{"url":"/sota/image-generation-on-wise","task":{"name":"Image Generation","url":"/task/image-generation","note":null},"dataset":{"name":"WISE","url":"/dataset/wise"},"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":["Overall","Cultural","Time","Space","Biology","Physics","Chemistry"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Overall":null,"Cultural":null,"Time":"lower","Space":null,"Biology":null,"Physics":null,"Chemistry":null}},"counts":{"rows":14,"rows_with_code":12,"rows_with_paper_page":13,"rows_dated":13,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"MindOmni\n(w/ cot)","metrics":{"Biology":"0.76","Chemistry":"0.52","Cultural":"0.75","Overall":"0.71","Physics":"0.72","Space":"0.76","Time":"0.70"},"uses_additional_data":false,"paper_date":"2025-05-19","paper":"/paper/mindomni-unleashing-reasoning-generation-in","paper_url":"https://arxiv.org/abs/2505.13031v1","paper_title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","code":"https://github.com/easonxiao-888/mindomni","n_code_links":1,"syntology":null},{"rank_in_archive_order":2,"model":"Bagel (w/ cot)","metrics":{"Biology":"0.65","Chemistry":"0.58","Cultural":"0.76","Overall":"0.70","Physics":"0.75","Space":"0.75","Time":"0.69"},"uses_additional_data":false,"paper_date":"2025-05-20","paper":"/paper/emerging-properties-in-unified-multimodal","paper_url":"https://arxiv.org/abs/2505.14683v1","paper_title":"Emerging Properties in Unified Multimodal Pretraining","code":"https://github.com/ByteDance-Seed/Bagel","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":12,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"MetaQuery-XL","metrics":{"Biology":"0.49","Chemistry":"0.41","Cultural":"0.56","Overall":"0.55","Physics":"0.63","Space":"0.62","Time":"0.55"},"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":4,"model":"UniWorld-V1","metrics":{"Biology":"0.45","Chemistry":"0.41","Cultural":"0.53","Overall":"0.55","Physics":"0.59","Space":"0.73","Time":"0.55"},"uses_additional_data":false,"paper_date":"2025-06-03","paper":"/paper/uniworld-v1-high-resolution-semantic-encoders","paper_url":"https://arxiv.org/abs/2506.03147v3","paper_title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","code":"https://github.com/PKU-YuanGroup/UniWorld-V1","n_code_links":2,"syntology":null},{"rank_in_archive_order":5,"model":"Bagel","metrics":{"Biology":"0.44","Chemistry":"0.39","Cultural":"0.44","Overall":"0.52","Physics":"0.60","Space":"0.68","Time":"0.55"},"uses_additional_data":false,"paper_date":"2025-05-20","paper":"/paper/emerging-properties-in-unified-multimodal","paper_url":"https://arxiv.org/abs/2505.14683v1","paper_title":"Emerging Properties in Unified Multimodal Pretraining","code":"https://github.com/ByteDance-Seed/Bagel","n_code_links":2,"syntology":{"n_ran":9,"n_unverified":12,"n_samples":21,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"Playground-v2.5-1024px-aesthetic","metrics":{"Biology":"0.43","Chemistry":"0.33","Cultural":"0.49","Overall":"0.49","Physics":"0.48","Space":"0.55","Time":"0.58"},"uses_additional_data":false,"paper_date":"2024-02-27","paper":"/paper/playground-v2-5-three-insights-towards","paper_url":"https://arxiv.org/abs/2402.17245v1","paper_title":"Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"PixArt-XL-2-1024-MS","metrics":{"Biology":"0.49","Chemistry":"0.34","Cultural":"0.45","Overall":"0.47","Physics":"0.56","Space":"0.48","Time":"0.50"},"uses_additional_data":false,"paper_date":"2023-09-30","paper":"/paper/pixart-a-fast-training-of-diffusion","paper_url":"https://arxiv.org/abs/2310.00426v3","paper_title":"PixArt-$α$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","code":"https://github.com/PixArt-alpha/PixArt-alpha","n_code_links":3,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":8,"model":"stable-diffusion-3.5-large","metrics":{"Biology":"0.44","Chemistry":"0.31","Cultural":"0.44","Overall":"0.46","Physics":"0.52","Space":"0.58","Time":"0.50"},"uses_additional_data":false,"paper_date":"2024-03-05","paper":"/paper/scaling-rectified-flow-transformers-for-high","paper_url":"https://arxiv.org/abs/2403.03206v1","paper_title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","code":"https://github.com/Karine-Huang/T2I-CompBench","n_code_links":2,"syntology":{"n_ran":10,"n_unverified":1,"n_samples":11,"n_pointer_only_licence":11}},{"rank_in_archive_order":9,"model":"stable-diffusion-xl-base-0.9","metrics":{"Biology":"0.44","Chemistry":"0.27","Cultural":"0.43","Overall":"0.43","Physics":"0.45","Space":"0.47","Time":"0.48"},"uses_additional_data":false,"paper_date":"2023-07-04","paper":"/paper/sdxl-improving-latent-diffusion-models-for","paper_url":"https://arxiv.org/abs/2307.01952v1","paper_title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","code":"https://github.com/stability-ai/generative-models","n_code_links":9,"syntology":{"n_ran":11,"n_unverified":16,"n_samples":27,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"MindOmni\n(w/o cot)","metrics":{"Biology":"0.36","Chemistry":"0.32","Cultural":"0.40","Overall":"0.43","Physics":"0.52","Space":"0.62","Time":"0.38"},"uses_additional_data":false,"paper_date":"2025-05-19","paper":"/paper/mindomni-unleashing-reasoning-generation-in","paper_url":"https://arxiv.org/abs/2505.13031v1","paper_title":"MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO","code":"https://github.com/easonxiao-888/mindomni","n_code_links":1,"syntology":null},{"rank_in_archive_order":11,"model":"Emu3-gen","metrics":{"Biology":"0.41","Chemistry":"0.27","Cultural":"0.34","Overall":"0.39","Physics":"0.45","Space":"0.48","Time":"0.45"},"uses_additional_data":false,"paper_date":"2024-09-27","paper":"/paper/emu3-next-token-prediction-is-all-you-need","paper_url":"https://arxiv.org/abs/2409.18869v1","paper_title":"Emu3: Next-Token Prediction is All You Need","code":"https://github.com/baaivision/emu3","n_code_links":2,"syntology":{"n_ran":3,"n_unverified":3,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":12,"model":"Janus-pro","metrics":{"Biology":"0.36","Chemistry":"0.26","Cultural":"0.30","Overall":"0.35","Physics":"0.42","Space":"0.49","Time":"0.37"},"uses_additional_data":false,"paper_date":"2025-01-29","paper":"/paper/janus-pro-unified-multimodal-understanding","paper_url":"https://arxiv.org/abs/2501.17811v1","paper_title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","code":"https://github.com/deepseek-ai/janus","n_code_links":1,"syntology":null},{"rank_in_archive_order":13,"model":"Show-o","metrics":{"Biology":"0.30","Chemistry":"0.30","Cultural":"0.28","Overall":"0.35","Physics":"0.46","Space":"0.48","Time":"0.40"},"uses_additional_data":false,"paper_date":"2024-08-22","paper":"/paper/show-o-one-single-transformer-to-unify","paper_url":"https://arxiv.org/abs/2408.12528v6","paper_title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","code":"https://github.com/showlab/show-o","n_code_links":1,"syntology":null},{"rank_in_archive_order":14,"model":"Janus","metrics":{"Biology":"0.28","Chemistry":"0.14","Cultural":"0.16","Overall":"0.23","Physics":"0.30","Space":"0.35","Time":"0.26"},"uses_additional_data":false,"paper_date":"2025-01-29","paper":"/paper/janus-pro-unified-multimodal-understanding","paper_url":"https://arxiv.org/abs/2501.17811v1","paper_title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","code":"https://github.com/deepseek-ai/janus","n_code_links":1,"syntology":null}],"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":6,"rows_with_any_sample_ran":6,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":35,"n_unverified":33,"n_samples":68,"n_pointer_only_licence":13,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":44,"n_unverified":45,"n_samples":89,"n_pointer_only_licence":13,"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"}}}