},{"name":"Image Denoising","url":"/task/image-denoising","datasets_with_task":"/datasets/task/image-denoising"},{"name":"Image Inpainting","url":"/task/image-inpainting","datasets_with_task":"/datasets/task/image-inpainting"},{"name":"Facial Inpainting","url":"/task/facial-inpainting","datasets_with_task":"/datasets/task/facial-inpainting"},{"name":"3D-Aware Image Synthesis","url":"/task/3d-aware-image-synthesis","datasets_with_task":"/datasets/task/3d-aware-image-synthesis"},{"name":"Face Hallucination","url":"/task/face-hallucination","datasets_with_task":"/datasets/task/face-hallucination"}],"languages":[],"variants":["FFHQ 64x64 - 4x upscaling","FFHQ 512 x 512","FFHQ-U","FFHQ 512 x 512 - 4x upscaling","FFHQ 512 x 512 - 16x upscaling","FFHQ 256 x 256 - 4x upscaling","FFHQ 256 x 256","FFHQ 1024 x 1024 - 4x upscaling","FFHQ 1024 x 1024","FFHQ"],"data_loaders":[{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/ffhq-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/NVlabs/ffhq-dataset","url":"https://github.com/NVlabs/ffhq-dataset","frameworks":[]}],"num_papers_in_archive":1468,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","task":"Image Generation","dataset_variant":"FFHQ 256 x 256","rows":51,"metrics":["FID","FD","Precision","Recall","bits/dimension","Density","Coverage"],"first_row_in_archive_order":{"model":"StyleSAN-XL","paper":"/paper/adversarially-slicing-generative-networks","metrics":{"FID":"1.68"},"code_links":[{"title":"sony/san","url":"https://github.com/sony/san"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-ffhq-1024-x-1024","task":"Image Generation","dataset_variant":"FFHQ 1024 x 1024","rows":20,"metrics":["FID","bits/dimension"],"first_row_in_archive_order":{"model":"StyleSAN-XL","paper":"/paper/adversarially-slicing-generative-networks","metrics":{"FID":"1.61"},"code_links":[{"title":"sony/san","url":"https://github.com/sony/san"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-ffhq-u","task":"Image Generation","dataset_variant":"FFHQ-U","rows":13,"metrics":["FID","EQ-T","EQ-R"],"first_row_in_archive_order":{"model":"Alias-Free-R","paper":"/paper/alias-free-generative-adversarial-networks","metrics":{"EQ-R":"47.64","EQ-T":" 64.78","FID":"3.66"},"code_links":[{"title":"NVlabs/stylegan3","url":"https://github.com/NVlabs/stylegan3"},{"title":"rosinality/alias-free-gan-pytorch","url":"https://github.com/rosinality/alias-free-gan-pytorch"},{"title":"kunheek/style-aware-discriminator","url":"https://github.com/kunheek/style-aware-discriminator"},{"title":"jychoi118/toward_spatial_unbiased","url":"https://github.com/jychoi118/toward_spatial_unbiased"},{"title":"duskvirkus/alias-free-gan-pytorch-lightning","url":"https://github.com/duskvirkus/alias-free-gan-pytorch-lightning"},{"title":"duskvirkus/alias-free-gan","url":"https://github.com/duskvirkus/alias-free-gan"},{"title":"lzhbrian/alias-free-gan-explanation","url":"https://github.com/lzhbrian/alias-free-gan-explanation"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-ffhq","task":"Image Generation","dataset_variant":"FFHQ","rows":12,"metrics":["FID","Clean-FID (70k)","FID-10k-training-steps"],"first_row_in_archive_order":{"model":"Anycost GAN","paper":"/paper/anycost-gans-for-interactive-image-synthesis","metrics":{"FID":"2.77"},"code_links":[{"title":"mit-han-lab/anycost-gan","url":"https://github.com/mit-han-lab/anycost-gan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-ffhq-256-x-256-4x","task":"Image Super-Resolution","dataset_variant":"FFHQ 256 x 256 - 4x upscaling","rows":11,"metrics":["FID","MS-SSIM","PSNR","SSIM"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper":"/paper/hifacegan-face-renovation-via-collaborative","metrics":{"FID":"5.36","MS-SSIM":"0.971","PSNR":"28.65","SSIM":"0.816"},"code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-ffhq-1024-x-1024-4x","task":"Image Super-Resolution","dataset_variant":"FFHQ 1024 x 1024 - 4x upscaling","rows":9,"metrics":["FID","MS-SSIM","PSNR","SSIM"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper":"/paper/hifacegan-face-renovation-via-collaborative","metrics":{"FID":"1.978","MS-SSIM":"0.975","PSNR":"33.04","SSIM":"0.875"},"code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-super-resolution-on-ffhq-512-x-512-4x","task":"Image Super-Resolution","dataset_variant":"FFHQ 512 x 512 - 4x upscaling","rows":8,"metrics":["PSNR","SSIM","MS-SSIM","LLE","FED","FID","LPIPS","NIQE"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper":"/paper/hifacegan-face-renovation-via-collaborative","metrics":{"FED":"0.0716","FID":"1.898","LLE":"2.071","LPIPS":"0.0723","MS-SSIM":"0.971","NIQE":"6.961","PSNR":"30.824","SSIM":"0.838"},"code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-aware-image-synthesis-on-ffhq-256-x-256","task":"3D-Aware Image Synthesis","dataset_variant":"FFHQ 256 x 256","rows":4,"metrics":["FID","KID"],"first_row_in_archive_order":{"model":"CIPS-3D","paper":"/paper/cips-3d-a-3d-aware-generator-of-gans-based-on","metrics":{"FID":"6.97","KID":"2.87"},"code_links":[{"title":"PeterouZh/CIPS-3D","url":"https://github.com/PeterouZh/CIPS-3D"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/face-hallucination-on-ffhq-512-x-512-16x","task":"Face Hallucination","dataset_variant":"FFHQ 512 x 512 - 16x upscaling","rows":4,"metrics":["FID","LPIPS","NIQE"],"first_row_in_archive_order":{"model":"HiFaceGAN","paper":"/paper/hifacegan-face-renovation-via-collaborative","metrics":{"FID":"11.389","LPIPS":"0.2449","NIQE":"6.767"},"code_links":[{"title":"Lotayou/Face-Renovation","url":"https://github.com/Lotayou/Face-Renovation"},{"title":"2023-MindSpore-4/Code-5","url":"https://github.com/2023-MindSpore-4/Code-5/tree/main/HiFaceGAN"},{"title":"Mind23-2/MindCode-3","url":"https://github.com/Mind23-2/MindCode-3/tree/main/HiFaceGAN"},{"title":"2023-MindSpore-1/ms-code-214","url":"https://github.com/2023-MindSpore-1/ms-code-214/tree/main/HiFaceGAN"},{"title":"MindSpore-paper-code-3/code4","url":"https://github.com/MindSpore-paper-code-3/code4/tree/main/HiFaceGAN"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-ffhq-512-x-512","task":"Image Generation","dataset_variant":"FFHQ 512 x 512","rows":3,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleSAN-XL","paper":"/paper/adversarially-slicing-generative-networks","metrics":{"FID":"1.77"},"code_links":[{"title":"sony/san","url":"https://github.com/sony/san"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-inpainting-on-ffhq-512-x-512","task":"Image Inpainting","dataset_variant":"FFHQ 512 x 512","rows":3,"metrics":["FID","P-IDS","U-IDS"],"first_row_in_archive_order":{"model":"SH-GAN","paper":"/paper/image-completion-with-heterogeneously","metrics":{"FID":"3.4"},"code_links":[{"title":"shi-labs/sh-gan","url":"https://github.com/shi-labs/sh-gan"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-inpainting-on-ffhq-1024-x-1024","task":"Image Inpainting","dataset_variant":"FFHQ 1024 x 1024","rows":2,"metrics":["LPIPS","RMSE","PSNR","SSIM"],"first_row_in_archive_order":{"model":"BRGM","paper":"/paper/bayesian-image-reconstruction-using-deep","metrics":{"LPIPS":"0.19","PSNR":"21.33","RMSE":"24.28","SSIM":"0.84"},"code_links":[{"title":"razvanmarinescu/brgm","url":"https://github.com/razvanmarinescu/brgm"},{"title":"razvanmarinescu/brgm-pytorch","url":"https://github.com/razvanmarinescu/brgm-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-aware-image-synthesis-on-ffhq-512-x-512-4x","task":"3D-Aware Image Synthesis","dataset_variant":"FFHQ 512 x 512 - 4x upscaling","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"IDE-3D","paper":"/paper/ide-3d-interactive-disentangled-editing-for","metrics":{"FID":"4.6"},"code_links":[{"title":"mrtornado24/ide-3d","url":"https://github.com/mrtornado24/ide-3d"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/facial-inpainting-on-ffhq","task":"Facial Inpainting","dataset_variant":"FFHQ","rows":1,"metrics":[" SSIM","LPIPS","PSNR"],"first_row_in_archive_order":{"model":"DMFN","paper":"/paper/image-fine-grained-inpainting","metrics":{" SSIM":"0.8985","LPIPS":"0.0457","PSNR":"26.49"},"code_links":[{"title":"Zheng222/DMFN","url":"https://github.com/Zheng222/DMFN"},{"title":"HannH/DMFN","url":"https://github.com/HannH/DMFN"},{"title":"Oorgien/Scene-Inpainting","url":"https://github.com/Oorgien/Scene-Inpainting"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-denoising-on-ffhq","task":"Image Denoising","dataset_variant":"FFHQ","rows":1,"metrics":["LPIPS"],"first_row_in_archive_order":{"model":"BRGM","paper":"/paper/bayesian-image-reconstruction-using-deep","metrics":{"LPIPS":"0.24"},"code_links":[{"title":"razvanmarinescu/brgm","url":"https://github.com/razvanmarinescu/brgm"},{"title":"razvanmarinescu/brgm-pytorch","url":"https://github.com/razvanmarinescu/brgm-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-denoising-on-ffhq-64x64-4x-upscaling","task":"Image Denoising","dataset_variant":"FFHQ 64x64 - 4x upscaling","rows":1,"metrics":["LPIPS"],"first_row_in_archive_order":{"model":"BRGM","paper":"/paper/bayesian-image-reconstruction-using-deep","metrics":{"LPIPS":"0.24"},"code_links":[{"title":"razvanmarinescu/brgm","url":"https://github.com/razvanmarinescu/brgm"},{"title":"razvanmarinescu/brgm-pytorch","url":"https://github.com/razvanmarinescu/brgm-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-generation-on-ffhq-64x64-4x-upscaling","task":"Image Generation","dataset_variant":"FFHQ 64x64 - 4x upscaling","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"PFGM++","paper":"/paper/pfgm-unlocking-the-potential-of-physics","metrics":{"FID":"2.43"},"code_links":[{"title":"newbeeer/pfgmpp","url":"https://github.com/newbeeer/pfgmpp"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"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","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":11,"samples_ran":9,"samples_unverified":2,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/clr-gan-improving-gans-stability-and-quality","title":"CLR-GAN: Improving GANs Stability and Quality via Consistent Latent Representation and Reconstruction","date":"2024-09-30","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/compensation-sampling-for-improved","title":"Compensation Sampling for Improved Convergence in Diffusion Models","date":"2023-12-11","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/flow-matching-in-latent-space","title":"Flow Matching in Latent Space","date":"2023-07-17","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/exposing-flaws-of-generative-model-evaluation-1","title":"Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models","date":"2023-06-07","rows_on_this_dataset":9,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":63,"samples_ran":30,"samples_unverified":33,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/polynomial-implicit-neural-representations","title":"Polynomial Implicit Neural Representations For Large Diverse Datasets","date":"2023-03-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/pfgm-unlocking-the-potential-of-physics","title":"PFGM++: Unlocking the Potential of Physics-Inspired Generative Models","date":"2023-02-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/adversarially-slicing-generative-networks","title":"SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer","date":"2023-01-30","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/stylenat-giving-each-head-a-new-perspective","title":"StyleNAT: Giving Each Head a New Perspective","date":"2022-11-10","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-completion-with-heterogeneously","title":"Image Completion with Heterogeneously Filtered Spectral Hints","date":"2022-11-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/diffusion-gan-training-gans-with-diffusion","title":"Diffusion-GAN: Training GANs with Diffusion","date":"2022-06-05","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":18,"samples_ran":14,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/ide-3d-interactive-disentangled-editing-for","title":"IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis","date":"2022-05-31","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/efficient-vdvae-less-is-more","title":"Efficient-VDVAE: Less is more","date":"2022-03-25","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/polarity-sampling-quality-and-diversity","title":"Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values","date":"2022-03-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/stylegan-xl-scaling-stylegan-to-large-diverse","title":"StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasets","date":"2022-02-01","rows_on_this_dataset":4,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":19,"samples_ran":14,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/styleswin-transformer-based-gan-for-high-1","title":"StyleSwin: Transformer-based GAN for High-resolution Image Generation","date":"2021-12-20","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":5,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/compositional-transformers-for-scene-1","title":"Compositional Transformers for Scene Generation","date":"2021-12-01","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/unleashing-transformers-parallel-token","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","date":"2021-11-24","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/projected-gans-converge-faster","title":"Projected GANs Converge Faster","date":"2021-11-01","rows_on_this_dataset":1,"code_links":3,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":49,"samples_ran":38,"samples_unverified":11,"pointer_only_for_licence":6,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/cips-3d-a-3d-aware-generator-of-gans-based-on","title":"CIPS-3D: A 3D-Aware Generator of GANs Based on Conditionally-Independent Pixel Synthesis","date":"2021-10-19","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":10,"samples_ran":6,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/magnet-uniform-sampling-from-deep-generative-1","title":"MaGNET: Uniform Sampling from Deep Generative Network Manifolds Without Retraining","date":"2021-10-15","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/alias-free-generative-adversarial-networks","title":"Alias-Free Generative Adversarial Networks","date":"2021-06-23","rows_on_this_dataset":15,"code_links":7,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":31,"samples_ran":25,"samples_unverified":6,"pointer_only_for_licence":9,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-transformer-for-high-resolution-gans","title":"Improved Transformer for High-Resolution GANs","date":"2021-06-14","rows_on_this_dataset":5,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/score-matching-model-for-unbounded-data-score-1","title":"Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation","date":"2021-06-10","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":12,"samples_ran":4,"samples_unverified":8,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/data-efficient-instance-generation-from","title":"Data-Efficient Instance Generation from Instance Discrimination","date":"2021-06-08","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":1,"samples_unverified":0,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/gotta-go-fast-when-generating-data-with-score","title":"Gotta Go Fast When Generating Data with Score-Based Models","date":"2021-05-28","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/regularizing-generative-adversarial-networks","title":"Regularizing Generative Adversarial Networks under Limited Data","date":"2021-04-07","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":8,"samples_unverified":1,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tfill-image-completion-via-a-transformer","title":"Bridging Global Context Interactions for High-Fidelity Image Completion","date":"2021-04-02","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/large-scale-image-completion-via-co-modulated-1","title":"Large Scale Image Completion via Co-Modulated Generative Adversarial Networks","date":"2021-03-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/anycost-gans-for-interactive-image-synthesis","title":"Anycost GANs for Interactive Image Synthesis and Editing","date":"2021-03-04","rows_on_this_dataset":3,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/generative-adversarial-transformers","title":"Generative Adversarial Transformers","date":"2021-03-01","rows_on_this_dataset":6,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":5,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/swagan-a-style-based-wavelet-driven","title":"SWAGAN: A Style-based Wavelet-driven Generative Model","date":"2021-02-11","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/taming-transformers-for-high-resolution-image","title":"Taming Transformers for High-Resolution Image Synthesis","date":"2020-12-17","rows_on_this_dataset":1,"code_links":13,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":6,"samples_ran":6,"samples_unverified":0,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/bayesian-image-reconstruction-using-deep","title":"Bayesian Image Reconstruction using Deep Generative Models","date":"2020-12-08","rows_on_this_dataset":5,"code_links":2,"syntology":null},{"paper":"/paper/image-generators-with-conditionally","title":"Image Generators with Conditionally-Independent Pixel Synthesis","date":"2020-11-27","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/adversarial-generation-of-continuous-images","title":"Adversarial Generation of Continuous Images","date":"2020-11-24","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/very-deep-vaes-generalize-autoregressive-1","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","date":"2020-11-20","rows_on_this_dataset":2,"code_links":8,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":9,"samples_ran":8,"samples_unverified":1,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/nvae-a-deep-hierarchical-variational","title":"NVAE: A Deep Hierarchical Variational Autoencoder","date":"2020-07-08","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":41,"samples_ran":26,"samples_unverified":15,"pointer_only_for_licence":23,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/training-generative-adversarial-networks-with-2","title":"Training Generative Adversarial Networks with Limited Data","date":"2020-06-11","rows_on_this_dataset":3,"code_links":28,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":29,"samples_ran":19,"samples_unverified":10,"pointer_only_for_licence":4,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/hifacegan-face-renovation-via-collaborative","title":"HiFaceGAN: Face Renovation via Collaborative Suppression and Replenishment","date":"2020-05-11","rows_on_this_dataset":4,"code_links":5,"syntology":null},{"paper":"/paper/adversarial-latent-autoencoders","title":"Adversarial Latent Autoencoders","date":"2020-04-09","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/feature-quantization-improves-gan-training","title":"Feature Quantization Improves GAN Training","date":"2020-04-05","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":3,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/pulse-self-supervised-photo-upsampling-via","title":"PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models","date":"2020-03-08","rows_on_this_dataset":1,"code_links":16,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":3,"samples_ran":1,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-u-net-based-discriminator-for-generative","title":"A U-Net Based Discriminator for Generative Adversarial Networks","date":"2020-02-28","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/image-fine-grained-inpainting","title":"Image Fine-grained Inpainting","date":"2020-02-07","rows_on_this_dataset":1,"code_links":3,"syntology":null},{"paper":"/paper/analyzing-and-improving-the-image-quality-of","title":"Analyzing and Improving the Image Quality of StyleGAN","date":"2019-12-03","rows_on_this_dataset":2,"code_links":126,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":92,"samples_ran":60,"samples_unverified":32,"pointer_only_for_licence":18,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/component-attention-guided-face-super","title":"Component Attention Guided Face Super-Resolution Network: CAGFace","date":"2019-10-19","rows_on_this_dataset":2,"code_links":1,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/improved-precision-and-recall-metric-for","title":"Improved Precision and Recall Metric for Assessing Generative Models","date":"2019-04-15","rows_on_this_dataset":1,"code_links":10,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":42,"samples_ran":30,"samples_unverified":12,"pointer_only_for_licence":25,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/feedback-network-for-image-super-resolution","title":"Feedback Network for Image Super-Resolution","date":"2019-03-23","rows_on_this_dataset":3,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":7,"samples_ran":2,"samples_unverified":5,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/msg-gan-multi-scale-gradients-gan-for-more","title":"MSG-GAN: Multi-Scale Gradients for Generative Adversarial Networks","date":"2019-03-14","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":15,"samples_ran":14,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/a-style-based-generator-architecture-for","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","date":"2018-12-12","rows_on_this_dataset":2,"code_links":83,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":396,"samples_ran":229,"samples_unverified":167,"pointer_only_for_licence":229,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/esrgan-enhanced-super-resolution-generative","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","date":"2018-09-01","rows_on_this_dataset":4,"code_links":46,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":44,"samples_ran":12,"samples_unverified":32,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/super-fan-integrated-facial-landmark","title":"Super-FAN: Integrated facial landmark localization and super-resolution of real-world low resolution faces in arbitrary poses with GANs","date":"2017-12-07","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/wavelet-srnet-a-wavelet-based-cnn-for-multi","title":"Wavelet-SRNet: A Wavelet-Based CNN for Multi-Scale Face Super Resolution","date":"2017-10-01","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/enhanced-deep-residual-networks-for-single","title":"Enhanced Deep Residual Networks for Single Image Super-Resolution","date":"2017-07-10","rows_on_this_dataset":3,"code_links":45,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":4,"samples_ran":4,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/enhancenet-single-image-super-resolution","title":"EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis","date":"2016-12-23","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":5,"samples_ran":0,"samples_unverified":5,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/photo-realistic-single-image-super-resolution","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","date":"2016-09-15","rows_on_this_dataset":3,"code_links":140,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":72,"samples_ran":21,"samples_unverified":51,"pointer_only_for_licence":11,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/accelerating-the-super-resolution","title":"Accelerating the Super-Resolution Convolutional Neural Network","date":"2016-08-01","rows_on_this_dataset":2,"code_links":16,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":15,"samples_ran":1,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/image-super-resolution-using-deep","title":"Image Super-Resolution Using Deep Convolutional Networks","date":"2014-12-31","rows_on_this_dataset":2,"code_links":60,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":27,"samples_ran":7,"samples_unverified":20,"pointer_only_for_licence":7,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":39,"samples_harvested":1067,"samples_ran":620,"samples_unverified":447,"pointer_only_for_licence":379,"papers_with_no_sample_that_ran":2,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}