{"url":"/sota/image-generation-on-cifar-10","task":{"name":"Image Generation","url":"/task/image-generation","note":null},"dataset":{"name":"CIFAR-10","url":"/dataset/cifar-10"},"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","IS","NFE"],"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","IS":null,"NFE":null}},"counts":{"rows":78,"rows_with_code":61,"rows_with_paper_page":74,"rows_dated":74,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"GMem","metrics":{"FID":"1.22"},"uses_additional_data":false,"paper_date":"2024-12-11","paper":"/paper/generative-modeling-with-explicit-memory","paper_url":"https://arxiv.org/abs/2412.08781v1","paper_title":"Generative Modeling with Explicit Memory","code":"https://github.com/lins-lab/gmem","n_code_links":1,"syntology":{"n_ran":8,"n_unverified":7,"n_samples":15,"n_pointer_only_licence":15}},{"rank_in_archive_order":2,"model":"EDM+DDO","metrics":{"FID":"1.30"},"uses_additional_data":false,"paper_date":"2025-03-03","paper":"/paper/direct-discriminative-optimization-your-1","paper_url":"https://arxiv.org/abs/2503.01103v2","paper_title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","code":"https://github.com/nvlabs/ddo","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"StyleSAN-XL","metrics":{"FID":"1.36"},"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":4,"model":"Uni-Instruct","metrics":{"FID":"1.38","NFE":"1"},"uses_additional_data":false,"paper_date":"2025-05-27","paper":"/paper/uni-instruct-one-step-diffusion-model-through","paper_url":"https://arxiv.org/abs/2505.20755","paper_title":"Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"SiDA-EDM","metrics":{"FID":"1.396","NFE":"1"},"uses_additional_data":false,"paper_date":"2024-10-19","paper":"/paper/adversarial-score-identity-distillation","paper_url":"https://arxiv.org/abs/2410.14919v4","paper_title":"Adversarial Score identity Distillation: Rapidly Surpassing the Teacher in One Step","code":"https://github.com/mingyuanzhou/sid","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":1}},{"rank_in_archive_order":6,"model":"PFGM++ +CS","metrics":{"FID":"1.50"},"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":"GDD-I","metrics":{"FID":"1.54","NFE":"1"},"uses_additional_data":false,"paper_date":"2024-05-31","paper":"/paper/diffusion-models-are-innate-one-step","paper_url":"https://arxiv.org/abs/2405.20750v2","paper_title":"Diffusion Models Are Innate One-Step Generators","code":"https://github.com/Zyriix/GDD","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"SiD","metrics":{"FID":"1.71","NFE":"1"},"uses_additional_data":false,"paper_date":"2024-04-05","paper":"/paper/score-identity-distillation-exponentially","paper_url":"https://arxiv.org/abs/2404.04057v3","paper_title":"Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation","code":"https://github.com/mingyuanzhou/sid","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":6,"n_samples":15,"n_pointer_only_licence":0}},{"rank_in_archive_order":9,"model":"PFGM++","metrics":{"FID":"1.74"},"uses_additional_data":false,"paper_date":"2023-02-08","paper":"/paper/pfgm-unlocking-the-potential-of-physics","paper_url":"https://arxiv.org/abs/2302.04265v2","paper_title":"PFGM++: Unlocking the Potential of Physics-Inspired Generative Models","code":"https://github.com/newbeeer/pfgmpp","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":10,"model":"SciRE-Solver (with EDM)","metrics":{"FID":"1.76"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/scire-solver-efficient-sampling-of-diffusion","paper_url":"https://arxiv.org/abs/2308.07896v3","paper_title":"SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":11,"model":"Discriminator Guidance (unconditional)","metrics":{"FID":"1.77"},"uses_additional_data":false,"paper_date":"2022-11-28","paper":"/paper/refining-generative-process-with","paper_url":"https://arxiv.org/abs/2211.17091v4","paper_title":"Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models","code":"https://github.com/alsdudrla10/DG","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":2}},{"rank_in_archive_order":12,"model":"EDM-ES","metrics":{"FID":"1.8"},"uses_additional_data":false,"paper_date":"2023-08-29","paper":"/paper/elucidating-the-exposure-bias-in-diffusion","paper_url":"https://arxiv.org/abs/2308.15321v6","paper_title":"Elucidating the Exposure Bias in Diffusion Models","code":"https://github.com/forever208/ddpm-ip","n_code_links":5,"syntology":{"n_ran":17,"n_unverified":2,"n_samples":19,"n_pointer_only_licence":16}},{"rank_in_archive_order":13,"model":"R3GAN","metrics":{"FID":"1.96"},"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":14,"model":"Inductive Moment Matching","metrics":{"FID":"1.98"},"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":15,"model":"TCM","metrics":{"FID":"2.05","NFE":"2"},"uses_additional_data":false,"paper_date":"2024-10-18","paper":"/paper/truncated-consistency-models","paper_url":"https://arxiv.org/abs/2410.14895v2","paper_title":"Truncated Consistency Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":16,"model":"ECT","metrics":{"FID":"2.11","NFE":"2"},"uses_additional_data":false,"paper_date":"2024-06-20","paper":"/paper/consistency-models-made-easy","paper_url":"https://arxiv.org/abs/2406.14548v2","paper_title":"Consistency Models Made Easy","code":"https://github.com/locuslab/ect","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":17,"model":"Subspace Diffusion (NSCN++)","metrics":{"FID":"2.17"},"uses_additional_data":false,"paper_date":"2022-05-03","paper":"/paper/subspace-diffusion-generative-models","paper_url":"https://arxiv.org/abs/2205.01490v2","paper_title":"Subspace Diffusion Generative Models","code":"https://github.com/bjing2016/subspace-diffusion","n_code_links":1,"syntology":{"n_ran":7,"n_unverified":5,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":18,"model":"Posterior Mean Matching","metrics":{"FID":"2.18"},"uses_additional_data":false,"paper_date":"2024-12-17","paper":"/paper/posterior-mean-matching-generative-modeling","paper_url":"https://arxiv.org/abs/2412.13286v2","paper_title":"Posterior Mean Matching: Generative Modeling through Online Bayesian Inference","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"VSDM","metrics":{"FID":"2.28"},"uses_additional_data":false,"paper_date":"2024-05-08","paper":"/paper/variational-schrodinger-diffusion-models","paper_url":"https://arxiv.org/abs/2405.04795v4","paper_title":"Variational Schrödinger Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":20,"model":"block flow","metrics":{"FID":"2.29"},"uses_additional_data":false,"paper_date":"2025-01-20","paper":"/paper/block-flow-learning-straight-flow-on-data","paper_url":"https://arxiv.org/abs/2501.11361v1","paper_title":"Block Flow: Learning Straight Flow on Data Blocks","code":"https://github.com/wpp13749/block_flow","n_code_links":1,"syntology":null},{"rank_in_archive_order":21,"model":"with Score-SDE","metrics":{"FID":"2.42 FID (20 NFE)"},"uses_additional_data":false,"paper_date":"2023-08-15","paper":"/paper/scire-solver-efficient-sampling-of-diffusion","paper_url":"https://arxiv.org/abs/2308.07896v3","paper_title":"SciRE-Solver: Accelerating Diffusion Models Sampling by Score-integrand Solver with Recursive Difference","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":22,"model":"PFGM","metrics":{"FID":"2.48"},"uses_additional_data":false,"paper_date":"2022-09-22","paper":"/paper/poisson-flow-generative-models","paper_url":"https://arxiv.org/abs/2209.11178v4","paper_title":"Poisson Flow Generative Models","code":"https://github.com/newbeeer/poisson_flow","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":23,"model":"PD (NFE=8)","metrics":{"FID":"2.57"},"uses_additional_data":false,"paper_date":"2022-02-01","paper":"/paper/progressive-distillation-for-fast-sampling-of-1","paper_url":"https://arxiv.org/abs/2202.00512v2","paper_title":"Progressive Distillation for Fast Sampling of Diffusion Models","code":"https://github.com/google-research/google-research/tree/master/diffusion_distillation","n_code_links":12,"syntology":{"n_ran":10,"n_unverified":17,"n_samples":27,"n_pointer_only_licence":10}},{"rank_in_archive_order":24,"model":"RDUOT","metrics":{"FID":"2.95"},"uses_additional_data":false,"paper_date":"2023-11-28","paper":"/paper/robust-diffusion-gan-using-semi-unbalanced","paper_url":"https://arxiv.org/abs/2311.17101v2","paper_title":"A High-Quality Robust Diffusion Framework for Corrupted Dataset","code":"https://github.com/VinAIResearch/RDUOT","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":7,"n_samples":12,"n_pointer_only_licence":0}},{"rank_in_archive_order":25,"model":"PD (NFE=4)","metrics":{"FID":"3.00"},"uses_additional_data":false,"paper_date":"2022-02-01","paper":"/paper/progressive-distillation-for-fast-sampling-of-1","paper_url":"https://arxiv.org/abs/2202.00512v2","paper_title":"Progressive Distillation for Fast Sampling of Diffusion Models","code":"https://github.com/google-research/google-research/tree/master/diffusion_distillation","n_code_links":12,"syntology":{"n_ran":10,"n_unverified":17,"n_samples":27,"n_pointer_only_licence":10}},{"rank_in_archive_order":26,"model":"SB-FBSDE","metrics":{"FID":"3.01"},"uses_additional_data":false,"paper_date":"2021-10-21","paper":"/paper/likelihood-training-of-schrodinger-bridge-1","paper_url":"https://arxiv.org/abs/2110.11291v5","paper_title":"Likelihood Training of Schrödinger Bridge using Forward-Backward SDEs Theory","code":"https://github.com/ghliu/sb-fbsde","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":2,"n_samples":11,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"DDPM","metrics":{"FID":"3.074"},"uses_additional_data":false,"paper_date":"2024-05-23","paper":"/paper/the-disappearance-of-timestep-embedding-in","paper_url":"https://arxiv.org/abs/2405.14126v1","paper_title":"The Disappearance of Timestep Embedding in Modern Time-Dependent Neural Networks","code":"https://github.com/kmbmjn/disappearance_of_timestep_embedding","n_code_links":1,"syntology":null},{"rank_in_archive_order":28,"model":"Denoising Diffusion","metrics":{"FID":"3.17"},"uses_additional_data":false,"paper_date":"2020-06-19","paper":"/paper/denoising-diffusion-probabilistic-models","paper_url":"https://arxiv.org/abs/2006.11239v2","paper_title":"Denoising Diffusion Probabilistic Models","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":70,"syntology":{"n_ran":186,"n_unverified":67,"n_samples":253,"n_pointer_only_licence":62}},{"rank_in_archive_order":29,"model":"MDM-Prime","metrics":{"FID":"3.26","IS":"9.67"},"uses_additional_data":false,"paper_date":"2025-05-24","paper":"/paper/beyond-masked-and-unmasked-discrete-diffusion","paper_url":"https://arxiv.org/abs/2505.18495v1","paper_title":"Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":30,"model":"LadaGAN","metrics":{"FID":"3.29"},"uses_additional_data":false,"paper_date":"2024-01-17","paper":"/paper/efficient-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/2401.09596v4","paper_title":"Efficient generative adversarial networks using linear additive-attention Transformers","code":"https://github.com/milmor/ladagan","n_code_links":2,"syntology":null},{"rank_in_archive_order":31,"model":"Blackout Diffusion","metrics":{"FID":"4.58"},"uses_additional_data":false,"paper_date":"2023-05-18","paper":"/paper/blackout-diffusion-generative-diffusion","paper_url":"https://arxiv.org/abs/2305.11089v1","paper_title":"Blackout Diffusion: Generative Diffusion Models in Discrete-State Spaces","code":"https://github.com/lanl/blackout-diffusion","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":4,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":32,"model":"DiffAugment-BigGAN","metrics":{"FID":"4.61"},"uses_additional_data":false,"paper_date":"2020-06-18","paper":"/paper/differentiable-augmentation-for-data","paper_url":"https://arxiv.org/abs/2006.10738v4","paper_title":"Differentiable Augmentation for Data-Efficient GAN Training","code":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN","n_code_links":13,"syntology":{"n_ran":49,"n_unverified":9,"n_samples":58,"n_pointer_only_licence":12}},{"rank_in_archive_order":33,"model":"MDM","metrics":{"FID":"4.66","IS":"9.09"},"uses_additional_data":false,"paper_date":"2025-05-24","paper":"/paper/beyond-masked-and-unmasked-discrete-diffusion","paper_url":"https://arxiv.org/abs/2505.18495v1","paper_title":"Beyond Masked and Unmasked: Discrete Diffusion Models via Partial Masking","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":34,"model":"FoD-ODE","metrics":{"FID":"5.01"},"uses_additional_data":false,"paper_date":"2025-05-22","paper":"/paper/forward-only-diffusion-probabilistic-models","paper_url":"https://arxiv.org/abs/2505.16733v1","paper_title":"Forward-only Diffusion Probabilistic Models","code":"https://github.com/Algolzw/FoD","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"CT (Direct Generation, NFE=2)","metrics":{"FID":"5.83"},"uses_additional_data":false,"paper_date":"2023-03-02","paper":"/paper/consistency-models","paper_url":"https://arxiv.org/abs/2303.01469v2","paper_title":"Consistency Models","code":"https://github.com/openai/consistency_models","n_code_links":15,"syntology":{"n_ran":29,"n_unverified":28,"n_samples":57,"n_pointer_only_licence":8}},{"rank_in_archive_order":36,"model":"GENIE (NFEs=10)","metrics":{"FID":"5.97"},"uses_additional_data":false,"paper_date":"2022-10-11","paper":"/paper/genie-higher-order-denoising-diffusion","paper_url":"https://arxiv.org/abs/2210.05475v1","paper_title":"GENIE: Higher-Order Denoising Diffusion Solvers","code":"https://github.com/nv-tlabs/GENIE","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"FM","metrics":{"FID":"6.35"},"uses_additional_data":false,"paper_date":"2022-10-06","paper":"/paper/flow-matching-for-generative-modeling","paper_url":"https://arxiv.org/abs/2210.02747v2","paper_title":"Flow Matching for Generative Modeling","code":"https://github.com/shivammehta25/Matcha-TTS","n_code_links":5,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":3}},{"rank_in_archive_order":38,"model":"ViTGAN","metrics":{"FID":"6.66"},"uses_additional_data":false,"paper_date":"2021-07-09","paper":"/paper/vitgan-training-gans-with-vision-transformers","paper_url":"https://arxiv.org/abs/2107.04589v2","paper_title":"ViTGAN: Training GANs with Vision Transformers","code":"https://github.com/lucidrains/parti-pytorch","n_code_links":3,"syntology":{"n_ran":16,"n_unverified":2,"n_samples":18,"n_pointer_only_licence":0}},{"rank_in_archive_order":39,"model":"LSGM (NLL)","metrics":{"FID":"6.89"},"uses_additional_data":false,"paper_date":"2021-06-10","paper":"/paper/score-based-generative-modeling-in-latent","paper_url":"https://arxiv.org/abs/2106.05931v3","paper_title":"Score-based Generative Modeling in Latent Space","code":"https://github.com/NVlabs/LSGM","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":3,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":40,"model":"MIX-BigGAN","metrics":{"FID":"8.17"},"uses_additional_data":false,"paper_date":"2020-07-13","paper":"/paper/lessons-learned-from-the-training-of-gans-on","paper_url":"https://arxiv.org/abs/2007.06418v2","paper_title":"Lessons Learned from the Training of GANs on Artificial Datasets","code":"https://github.com/tsc2017/MIX-GAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"LeCAM (BigGAN + DA)","metrics":{"FID":"8.46"},"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":8,"n_unverified":1,"n_samples":9,"n_pointer_only_licence":3}},{"rank_in_archive_order":42,"model":"CR +LT-BigGAN","metrics":{"FID":"9.80"},"uses_additional_data":false,"paper_date":"2020-10-19","paper":"/paper/lt-gan-self-supervised-gan-with-latent","paper_url":"https://arxiv.org/abs/2010.09893v1","paper_title":"LT-GAN: Self-Supervised GAN with Latent Transformation Detection","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":43,"model":"EAGAN (G+D)","metrics":{"FID":"9.91"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/eagan-efficient-two-stage-evolutionary","paper_url":"https://arxiv.org/abs/2111.15097v2","paper_title":"EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs","code":"https://github.com/marsggbo/EAGAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"EAGAN (G)","metrics":{"FID":"10.14"},"uses_additional_data":false,"paper_date":"2021-11-30","paper":"/paper/eagan-efficient-two-stage-evolutionary","paper_url":"https://arxiv.org/abs/2111.15097v2","paper_title":"EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs","code":"https://github.com/marsggbo/EAGAN","n_code_links":1,"syntology":null},{"rank_in_archive_order":45,"model":"PPOGAN","metrics":{"FID":"10.7"},"uses_additional_data":false,"paper_date":"2020-06-12","paper":"/paper/improving-gan-training-with-probability-ratio","paper_url":"https://arxiv.org/abs/2006.06900v4","paper_title":"Improving GAN Training with Probability Ratio Clipping and Sample Reweighting","code":"https://github.com/Holmeswww/PPOGAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":3,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"NCSNv2","metrics":{"FID":"10.87"},"uses_additional_data":false,"paper_date":"2020-06-16","paper":"/paper/improved-techniques-for-training-score-based","paper_url":"https://arxiv.org/abs/2006.09011v2","paper_title":"Improved Techniques for Training Score-Based Generative Models","code":"https://github.com/yang-song/score_sde_pytorch","n_code_links":9,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":47,"model":"SNGAN-DCD (Latent)","metrics":{"FID":"16.24"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/discriminator-contrastive-divergence-semi","paper_url":"https://arxiv.org/abs/2004.01704v1","paper_title":"Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator","code":"https://github.com/MinkaiXu/Discriminator-Contrastive-Divergence","n_code_links":1,"syntology":null},{"rank_in_archive_order":48,"model":"Pi-net","metrics":{"FID":"16.79"},"uses_additional_data":false,"paper_date":"2020-03-08","paper":"/paper/-nets-deep-polynomial-neural-networks","paper_url":"https://arxiv.org/abs/2003.03828v2","paper_title":"$Π-$nets: Deep Polynomial Neural Networks","code":"https://github.com/grigorisg9gr/polynomial_nets","n_code_links":2,"syntology":null},{"rank_in_archive_order":49,"model":"ProdPoly","metrics":{"FID":"16.79"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/deep-polynomial-neural-networks","paper_url":"https://arxiv.org/abs/2006.13026v2","paper_title":"Deep Polynomial Neural Networks","code":"https://github.com/Faceplugin-ltd/FaceRecognition-Android","n_code_links":5,"syntology":null},{"rank_in_archive_order":50,"model":"Dist-GAN","metrics":{"FID":"17.61"},"uses_additional_data":false,"paper_date":"2018-03-23","paper":"/paper/dist-gan-an-improved-gan-using-distance","paper_url":"http://arxiv.org/abs/1803.08887v3","paper_title":"Dist-GAN: An Improved GAN using Distance Constraints","code":"https://github.com/tntrung/gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":51,"model":"LOGAN","metrics":{"FID":"17.87"},"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":52,"model":"DC-VAE","metrics":{"FID":"17.9"},"uses_additional_data":false,"paper_date":"2020-11-19","paper":"/paper/dual-contradistinctive-generative-autoencoder-1","paper_url":"https://arxiv.org/abs/2011.10063v1","paper_title":"Dual Contradistinctive Generative Autoencoder","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":53,"model":"NK-CA","metrics":{"FID":"18.27"},"uses_additional_data":false,"paper_date":"2023-03-09","paper":"/paper/learning-stationary-markov-processes-with","paper_url":"https://arxiv.org/abs/2303.05497v2","paper_title":"Learning Stationary Markov Processes with Contrastive Adjustment","code":"https://github.com/ludvb/nkca","n_code_links":1,"syntology":null},{"rank_in_archive_order":54,"model":"CoProGAN","metrics":{"FID":"19.66"},"uses_additional_data":false,"paper_date":"2021-08-17","paper":"/paper/contextual-convolutional-neural-networks","paper_url":"https://arxiv.org/abs/2108.07387v1","paper_title":"Contextual Convolutional Neural Networks","code":"https://github.com/iduta/coconv","n_code_links":1,"syntology":null},{"rank_in_archive_order":55,"model":"SRN-GANs","metrics":{"FID":"19.83"},"uses_additional_data":false,"paper_date":"2019-06-11","paper":"/paper/stable-rank-normalization-for-improved","paper_url":"https://arxiv.org/abs/1906.04659v3","paper_title":"Stable Rank Normalization for Improved Generalization in Neural Networks and GANs","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":56,"model":"PeerGAN","metrics":{"FID":"21.55"},"uses_additional_data":false,"paper_date":"2021-01-19","paper":"/paper/peergan-generative-adversarial-networks-with","paper_url":"https://arxiv.org/abs/2101.07524v3","paper_title":"DuelGAN: A Duel Between Two Discriminators Stabilizes the GAN Training","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":57,"model":"SNGAN-DCD (Pixel)","metrics":{"FID":"21.67"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/discriminator-contrastive-divergence-semi","paper_url":"https://arxiv.org/abs/2004.01704v1","paper_title":"Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator","code":"https://github.com/MinkaiXu/Discriminator-Contrastive-Divergence","n_code_links":1,"syntology":null},{"rank_in_archive_order":58,"model":"SN-GANs","metrics":{"FID":"21.7"},"uses_additional_data":false,"paper_date":"2018-02-16","paper":"/paper/spectral-normalization-for-generative","paper_url":"http://arxiv.org/abs/1802.05957v1","paper_title":"Spectral Normalization for Generative Adversarial Networks","code":"https://github.com/pytorch/pytorch/blob/a77b391de723a69fb59ff6ae9d1236ca93f03a97/torch/nn/utils/spectral_norm.py","n_code_links":38,"syntology":{"n_ran":16,"n_unverified":15,"n_samples":31,"n_pointer_only_licence":14}},{"rank_in_archive_order":59,"model":"CLR-GAN","metrics":{"FID":"23.3"},"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":60,"model":"NCP-VAE","metrics":{"FID":"24.08"},"uses_additional_data":false,"paper_date":"2020-10-06","paper":"/paper/ncp-vae-variational-autoencoders-with-noise-1","paper_url":"https://arxiv.org/abs/2010.02917v3","paper_title":"A Contrastive Learning Approach for Training Variational Autoencoder Priors","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":61,"model":"WGAN-GP + TT Update Rule","metrics":{"FID":"24.8"},"uses_additional_data":false,"paper_date":"2017-06-26","paper":"/paper/gans-trained-by-a-two-time-scale-update-rule","paper_url":"http://arxiv.org/abs/1706.08500v6","paper_title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","code":"https://github.com/jantic/DeOldify","n_code_links":71,"syntology":{"n_ran":3,"n_unverified":1,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":62,"model":"SN-SMMDGAN","metrics":{"FID":"25.0"},"uses_additional_data":false,"paper_date":"2018-05-29","paper":"/paper/on-gradient-regularizers-for-mmd-gans","paper_url":"https://arxiv.org/abs/1805.11565v5","paper_title":"On gradient regularizers for MMD GANs","code":"https://github.com/MichaelArbel/Scaled-MMD-GAN","n_code_links":1,"syntology":{"n_ran":0,"n_unverified":2,"n_samples":2,"n_pointer_only_licence":1}},{"rank_in_archive_order":63,"model":"NCSN","metrics":{"FID":"25.32"},"uses_additional_data":false,"paper_date":"2019-07-12","paper":"/paper/generative-modeling-by-estimating-gradients","paper_url":"https://arxiv.org/abs/1907.05600v3","paper_title":"Generative Modeling by Estimating Gradients of the Data Distribution","code":"https://github.com/yang-song/score_sde_pytorch","n_code_links":13,"syntology":{"n_ran":14,"n_unverified":8,"n_samples":22,"n_pointer_only_licence":9}},{"rank_in_archive_order":64,"model":"RSGAN-GP","metrics":{"FID":"25.60"},"uses_additional_data":false,"paper_date":"2018-07-02","paper":"/paper/the-relativistic-discriminator-a-key-element","paper_url":"http://arxiv.org/abs/1807.00734v3","paper_title":"The relativistic discriminator: a key element missing from standard GAN","code":"https://github.com/eriklindernoren/PyTorch-GAN","n_code_links":10,"syntology":{"n_ran":1,"n_unverified":8,"n_samples":9,"n_pointer_only_licence":2}},{"rank_in_archive_order":65,"model":"HingeGAN","metrics":{"FID":"27.12"},"uses_additional_data":false,"paper_date":"2019-10-15","paper":"/paper/connections-between-support-vector-machines","paper_url":"https://arxiv.org/abs/1910.06922v2","paper_title":"Gradient penalty from a maximum margin perspective","code":"https://github.com/lucidrains/stylegan2-pytorch","n_code_links":2,"syntology":{"n_ran":2,"n_unverified":8,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":66,"model":"FOGAN","metrics":{"FID":"27.4"},"uses_additional_data":false,"paper_date":"2018-02-13","paper":"/paper/first-order-generative-adversarial-networks","paper_url":"http://arxiv.org/abs/1802.04591v2","paper_title":"First Order Generative Adversarial Networks","code":"https://github.com/zalandoresearch/first_order_gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":67,"model":"MSGAN","metrics":{"FID":"28.73"},"uses_additional_data":false,"paper_date":"2019-03-13","paper":"/paper/mode-seeking-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/1903.05628v6","paper_title":"Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis","code":"https://github.com/HelenMao/MSGAN","n_code_links":2,"syntology":null},{"rank_in_archive_order":68,"model":"WGAN-GP","metrics":{"FID":"29.3"},"uses_additional_data":false,"paper_date":"2017-03-31","paper":"/paper/improved-training-of-wasserstein-gans","paper_url":"http://arxiv.org/abs/1704.00028v3","paper_title":"Improved Training of Wasserstein GANs","code":"https://github.com/labmlai/annotated_deep_learning_paper_implementations","n_code_links":110,"syntology":{"n_ran":27,"n_unverified":22,"n_samples":49,"n_pointer_only_licence":20}},{"rank_in_archive_order":69,"model":"QSNGAN","metrics":{"FID":"31.966"},"uses_additional_data":false,"paper_date":"2021-04-19","paper":"/paper/quaternion-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/2104.09630v2","paper_title":"Quaternion Generative Adversarial Networks","code":"https://github.com/eleGAN23/QVAE","n_code_links":3,"syntology":null},{"rank_in_archive_order":70,"model":"NVAE w/ flow","metrics":{"FID":"32.53"},"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":26,"n_unverified":15,"n_samples":41,"n_pointer_only_licence":23}},{"rank_in_archive_order":71,"model":"DenseFlow-74-10","metrics":{"FID":"34.90"},"uses_additional_data":false,"paper_date":"2021-06-08","paper":"/paper/densely-connected-normalizing-flows","paper_url":"https://arxiv.org/abs/2106.04627v3","paper_title":"Densely connected normalizing flows","code":"https://github.com/matejgrcic/DenseFlow","n_code_links":4,"syntology":null},{"rank_in_archive_order":72,"model":"ACGAN","metrics":{"FID":"35.47"},"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":73,"model":"ProdPoly no activation functions","metrics":{"FID":"40.45"},"uses_additional_data":false,"paper_date":"2020-06-20","paper":"/paper/deep-polynomial-neural-networks","paper_url":"https://arxiv.org/abs/2006.13026v2","paper_title":"Deep Polynomial Neural Networks","code":"https://github.com/Faceplugin-ltd/FaceRecognition-Android","n_code_links":5,"syntology":null},{"rank_in_archive_order":74,"model":"GLF+perceptual loss (ours)","metrics":{"FID":"44.6"},"uses_additional_data":false,"paper_date":"2019-05-24","paper":"/paper/generative-latent-flow-a-framework-for-non","paper_url":"https://arxiv.org/abs/1905.10485v2","paper_title":"Generative Latent Flow","code":"https://github.com/rakhimovv/GenerativeLatentFlow","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":0}},{"rank_in_archive_order":75,"model":"Residual Flow","metrics":{"FID":"46.37"},"uses_additional_data":false,"paper_date":"2019-06-06","paper":"/paper/residual-flows-for-invertible-generative","paper_url":"https://arxiv.org/abs/1906.02735v6","paper_title":"Residual Flows for Invertible Generative Modeling","code":"https://github.com/rtqichen/residual-flows","n_code_links":4,"syntology":{"n_ran":7,"n_unverified":1,"n_samples":8,"n_pointer_only_licence":0}},{"rank_in_archive_order":76,"model":"RESFLOW","metrics":{"FID":"48.29"},"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":77,"model":"PresGAN","metrics":{"FID":"52.202"},"uses_additional_data":false,"paper_date":"2019-10-09","paper":"/paper/prescribed-generative-adversarial-networks","paper_url":"https://arxiv.org/abs/1910.04302v1","paper_title":"Prescribed Generative Adversarial Networks","code":"https://github.com/adjidieng/PresGANs","n_code_links":2,"syntology":null},{"rank_in_archive_order":78,"model":"BigGAN","metrics":{"IS":"9.22"},"uses_additional_data":false,"paper_date":"2018-09-28","paper":"/paper/large-scale-gan-training-for-high-fidelity","paper_url":"http://arxiv.org/abs/1809.11096v2","paper_title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","code":"https://github.com/ajbrock/BigGAN-PyTorch","n_code_links":35,"syntology":{"n_ran":14,"n_unverified":27,"n_samples":41,"n_pointer_only_licence":4}}],"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 6,885 of the 9,623 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":9623,"papers_checked":6885,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2737},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-25T09:33:49+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":34,"distinct_papers_with_graph_line":35,"distinct_papers_with_any_sample_ran":33,"samples_over_distinct_papers":{"n_ran":495,"n_unverified":279,"n_samples":774,"n_pointer_only_licence":233,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":505,"n_unverified":296,"n_samples":801,"n_pointer_only_licence":243,"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"}}}