{"url":"/sota/text-to-video-generation-on-msr-vtt","task":{"name":"Text-to-Video Generation","url":"/task/text-to-video-generation","note":null},"dataset":{"name":"MSR-VTT","url":"/dataset/msr-vtt"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"Ma grand-mère m’a raconté que quand elle était étudiante, elle avait un petit-ami. À l’âge de 18 ans, il a dû partir pour le service militaire, elle ne l’a pas attendu et elle a épousé quelqu’un d’autre. Quand ma grand-mère avait 58-59 ans, un homme (son premier amour) lui a envoyé une demande d’amis sur un réseau social, ils ont commencé à parler... En moins de six mois, ils ont décidé de se voir. Le trajet en train a duré deux jours et ils se sont finalement rencontrés. Cela fait maintenant deux ans qu’ils habitent ensemble et qu’ils nous rendent visite de temps en temps. Je réalise maintenant que leur amour l’un envers l’autre n’a jamais cessé.","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":["FVD","CLIPSIM","CLIP-FID","FID"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FVD":null,"CLIPSIM":null,"CLIP-FID":"lower","FID":"lower"}},"counts":{"rows":18,"rows_with_code":13,"rows_with_paper_page":18,"rows_dated":18,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"Snap Video (512x288)","metrics":{"CLIP-FID":"9.35","CLIPSIM":"0.2793","FVD":"104.0"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/snap-video-scaled-spatiotemporal-transformers","paper_url":"https://arxiv.org/abs/2402.14797v1","paper_title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Snap Video (288×288)","metrics":{"CLIP-FID":"8.48","CLIPSIM":"0.2793","FVD":"110.4"},"uses_additional_data":false,"paper_date":"2024-02-22","paper":"/paper/snap-video-scaled-spatiotemporal-transformers","paper_url":"https://arxiv.org/abs/2402.14797v1","paper_title":"Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":3,"model":"Video-LaVIT","metrics":{"CLIPSIM":"0.3012","FID":"11.27","FVD":"188.36"},"uses_additional_data":false,"paper_date":"2024-02-05","paper":"/paper/video-lavit-unified-video-language-pre","paper_url":"https://arxiv.org/abs/2402.03161v3","paper_title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","code":"https://github.com/jy0205/lavit","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":2,"n_samples":5,"n_pointer_only_licence":5}},{"rank_in_archive_order":4,"model":"VideoPoet","metrics":{"CLIPSIM":"0.3123","FVD":"213"},"uses_additional_data":false,"paper_date":"2023-12-21","paper":"/paper/videopoet-a-large-language-model-for-zero","paper_url":"https://arxiv.org/abs/2312.14125v4","paper_title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":5,"model":"PixelDance","metrics":{"CLIPSIM":"0.3125","FVD":"381"},"uses_additional_data":false,"paper_date":"2023-11-18","paper":"/paper/make-pixels-dance-high-dynamic-video","paper_url":"https://arxiv.org/abs/2311.10982v1","paper_title":"Make Pixels Dance: High-Dynamic Video Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":6,"model":"HiGen","metrics":{"CLIPSIM":"0.2947","FID":"8.60","FVD":"406"},"uses_additional_data":false,"paper_date":"2023-12-07","paper":"/paper/hierarchical-spatio-temporal-decoupling-for","paper_url":"https://arxiv.org/abs/2312.04483v1","paper_title":"Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation","code":"https://github.com/ali-vilab/VGen","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"TF-T2V","metrics":{"CLIPSIM":"0.2991","FID":"8.19","FVD":"441"},"uses_additional_data":false,"paper_date":"2023-12-25","paper":"/paper/a-recipe-for-scaling-up-text-to-video","paper_url":"https://arxiv.org/abs/2312.15770v1","paper_title":"A Recipe for Scaling up Text-to-Video Generation with Text-free Videos","code":"https://github.com/ali-vilab/i2vgen-xl","n_code_links":1,"syntology":null},{"rank_in_archive_order":8,"model":"Show-1","metrics":{"CLIPSIM":"0.3072","FID":"13.08","FVD":"538"},"uses_additional_data":false,"paper_date":"2023-09-27","paper":"/paper/show-1-marrying-pixel-and-latent-diffusion","paper_url":"https://arxiv.org/abs/2309.15818v2","paper_title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","code":"https://github.com/showlab/show-1","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":0,"n_samples":1,"n_pointer_only_licence":1}},{"rank_in_archive_order":9,"model":"ModelScopeT2V","metrics":{"CLIPSIM":"0.2930","FID":"11.09","FVD":"550"},"uses_additional_data":false,"paper_date":"2023-08-12","paper":"/paper/modelscope-text-to-video-technical-report","paper_url":"https://arxiv.org/abs/2308.06571v1","paper_title":"ModelScope Text-to-Video Technical Report","code":"https://github.com/ali-vilab/VGen","n_code_links":5,"syntology":{"n_ran":11,"n_unverified":5,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"VideoComposer","metrics":{"CLIPSIM":"0.2932","FVD":"580"},"uses_additional_data":false,"paper_date":"2023-06-03","paper":"/paper/videocomposer-compositional-video-synthesis","paper_url":"https://arxiv.org/abs/2306.02018v2","paper_title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","code":"https://github.com/ali-vilab/videocomposer","n_code_links":4,"syntology":{"n_ran":12,"n_unverified":9,"n_samples":21,"n_pointer_only_licence":1}},{"rank_in_archive_order":11,"model":"MagicVideo","metrics":{"FID":"36.5","FVD":"998"},"uses_additional_data":false,"paper_date":"2022-11-20","paper":"/paper/magicvideo-efficient-video-generation-with","paper_url":"https://arxiv.org/abs/2211.11018v2","paper_title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":12,"model":"Make-A-Video","metrics":{"CLIP-FID":"13.17","CLIPSIM":"0.3049","FID":"13.17"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/make-a-video-text-to-video-generation-without","paper_url":"https://arxiv.org/abs/2209.14792v1","paper_title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","code":"https://github.com/lucidrains/make-a-video-pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":13,"model":"Video LDM","metrics":{"CLIPSIM":"0.2929"},"uses_additional_data":false,"paper_date":"2023-04-18","paper":"/paper/align-your-latents-high-resolution-video","paper_url":"https://arxiv.org/abs/2304.08818v2","paper_title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","code":"https://github.com/stability-ai/generative-models","n_code_links":4,"syntology":{"n_ran":18,"n_unverified":8,"n_samples":26,"n_pointer_only_licence":1}},{"rank_in_archive_order":14,"model":"MMVG","metrics":{"CLIPSIM":"0.2644","FID":"23.4"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/tell-me-what-happened-unifying-text-guided","paper_url":"https://arxiv.org/abs/2211.12824v2","paper_title":"Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation","code":"https://github.com/tsujuifu/pytorch_tvc","n_code_links":1,"syntology":null},{"rank_in_archive_order":15,"model":"CogVideo (English)","metrics":{"CLIP-FID":"23.59","CLIPSIM":"0.2631","FID":"23.59"},"uses_additional_data":false,"paper_date":"2022-09-29","paper":"/paper/make-a-video-text-to-video-generation-without","paper_url":"https://arxiv.org/abs/2209.14792v1","paper_title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","code":"https://github.com/lucidrains/make-a-video-pytorch","n_code_links":2,"syntology":null},{"rank_in_archive_order":16,"model":"CogVideo (Chinese)","metrics":{"CLIP-FID":"24.78","CLIPSIM":"0.2614"},"uses_additional_data":false,"paper_date":"2023-04-18","paper":"/paper/align-your-latents-high-resolution-video","paper_url":"https://arxiv.org/abs/2304.08818v2","paper_title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","code":"https://github.com/stability-ai/generative-models","n_code_links":4,"syntology":{"n_ran":18,"n_unverified":8,"n_samples":26,"n_pointer_only_licence":1}},{"rank_in_archive_order":17,"model":"NUWA","metrics":{"CLIP-FID":"47.68","CLIPSIM":"0.2439","FID":"47.68"},"uses_additional_data":false,"paper_date":"2021-11-24","paper":"/paper/nuwa-visual-synthesis-pre-training-for-neural","paper_url":"https://arxiv.org/abs/2111.12417v1","paper_title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","code":"https://github.com/lucidrains/nuwa-pytorch","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":2}},{"rank_in_archive_order":18,"model":"GODIVA","metrics":{"CLIPSIM":"0.2402"},"uses_additional_data":false,"paper_date":"2021-04-30","paper":"/paper/godiva-generating-open-domain-videos-from","paper_url":"https://arxiv.org/abs/2104.14806v1","paper_title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","code":"https://github.com/mehdidc/DALLE_clip_score","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 7,081 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":7081,"papers_extracted_not_yet_verified":217,"boards_without_verdict":27,"papers_not_yet_extracted":2325},"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":7,"rows_with_any_sample_ran":7,"distinct_papers_with_graph_line":6,"distinct_papers_with_any_sample_ran":6,"samples_over_distinct_papers":{"n_ran":48,"n_unverified":24,"n_samples":72,"n_pointer_only_licence":10,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":66,"n_unverified":32,"n_samples":98,"n_pointer_only_licence":11,"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"}}}