{"url":"/sota/video-generation-on-ucf-101","task":{"name":"Video Generation","url":"/task/video-generation","note":null},"dataset":{"name":"UCF-101","url":"/dataset/ucf101"},"category":"Computer Vision","categories":["Computer Vision","Natural Language Processing"],"category_note":null,"description":"<span style=\"color:grey; opacity: 0.6\">( Various Video Generation Tasks.\r\nGif credit: [MaGViT](https://paperswithcode.com/paper/magvit-masked-generative-video-transformer) )</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":["FVD16","FVD128","Inception Score","KVD16"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"FVD16":null,"FVD128":null,"Inception Score":"higher","KVD16":null}},"counts":{"rows":48,"rows_with_code":39,"rows_with_paper_page":48,"rows_dated":48,"rows_using_additional_data":2},"rows":[{"rank_in_archive_order":1,"model":"W.A.L.T-XL (class-conditional)","metrics":{"FVD16":"36±2"},"uses_additional_data":true,"paper_date":"2023-12-11","paper":"/paper/photorealistic-video-generation-with","paper_url":"https://arxiv.org/abs/2312.06662v1","paper_title":"Photorealistic Video Generation with Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":2,"model":"Video-GPT","metrics":{"FVD16":"53"},"uses_additional_data":true,"paper_date":"2025-05-18","paper":"/paper/video-gpt-via-next-clip-diffusion","paper_url":"https://arxiv.org/abs/2505.12489v2","paper_title":"Video-GPT via Next Clip Diffusion","code":"https://github.com/zhuangshaobin/Video-GPT","n_code_links":1,"syntology":null},{"rank_in_archive_order":3,"model":"LARP","metrics":{"FVD16":"57"},"uses_additional_data":false,"paper_date":"2024-10-28","paper":"/paper/larp-tokenizing-videos-with-a-learned-1","paper_url":"https://arxiv.org/abs/2410.21264v1","paper_title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","code":"https://github.com/hywang66/LARP","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":9,"n_samples":13,"n_pointer_only_licence":0}},{"rank_in_archive_order":4,"model":"FAR","metrics":{"FVD16":"57"},"uses_additional_data":false,"paper_date":"2025-03-25","paper":"/paper/long-context-autoregressive-video-modeling-1","paper_url":"https://arxiv.org/abs/2503.19325v3","paper_title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","code":"https://github.com/showlab/FAR","n_code_links":1,"syntology":null},{"rank_in_archive_order":5,"model":"MAGVIT-v2","metrics":{"FVD16":"58±3"},"uses_additional_data":false,"paper_date":"2023-10-09","paper":"/paper/language-model-beats-diffusion-tokenizer-is","paper_url":"https://arxiv.org/abs/2310.05737v3","paper_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","code":"https://github.com/jy0205/Pyramid-Flow","n_code_links":3,"syntology":{"n_ran":12,"n_unverified":8,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":6,"model":"HPDM-L","metrics":{"FVD16":"66.32","Inception Score":"87.68"},"uses_additional_data":false,"paper_date":"2024-06-12","paper":"/paper/hierarchical-patch-diffusion-models-for-high-1","paper_url":"https://arxiv.org/abs/2406.07792v1","paper_title":"Hierarchical Patch Diffusion Models for High-Resolution Video Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":7,"model":"MAGVIT (-L-CG, 128x128, class-conditional)","metrics":{"FVD16":"76±2","Inception Score":"89.27±0.15"},"uses_additional_data":false,"paper_date":"2022-12-10","paper":"/paper/magvit-masked-generative-video-transformer","paper_url":"https://arxiv.org/abs/2212.05199v2","paper_title":"MAGVIT: Masked Generative Video Transformer","code":"https://github.com/google-research/magvit","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":9,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":8,"model":"Make-A-Video (Finetuning, 256x256, class-conditional)","metrics":{"FVD16":"81.25","Inception Score":"82.55"},"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":9,"model":"ACDiT","metrics":{"FVD16":"90"},"uses_additional_data":false,"paper_date":"2024-12-10","paper":"/paper/acdit-interpolating-autoregressive","paper_url":"https://arxiv.org/abs/2412.07720v1","paper_title":"ACDiT: Interpolating Autoregressive Conditional Modeling and Diffusion Transformer","code":"https://github.com/thunlp/acdit","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":5,"n_samples":6,"n_pointer_only_licence":0}},{"rank_in_archive_order":10,"model":"MAGVIT-v2 (AR)","metrics":{"FVD16":"109"},"uses_additional_data":false,"paper_date":"2023-10-09","paper":"/paper/language-model-beats-diffusion-tokenizer-is","paper_url":"https://arxiv.org/abs/2310.05737v3","paper_title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","code":"https://github.com/jy0205/Pyramid-Flow","n_code_links":3,"syntology":{"n_ran":12,"n_unverified":8,"n_samples":20,"n_pointer_only_licence":0}},{"rank_in_archive_order":11,"model":"REGIS-Fuse (Finetuning, 128x128, text-conditional)","metrics":{"FVD16":"141"},"uses_additional_data":false,"paper_date":"2023-11-03","paper":"/paper/regis-refining-generated-videos-via-iterative","paper_url":"https://doi.org/10.21203/rs.3.rs-3541408/v1","paper_title":"REGIS: Refining Generated Videos via Iterative Stylistic Redesigning","code":"https://github.com/Jaso1024/Refining-Generated-Videos","n_code_links":1,"syntology":null},{"rank_in_archive_order":12,"model":"MAGVIT (-B-CG, 128x128, class-conditional)","metrics":{"FVD16":"159±2","Inception Score":"83.55±0.14"},"uses_additional_data":false,"paper_date":"2022-12-10","paper":"/paper/magvit-masked-generative-video-transformer","paper_url":"https://arxiv.org/abs/2212.05199v2","paper_title":"MAGVIT: Masked Generative Video Transformer","code":"https://github.com/google-research/magvit","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":9,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":13,"model":"Latte + LeanVAE","metrics":{"FVD16":"164.45"},"uses_additional_data":false,"paper_date":"2025-03-18","paper":"/paper/leanvae-an-ultra-efficient-reconstruction-vae","paper_url":"https://arxiv.org/abs/2503.14325v1","paper_title":"LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models","code":"https://github.com/westlake-repl/leanvae","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":2,"n_samples":4,"n_pointer_only_licence":0}},{"rank_in_archive_order":14,"model":"VideoFusion (128x128, class-conditional)","metrics":{"FVD16":"173","Inception Score":"80.03"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/decomposed-diffusion-models-for-high-quality","paper_url":"https://arxiv.org/abs/2303.08320v4","paper_title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","code":"https://github.com/modelscope/modelscope","n_code_links":2,"syntology":null},{"rank_in_archive_order":15,"model":"OmniTokenizer-AR","metrics":{"FVD16":"191"},"uses_additional_data":false,"paper_date":"2024-06-13","paper":"/paper/omnitokenizer-a-joint-image-video-tokenizer","paper_url":"https://arxiv.org/abs/2406.09399v1","paper_title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","code":"https://github.com/foundationvision/omnitokenizer","n_code_links":1,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":1}},{"rank_in_archive_order":16,"model":"VideoFusion (128x128, unconditional)","metrics":{"FVD16":"220","Inception Score":"72.22"},"uses_additional_data":false,"paper_date":"2023-03-15","paper":"/paper/decomposed-diffusion-models-for-high-quality","paper_url":"https://arxiv.org/abs/2303.08320v4","paper_title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","code":"https://github.com/modelscope/modelscope","n_code_links":2,"syntology":null},{"rank_in_archive_order":17,"model":"PixelDance (256x256, text-conditional)","metrics":{"FVD16":"242.82","Inception Score":"42.10"},"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":18,"model":"W.A.L.T 3B (text-conditional)","metrics":{"FVD16":"258.1","Inception Score":"35.1"},"uses_additional_data":false,"paper_date":"2023-12-11","paper":"/paper/photorealistic-video-generation-with","paper_url":"https://arxiv.org/abs/2312.06662v1","paper_title":"Photorealistic Video Generation with Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":19,"model":"MAGVIT (AR)","metrics":{"FVD16":"265"},"uses_additional_data":false,"paper_date":"2022-12-10","paper":"/paper/magvit-masked-generative-video-transformer","paper_url":"https://arxiv.org/abs/2212.05199v2","paper_title":"MAGVIT: Masked Generative Video Transformer","code":"https://github.com/google-research/magvit","n_code_links":1,"syntology":{"n_ran":1,"n_unverified":9,"n_samples":10,"n_pointer_only_licence":0}},{"rank_in_archive_order":20,"model":"Video-LaVIT","metrics":{"FVD16":"280.57","Inception Score":"44.26"},"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":21,"model":"VIDM (256x256, unconditional)","metrics":{"FVD128":"1531.9","FVD16":"294.7"},"uses_additional_data":false,"paper_date":"2022-12-01","paper":"/paper/vidm-video-implicit-diffusion-models","paper_url":"https://arxiv.org/abs/2212.00235v1","paper_title":"VIDM: Video Implicit Diffusion Models","code":"https://github.com/MKFMIKU/VIDM","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":0,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":22,"model":"CogVideo (128x128, class-conditional)","metrics":{"FVD16":"305","Inception Score":"51.11"},"uses_additional_data":false,"paper_date":"2022-05-29","paper":"/paper/cogvideo-large-scale-pretraining-for-text-to","paper_url":"https://arxiv.org/abs/2205.15868v1","paper_title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","code":"https://github.com/thudm/cogvideo","n_code_links":1,"syntology":null},{"rank_in_archive_order":23,"model":"PYoCo (Zero-shot, 64x64, unconditional)","metrics":{"FVD16":"310","Inception Score":"60.01"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/preserve-your-own-correlation-a-noise-prior","paper_url":"https://arxiv.org/abs/2305.10474v3","paper_title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":24,"model":"MMVG (128x128, class-conditional)","metrics":{"FVD16":"328","Inception Score":"73.7"},"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":25,"model":"TATS (128x128, class-conditional)","metrics":{"FVD16":"332","Inception Score":"79.28"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/long-video-generation-with-time-agnostic","paper_url":"https://arxiv.org/abs/2204.03638v4","paper_title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","code":"https://github.com/songweige/tats","n_code_links":1,"syntology":null},{"rank_in_archive_order":26,"model":"Lumiere (Zero-shot. 1024x1024, text-conditional)","metrics":{"FVD16":"332.49","Inception Score":"37.54"},"uses_additional_data":false,"paper_date":"2024-01-23","paper":"/paper/lumiere-a-space-time-diffusion-model-for","paper_url":"https://arxiv.org/abs/2401.12945v2","paper_title":"Lumiere: A Space-Time Diffusion Model for Video Generation","code":"https://github.com/lucidrains/lumiere-pytorch","n_code_links":1,"syntology":{"n_ran":2,"n_unverified":1,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":27,"model":"GridDiff (Zero-shot)","metrics":{"FVD16":"340.0","Inception Score":"62.88"},"uses_additional_data":false,"paper_date":"2024-03-30","paper":"/paper/grid-diffusion-models-for-text-to-video-1","paper_url":"https://arxiv.org/abs/2404.00234v2","paper_title":"Grid Diffusion Models for Text-to-Video Generation","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":28,"model":"VideoAssembler (Zero-shot, 256x256, class-conditional)","metrics":{"FVD16":"346.84","Inception Score":"48.01"},"uses_additional_data":false,"paper_date":"2023-11-29","paper":"/paper/videoassembler-identity-consistent-video","paper_url":"https://arxiv.org/abs/2311.17338v3","paper_title":"MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing","code":"https://github.com/gulucaptain/videoassembler","n_code_links":1,"syntology":{"n_ran":10,"n_unverified":2,"n_samples":12,"n_pointer_only_licence":12}},{"rank_in_archive_order":29,"model":"VideoPoet (text-conditional)","metrics":{"FVD16":"355","Inception Score":"38.44"},"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":30,"model":"PYoCo (Zero-shot, 64x64, text-conditional)","metrics":{"FVD16":"355.19","Inception Score":"47.76"},"uses_additional_data":false,"paper_date":"2023-05-17","paper":"/paper/preserve-your-own-correlation-a-noise-prior","paper_url":"https://arxiv.org/abs/2305.10474v3","paper_title":"Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models","code":null,"n_code_links":0,"syntology":null},{"rank_in_archive_order":31,"model":"Make-A-Video (Zero-shot, 256x256, class-conditional)","metrics":{"FVD16":"367.23","Inception Score":"33"},"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":32,"model":"LVDM (256x256, unconditional)","metrics":{"FVD16":"372","KVD16":"27"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/latent-video-diffusion-models-for-high","paper_url":"https://arxiv.org/abs/2211.13221v2","paper_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","code":"https://github.com/yingqinghe/lvdm","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":33,"model":"MMVG (128x128, unconditional)","metrics":{"FVD16":"395","Inception Score":"58.3"},"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":34,"model":"TATS (128x128, unconditional)","metrics":{"FVD16":"420","Inception Score":"57.63"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/long-video-generation-with-time-agnostic","paper_url":"https://arxiv.org/abs/2204.03638v4","paper_title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","code":"https://github.com/songweige/tats","n_code_links":1,"syntology":null},{"rank_in_archive_order":35,"model":"MeBT (128x128, unconditional)","metrics":{"FVD128":"968","FVD16":"438","Inception Score":"65.93"},"uses_additional_data":false,"paper_date":"2023-03-20","paper":"/paper/towards-end-to-end-generative-modeling-of","paper_url":"https://arxiv.org/abs/2303.11251v3","paper_title":"Towards End-to-End Generative Modeling of Long Videos with Memory-Efficient Bidirectional Transformers","code":"https://github.com/Ugness/MeBT","n_code_links":1,"syntology":null},{"rank_in_archive_order":36,"model":"DIGAN (128x128, class-conditional)","metrics":{"FVD16":"465","Inception Score":"59.68","KVD16":"39.6"},"uses_additional_data":false,"paper_date":"2022-02-21","paper":"/paper/generating-videos-with-dynamics-aware-1","paper_url":"https://arxiv.org/abs/2202.10571v1","paper_title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","code":"https://github.com/sihyun-yu/digan","n_code_links":1,"syntology":null},{"rank_in_archive_order":37,"model":"LAVIE (320x512, text-conditional)","metrics":{"FVD16":"526.30"},"uses_additional_data":false,"paper_date":"2023-09-26","paper":"/paper/lavie-high-quality-video-generation-with","paper_url":"https://arxiv.org/abs/2309.15103v2","paper_title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","code":"https://github.com/Vchitect/LaVie","n_code_links":2,"syntology":{"n_ran":1,"n_unverified":1,"n_samples":2,"n_pointer_only_licence":0}},{"rank_in_archive_order":38,"model":"Video LDM (320x512, text-conditional)","metrics":{"FVD16":"550.61","Inception Score":"33.45"},"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":39,"model":"LVDM (256x256, unconditional)","metrics":{"FVD16":"552","KVD16":"42"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/latent-video-diffusion-models-for-high","paper_url":"https://arxiv.org/abs/2211.13221v2","paper_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","code":"https://github.com/yingqinghe/lvdm","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":40,"model":"DIGAN (128x128, unconditional)","metrics":{"FVD16":"577","Inception Score":"32.70"},"uses_additional_data":false,"paper_date":"2022-02-21","paper":"/paper/generating-videos-with-dynamics-aware-1","paper_url":"https://arxiv.org/abs/2202.10571v1","paper_title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","code":"https://github.com/sihyun-yu/digan","n_code_links":1,"syntology":null},{"rank_in_archive_order":41,"model":"TATS (256x256)","metrics":{"FVD16":"635","KVD16":"55"},"uses_additional_data":false,"paper_date":"2022-04-07","paper":"/paper/long-video-generation-with-time-agnostic","paper_url":"https://arxiv.org/abs/2204.03638v4","paper_title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","code":"https://github.com/songweige/tats","n_code_links":1,"syntology":null},{"rank_in_archive_order":42,"model":"MagicVideo (256x256, text-conditional)","metrics":{"FVD16":"699"},"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":43,"model":"MoCoGAN-HD (256x256, unconditional)","metrics":{"FVD16":"700","Inception Score":"33.95"},"uses_additional_data":false,"paper_date":"2021-04-30","paper":"/paper/a-good-image-generator-is-what-you-need-for-1","paper_url":"https://arxiv.org/abs/2104.15069v1","paper_title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","code":"https://github.com/snap-research/MoCoGAN-HD","n_code_links":1,"syntology":null},{"rank_in_archive_order":44,"model":"MCVD (64x64)","metrics":{"FVD16":"1143"},"uses_additional_data":false,"paper_date":"2022-05-19","paper":"/paper/masked-conditional-video-diffusion-for","paper_url":"https://arxiv.org/abs/2205.09853v4","paper_title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","code":"https://github.com/voletiv/mcvd-pytorch","n_code_links":2,"syntology":{"n_ran":7,"n_unverified":9,"n_samples":16,"n_pointer_only_licence":0}},{"rank_in_archive_order":45,"model":"TGAN-v2 (128x128)","metrics":{"FVD16":"1209"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/latent-video-diffusion-models-for-high","paper_url":"https://arxiv.org/abs/2211.13221v2","paper_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","code":"https://github.com/yingqinghe/lvdm","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":46,"model":"VDM","metrics":{"FVD16":"1396","KVD16":"116"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/latent-video-diffusion-models-for-high","paper_url":"https://arxiv.org/abs/2211.13221v2","paper_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","code":"https://github.com/yingqinghe/lvdm","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":47,"model":"MCVD","metrics":{"FVD16":"2460","KVD16":"148"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/latent-video-diffusion-models-for-high","paper_url":"https://arxiv.org/abs/2211.13221v2","paper_title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","code":"https://github.com/yingqinghe/lvdm","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":5,"n_samples":14,"n_pointer_only_licence":0}},{"rank_in_archive_order":48,"model":"\bFIFO-Diffusion","metrics":{"FVD128":"596.64","Inception Score":"74.44"},"uses_additional_data":false,"paper_date":"2024-05-19","paper":"/paper/fifo-diffusion-generating-infinite-videos","paper_url":"https://arxiv.org/abs/2405.11473v4","paper_title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","code":"https://github.com/jjihwan/FIFO-Diffusion_public","n_code_links":1,"syntology":{"n_ran":9,"n_unverified":4,"n_samples":13,"n_pointer_only_licence":13}}],"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":22,"rows_with_any_sample_ran":22,"distinct_papers_with_graph_line":15,"distinct_papers_with_any_sample_ran":15,"samples_over_distinct_papers":{"n_ran":86,"n_unverified":65,"n_samples":151,"n_pointer_only_licence":32,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":136,"n_unverified":111,"n_samples":247,"n_pointer_only_licence":32,"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"}}}