{"url":"/sota/conditional-image-generation-on-imagenet","task":{"name":"Conditional Image Generation","url":"/task/conditional-image-generation","note":null},"dataset":{"name":"ImageNet 128x128","url":null},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"Conditional image generation is the task of generating new images from a dataset conditional on their class.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [PixelCNN++](https://github.com/openai/pixel-cnn) )</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","Inception score"],"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","Inception score":"higher"}},"counts":{"rows":22,"rows_with_code":21,"rows_with_paper_page":22,"rows_dated":22,"rows_using_additional_data":5},"rows":[{"rank_in_archive_order":1,"model":"EluCD_DDPM","metrics":{"FID":"2.19"},"uses_additional_data":false,"paper_date":"2023-10-17","paper":"/paper/elucidating-the-design-space-of-classifier","paper_url":"https://arxiv.org/abs/2310.11311v1","paper_title":"Elucidating The Design Space of Classifier-Guided Diffusion Generation","code":"https://github.com/alexmaols/elucd","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"ADM-G + EDS (ED-DPM, classifier_scale=0.4)","metrics":{"FID":"2.63","Inception score":"159.72"},"uses_additional_data":false,"paper_date":"2022-06-23","paper":"/paper/entropy-driven-sampling-and-training-scheme","paper_url":"https://arxiv.org/abs/2206.11474v5","paper_title":"Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation","code":"https://github.com/ZGCTroy/ED-DPM","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"ADM-G + EDS + ECT (ED-DPM, classifier_scale=0.6)","metrics":{"FID":"2.68","Inception score":"169.24"},"uses_additional_data":false,"paper_date":"2022-06-23","paper":"/paper/entropy-driven-sampling-and-training-scheme","paper_url":"https://arxiv.org/abs/2206.11474v5","paper_title":"Entropy-driven Sampling and Training Scheme for Conditional Diffusion Generation","code":"https://github.com/ZGCTroy/ED-DPM","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"simple diffusion (U-Net)","metrics":{"FID":"2.88","Inception score":"137.3"},"uses_additional_data":false,"paper_date":"2023-01-26","paper":"/paper/simple-diffusion-end-to-end-diffusion-for","paper_url":"https://arxiv.org/abs/2301.11093v2","paper_title":"Simple diffusion: End-to-end diffusion for high resolution images","code":"https://github.com/fashn-AI/tryondiffusion","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"ADM-G (classifier_scale=0.5)","metrics":{"FID":"2.97"},"uses_additional_data":false,"paper_date":"2021-05-11","paper":"/paper/diffusion-models-beat-gans-on-image-synthesis","paper_url":"https://arxiv.org/abs/2105.05233v4","paper_title":"Diffusion Models Beat GANs on Image Synthesis","code":"https://github.com/openai/guided-diffusion","n_code_links":21,"syntology":{"n_ran":27,"n_unverified":23,"n_samples":50,"n_pointer_only_licence":16}},{"rank_in_archive_order":6,"model":"simple diffusion (U-ViT, L)","metrics":{"FID":"3.23","Inception score":"171.9"},"uses_additional_data":false,"paper_date":"2023-01-26","paper":"/paper/simple-diffusion-end-to-end-diffusion-for","paper_url":"https://arxiv.org/abs/2301.11093v2","paper_title":"Simple diffusion: End-to-end diffusion for high resolution images","code":"https://github.com/fashn-AI/tryondiffusion","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"BigGAN-deep","metrics":{"FID":"5.7","Inception score":"124.5"},"uses_additional_data":true,"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}},{"rank_in_archive_order":8,"model":"Omni-INR-GAN","metrics":{"FID":"6.53","Inception score":"262.85"},"uses_additional_data":false,"paper_date":"2020-11-26","paper":"/paper/omni-gan-on-the-secrets-of-cgans-and-beyond","paper_url":"https://arxiv.org/abs/2011.13074v3","paper_title":"Omni-GAN: On the Secrets of cGANs and Beyond","code":"https://github.com/PeterouZh/Omni-GAN-PyTorch","n_code_links":3,"syntology":null},{"rank_in_archive_order":9,"model":"CR-BigGAN","metrics":{"FID":"6.66"},"uses_additional_data":false,"paper_date":"2019-10-26","paper":"/paper/consistency-regularization-for-generative-1","paper_url":"https://arxiv.org/abs/1910.12027v2","paper_title":"Consistency Regularization for Generative Adversarial Networks","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":10,"model":"S3 GAN","metrics":{"FID":"7.7","Inception score":"83.1"},"uses_additional_data":false,"paper_date":"2019-03-06","paper":"/paper/high-fidelity-image-generation-with-fewer","paper_url":"https://arxiv.org/abs/1903.02271v2","paper_title":"High-Fidelity Image Generation With Fewer Labels","code":"https://github.com/google/compare_gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"ADC-GAN","metrics":{"FID":"8.02","Inception score":"108.10"},"uses_additional_data":false,"paper_date":"2021-07-21","paper":"/paper/cgans-with-auxiliary-discriminative","paper_url":"https://arxiv.org/abs/2107.10060v5","paper_title":"Conditional GANs with Auxiliary Discriminative Classifier","code":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":2,"n_samples":6,"n_pointer_only_licence":6}},{"rank_in_archive_order":12,"model":"ReACGAN","metrics":{"FID":"8.206","Inception score":"96.299"},"uses_additional_data":false,"paper_date":"2021-11-01","paper":"/paper/rebooting-acgan-auxiliary-classifier-gans","paper_url":"https://arxiv.org/abs/2111.01118v1","paper_title":"Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training","code":"https://github.com/POSTECH-CVLab/PyTorch-StudioGAN","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":9}},{"rank_in_archive_order":13,"model":"Omni-GAN","metrics":{"FID":"8.30","Inception score":"190.94"},"uses_additional_data":false,"paper_date":"2020-11-26","paper":"/paper/omni-gan-on-the-secrets-of-cgans-and-beyond","paper_url":"https://arxiv.org/abs/2011.13074v3","paper_title":"Omni-GAN: On the Secrets of cGANs and Beyond","code":"https://github.com/PeterouZh/Omni-GAN-PyTorch","n_code_links":3,"syntology":null},{"rank_in_archive_order":14,"model":"BigGAN","metrics":{"FID":"8.7","Inception score":"98.8"},"uses_additional_data":true,"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}},{"rank_in_archive_order":15,"model":"IC-GAN + DA","metrics":{"FID":"9.5","Inception score":"108.6"},"uses_additional_data":false,"paper_date":"2021-09-10","paper":"/paper/instance-conditioned-gan","paper_url":"https://arxiv.org/abs/2109.05070v2","paper_title":"Instance-Conditioned GAN","code":"https://github.com/facebookresearch/ic_gan","n_code_links":1,"syntology":null},{"rank_in_archive_order":16,"model":"BigGAN + instance selection","metrics":{"FID":"9.61","Inception score":"114.32"},"uses_additional_data":false,"paper_date":"2020-07-30","paper":"/paper/instance-selection-for-gans","paper_url":"https://arxiv.org/abs/2007.15255v2","paper_title":"Instance Selection for GANs","code":"https://github.com/snap-research/3dgp","n_code_links":2,"syntology":{"n_ran":11,"n_unverified":8,"n_samples":19,"n_pointer_only_licence":19}},{"rank_in_archive_order":17,"model":"FQ-GAN","metrics":{"FID":"13.77","Inception score":"54.36"},"uses_additional_data":false,"paper_date":"2020-04-05","paper":"/paper/feature-quantization-improves-gan-training","paper_url":"https://arxiv.org/abs/2004.02088v2","paper_title":"Feature Quantization Improves GAN Training","code":"https://github.com/YangNaruto/FQ-GAN","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":3,"n_samples":4,"n_pointer_only_licence":1}},{"rank_in_archive_order":18,"model":"HamGAN","metrics":{"FID":"14.80","Inception score":"58.75"},"uses_additional_data":false,"paper_date":"2021-09-09","paper":"/paper/is-attention-better-than-matrix-decomposition-1","paper_url":"https://arxiv.org/abs/2109.04553v2","paper_title":"Is Attention Better Than Matrix Decomposition?","code":"https://github.com/Gsunshine/Enjoy-Hamburger","n_code_links":3,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":3}},{"rank_in_archive_order":19,"model":"Your Local GAN","metrics":{"FID":"15.94","Inception score":"57.22"},"uses_additional_data":false,"paper_date":"2019-11-27","paper":"/paper/your-local-gan-designing-two-dimensional","paper_url":"https://arxiv.org/abs/1911.12287v2","paper_title":"Your Local GAN: Designing Two Dimensional Local Attention Mechanisms for Generative Models","code":"https://github.com/giannisdaras/ylg","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":20,"model":"SAGAN","metrics":{"FID":"18.65","Inception score":"52.52"},"uses_additional_data":true,"paper_date":"2018-05-21","paper":"/paper/self-attention-generative-adversarial","paper_url":"https://arxiv.org/abs/1805.08318v2","paper_title":"Self-Attention Generative Adversarial Networks","code":"https://github.com/jantic/DeOldify","n_code_links":48,"syntology":{"n_ran":18,"n_unverified":63,"n_samples":81,"n_pointer_only_licence":1}},{"rank_in_archive_order":21,"model":"Projection Discriminator","metrics":{"FID":"27.62","Inception score":"36.8"},"uses_additional_data":true,"paper_date":"2018-02-15","paper":"/paper/cgans-with-projection-discriminator","paper_url":"http://arxiv.org/abs/1802.05637v2","paper_title":"cGANs with Projection Discriminator","code":"https://github.com/pfnet-research/sngan_projection","n_code_links":12,"syntology":{"n_ran":9,"n_unverified":0,"n_samples":9,"n_pointer_only_licence":6}},{"rank_in_archive_order":22,"model":"AC-GAN","metrics":{"Inception score":"28.5"},"uses_additional_data":true,"paper_date":"2016-10-30","paper":"/paper/conditional-image-synthesis-with-auxiliary","paper_url":"http://arxiv.org/abs/1610.09585v4","paper_title":"Conditional Image Synthesis With Auxiliary Classifier GANs","code":"https://github.com/eriklindernoren/PyTorch-GAN","n_code_links":37,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":5}}],"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 6,795 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":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"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":14,"rows_with_any_sample_ran":14,"distinct_papers_with_graph_line":12,"distinct_papers_with_any_sample_ran":12,"samples_over_distinct_papers":{"n_ran":103,"n_unverified":126,"n_samples":229,"n_pointer_only_licence":71,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":118,"n_unverified":153,"n_samples":271,"n_pointer_only_licence":75,"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"}}}