{"id":54805,"url":"https://github.com/ChenHsing/Awesome-Video-Diffusion-Models","name":"Awesome-Video-Diffusion-Models","description":"[CSUR] A Survey on Video Diffusion Models","projects_count":375,"last_synced_at":"2026-08-02T05:00:21.940Z","repository":{"id":185303149,"uuid":"673277480","full_name":"ChenHsing/Awesome-Video-Diffusion-Models","owner":"ChenHsing","description":"[CSUR] A Survey on Video Diffusion Models","archived":false,"fork":false,"pushed_at":"2026-06-22T10:57:06.000Z","size":170048,"stargazers_count":2301,"open_issues_count":0,"forks_count":116,"subscribers_count":53,"default_branch":"main","last_synced_at":"2026-07-14T01:03:41.030Z","etag":null,"topics":["awesome","awesome-list","diffusion","diffusion-models","survey","text-to-video","video","video-diffusion","video-diffusion-model","video-editing"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/ChenHsing.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2023-08-01T09:15:28.000Z","updated_at":"2026-07-12T21:10:30.000Z","dependencies_parsed_at":"2023-10-15T09:56:25.306Z","dependency_job_id":"8480f2c8-c599-43f3-89d2-82d448cdea6b","html_url":"https://github.com/ChenHsing/Awesome-Video-Diffusion-Models","commit_stats":null,"previous_names":["chenhsing/awesome-video-diffusion-models"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ChenHsing/Awesome-Video-Diffusion-Models","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenHsing%2FAwesome-Video-Diffusion-Models","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenHsing%2FAwesome-Video-Diffusion-Models/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenHsing%2FAwesome-Video-Diffusion-Models/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenHsing%2FAwesome-Video-Diffusion-Models/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ChenHsing","download_url":"https://codeload.github.com/ChenHsing/Awesome-Video-Diffusion-Models/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ChenHsing%2FAwesome-Video-Diffusion-Models/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36180050,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-07-20T02:08:10.276Z","status":"online","status_checked_at":"2026-08-02T02:00:06.915Z","response_time":58,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-19T09:12:31.791Z","updated_at":"2026-08-02T05:00:21.940Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Video Editing","Uncategorized","Unconditional Video Generation","Video Generation with other conditions","Depth-guided Video Generation","Text-to-Video Generation","Video Completion","Data","Open-source Toolboxes and Foundation Models","Contact"],"sub_categories":["General Editing Model","Uncategorized","Transformer based","Image-guided Video Generation","U-Net based","Brain-guided Video Generation","Motion-guided  Video Generation","Multi-modal guided Video Generation","Pose-guided Video Generation","Training-based","Video Enhancement and Restoration","Multi-modal Control Editing Model","Training-free Editing Model","Training-free","Sound-guided Video Generation","One-shot Editing Model","Domain-specific Editing Model","Sound-guided Video Editing","Category-level","Video Understanding","Video Prediction","Metric and BenchMark","Non-diffusion Editing model","Instruct-guided Video Editing","Motion-guided Video Editing","Caption-level"],"readme":"\n# [A Survey on Video Diffusion Models](https://arxiv.org/abs/2310.10647) [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome)  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.10647) \n\n\n\u003cdiv style=\"text-align:center; font-size: 18px;\"\u003e\n    \u003cp\u003e\n    \u003ca href=\"https://chenhsing.github.io\"\u003eZhen Xing\u003c/a\u003e, \n    Qijun Feng,\n    Haoran Chen,\n    \u003ca href=\"https://scholar.google.com/citations?user=NSJY12IAAAAJ\u0026hl=zh-CN\" \u003eQi Dai,\u003c/a\u003e\n    \u003ca href=\"https://scholar.google.com/citations?user=Jkss014AAAAJ\u0026hl=zh-CN\u0026oi=ao\" \u003eHan Hu,\u003c/a\u003e\n    \u003ca href=\"https://scholar.google.com/citations?user=J_8TX6sAAAAJ\u0026hl=zh-CN\u0026oi=ao\" \u003eHang Xu,\u003c/a\u003e\n    \u003ca href=\"https://scholar.google.com/citations?user=7t12hVkAAAAJ\u0026hl=en\" \u003eZuxuan Wu,\u003c/a\u003e\n    \u003ca href=\"https://scholar.google.com/citations?user=f3_FP8AAAAAJ\u0026hl=en\" \u003eYu-Gang Jiang \u003c/a\u003e\n     \u003c/p\u003e\n\u003c/div\u003e\n\n\n\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"asset/fish.webp\" width=\"160px\"/\u003e\n\u003cimg src=\"asset/tree.gif\" width=\"160px\"/\u003e    \n\u003cimg src=\"asset/raccoon.gif\" width=\"160px\"/\u003e    \n\u003c/p\u003e\n\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"asset/svd.gif\" width=\"240px\"/\u003e  \n\u003cimg src=\"asset/fly3.gif\" width=\"240px\"/\u003e  \n\u003c/p\u003e\n\n\n\u003cp align=\"center\"\u003e\n\u003cimg src=\"asset/1.gif\" width=\"120px\"/\u003e\n\u003cimg src=\"asset/2.gif\" width=\"120px\"/\u003e\n\u003cimg src=\"asset/3.gif\" width=\"120px\"/\u003e\n\u003cimg src=\"asset/4.gif\" width=\"120px\"/\u003e\n\u003c/p\u003e\n\n\n\u003cp align=\"center\"\u003e\n(Source: \u003ca href=\"https://makeavideo.studio/\"\u003eMake-A-Video\u003c/a\u003e, \u003ca href=\"https://chenhsing.github.io/SimDA/\"\u003eSimDA\u003c/a\u003e, \u003ca href=\"https://research.nvidia.com/labs/dir/pyoco/\"\u003ePYoCo\u003c/a\u003e, \u003ca href=\"https://img.shields.io/badge/Website-9cf\"\u003e SVD \u003c/a\u003e,\n\u003ca href=\"https://research.nvidia.com/labs/toronto-ai/VideoLDM/\"\u003eVideo LDM\u003c/a\u003e and \u003ca href=\"https://tuneavideo.github.io/\"\u003eTune-A-Video\u003c/a\u003e)\n\u003c/p\u003e\n\n- [News] The updated version is available on [arXiv](https://arxiv.org/abs/2310.10647).\n- [News] \u003cspan style=\"color:red;\"\u003e **Our survey is accepted by ACM Computing Surveys (CSUR).**\u003c/span\u003e\n- [News] The Chinese translation is available on [Zhihu](https://zhuanlan.zhihu.com/p/661860981). Special thanks to [Dai-Wenxun](https://github.com/Dai-Wenxun) for this.\n\n\n## Contact\nIf you have any suggestions or find our work helpful, feel free to contact us\n\nHomepage: [Zhen Xing](https://chenhsing.github.io)\n\nEmail: zhenxingfd@gmail.com\n\n\nIf you find our survey is useful in your research or applications, please consider giving us a star 🌟 and citing it by the following BibTeX entry.\n\n```\n@article{xing2023survey,\n  title={A survey on video diffusion models},\n  author={Xing, Zhen and Feng, Qijun and Chen, Haoran and Dai, Qi and Hu, Han and Xu, Hang and Wu, Zuxuan and Jiang, Yu-Gang},\n  journal={ACM Computing Surveys},\n  year={2023},\n  publisher={ACM New York, NY}\n}\n```\n\n\n\n\n## Open-source Toolboxes and Foundation Models \n\n| Methods | Task | Github|\n|:-----:|:-----:|:-----:|\n| [Helios](https://github.com/PKU-YuanGroup/Helios)  | T2V Generation | [![Star](https://img.shields.io/github/stars/PKU-YuanGroup/Helios.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/Helios)|\n| [Movie Gen](https://ai.meta.com/research/movie-gen/)  | T2V Generation | -|\n| [CogVideoX](https://github.com/THUDM/CogVideo)  | T2V Generation | [![Star](https://img.shields.io/github/stars/THUDM/CogVideo.svg?style=social\u0026label=Star)](https://github.com/THUDM/CogVideo)|\n| [Open-Sora-Plan](https://github.com/PKU-YuanGroup/Open-Sora-Plan/blob/main/docs/Report-v1.0.0.md)  | T2V Generation | [![Star](https://img.shields.io/github/stars/PKU-YuanGroup/Open-Sora-Plan.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/Open-Sora-Plan)|\n| [Open-Sora](https://github.com/hpcaitech/Open-Sora/blob/main/docs/zh_CN/README.md)  | T2V Generation | [![Star](https://img.shields.io/github/stars/hpcaitech/Open-Sora.svg?style=social\u0026label=Star)](https://github.com/hpcaitech/Open-Sora)|\n| [Morph Studio](https://app.morphstudio.com/)  | T2V Generation | -|\n| [Genie](https://sites.google.com/view/genie-2024/home)  | T2V Generation | -|\n| [Sora](https://openai.com/sora)  | T2V Generation \u0026 Editing | -|\n| [VideoPoet](https://blog.research.google/2023/12/videopoet-large-language-model-for-zero.html)  | T2V Generation \u0026 Editing | -|\n| [Stable Video Diffusion](https://stability.ai/news/stable-video-diffusion-open-ai-video-model)  | T2V Generation | [![Star](https://img.shields.io/github/stars/Stability-AI/generative-models.svg?style=social\u0026label=Star)](https://github.com/Stability-AI/generative-models)|\n| [NeverEnds](https://neverends.life)   | T2V Generation | - |\n| [Pika](https://pika.art)   | T2V Generation | - |\n| [EMU-Video](https://emu-video.metademolab.com/)   | T2V Generation | - |\n| [GEN-2](https://app.runwayml.com/)   | T2V Generation \u0026 Editing | - |\n| [ModelScope](https://modelscope.cn/models/damo/text-to-video-synthesis/summary)  | T2V Generation | [![Star](https://img.shields.io/github/stars/modelscope/modelscope.svg?style=social\u0026label=Star)](https://github.com/modelscope/modelscope) |\n| [ZeroScope](https://easywithai.com/ai-video-generators/zeroscope/)  | T2V Generation | -|\n| [T2V Synthesis Colab](https://github.com/camenduru/text-to-video-synthesis-colab) | T2V Genetation |[![Star](https://img.shields.io/github/stars/camenduru/text-to-video-synthesis-colab.svg?style=social\u0026label=Star)](https://github.com/camenduru/text-to-video-synthesis-colab)|\n| [VideoCraft](https://github.com/VideoCrafter/VideoCrafter) | T2V Genetation \u0026 Editing |[![Star](https://img.shields.io/github/stars/VideoCrafter/VideoCrafter.svg?style=social\u0026label=Star)](https://github.com/VideoCrafter/VideoCrafter)|\n| [Diffusers (T2V synthesis)](https://huggingface.co/docs/diffusers/main/en/api/pipelines/text_to_video#texttovideo-synthesis) | T2V Genetation |-|\n| [AnimateDiff](https://github.com/guoyww/AnimateDiff) | Personalized T2V Genetation |[![Star](https://img.shields.io/github/stars/guoyww/AnimateDiff.svg?style=social\u0026label=Star)](https://github.com/guoyww/AnimateDiff)|\n| [Text2Video-Zero](https://github.com/Picsart-AI-Research/Text2Video-Zero) |  T2V Genetation |[![Star](https://img.shields.io/github/stars/Picsart-AI-Research/Text2Video-Zero.svg?style=social\u0026label=Star)](https://github.com/Picsart-AI-Research/Text2Video-Zero)|\n| [HotShot-XL](https://github.com/hotshotco/Hotshot-XL) |  T2V Genetation |[![Star](https://img.shields.io/github/stars/hotshotco/Hotshot-XL.svg?style=social\u0026label=Star)](https://github.com/hotshotco/Hotshot-XL)|\n| [Genmo](https://www.genmo.ai/) |  T2V Genetation |-|\n| [Fliki](https://fliki.ai/) | T2V Generation | -|\n| [Seedream AI Studio](https://seedream4.video/) | Image Generation + I2V Animation | -|\n\n\n\n## Table of Contents \n\n- [Video Generation](#video-generation)\n- - [Data](#data)\n- - - [Caption-level](#caption-level)\n- - - [Category-level](#category-level)\n- - [T2V Generation](#text-to-video-generation)\n- - - [Training-based](#training-based)\n- - - [Training-free](#training-free)\n- - [Video Generation with other Condtions](#modality-control-video-generation)\n- - - [Pose-gudied](#pose-guided-video-generation)\n- - - [Instruct-guided](#instruct-guided-video-generation)\n- - - [Sound-guided](#sound-guided-video-generation)\n- - - [Brain-guided](#brain-guided-video-generation)\n- - - [Multi-Modal guided](#multi-modal-guided-video-generation)\n- - [Unconditional Video Generation](#domain-specific-video-generation)\n- - - [U-Net based](#category-specific)\n- - - [Transformer-based](#personalized-video)\n- - [Video Completion](#video-completion)\n- - - [Video Enhance and Restoration](#video-enhancement-and-restoration)\n- - - [Video Prediction](#video-prediction)\n- [Video Editing](#video-editing)\n- - [Text guided Video Editing](#text-guided-video-editing)\n- - - [Training-based Editing](#general-editing-model)\n- - - [One-shot Editing](#one-shot-editing-model)\n- - - [Traning-free](#training-free-editing-model)\n- - [Modality-guided Video Editing](#modality-guided)\n- - - [Motion-guided](#motion-guided-editing-model)\n- - - [Instruct-guided](#instruct-guided-editing-model)\n- - - [Sound-guided](#sound-guided-editing-model)\n- - - [Multi-Modal Control](#multi-modal-control-editing-model)\n- - [Domain-specific editing](#domain-specific-editing-model)\n- - [Non-diffusion editing](#non-diffusion-editing-Model)\n- [Video Understanding](#video-understanding)\n- [Contact](#Contact)\n\n\n\n\n\n\n\n# Video Generation\n\n## Data \n\n### Caption-level\n\n| Title | arXiv | Github| WebSite | Pub. \u0026 Date\n|:-----:|:-----:|:-----:|:-----:|:-----:|\n| [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://arxiv.org/abs/2505.20292) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2505.20292) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/OpenS2V-Nexus.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/OpenS2V-Nexus)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/OpenS2V-Nexus) | May, 2025 |\n| [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/abs/2411.17440) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2411.17440) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/ConsisID.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/ConsisID)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/ConsisID/) | CVPR, 2025 |\n|[ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation](https://arxiv.org/abs/2406.18522) |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.18522)|   [![Star](https://img.shields.io/github/stars/PKU-YuanGroup/ChronoMagic-Bench.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/ChronoMagic-Bench)| [![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/ChronoMagic-Bench/)  | NeurIPS, 2024 |\n|[Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://arxiv.org/abs/2402.19479) |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.19479)|   [![Star](https://img.shields.io/github/stars/snap-research/Panda-70M.svg?style=social\u0026label=Star)](https://github.com/snap-research/Panda-70M)| [![Website](https://img.shields.io/badge/Website-9cf)](https://snap-research.github.io/Panda-70M/)  | CVPR, 2024 |\n|[CelebV-Text: A Large-Scale Facial Text-Video Dataset](https://arxiv.org/pdf/2303.14717.pdf)|  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2303.14717.pdf) |   [![Star](https://img.shields.io/github/stars/CelebV-Text/CelebV-Text.svg?style=social\u0026label=Star)](https://github.com/CelebV-Text/CelebV-Text) | - | CVPR, 2023\n|[InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://arxiv.org/abs/2307.06942) |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2307.06942)|   [![Star](https://img.shields.io/github/stars/OpenGVLab/InternVideo.svg?style=social\u0026label=Star)](https://github.com/OpenGVLab/InternVideo/tree/main/Data/InternVid)| - | May, 2023 |\n|[VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation](https://arxiv.org/abs/2305.10874)| [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.10874) | - | - | May, 2023|\n|[Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://arxiv.org/abs/2111.10337)  |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2111.10337)|- |- |Nov, 2021 |\n| [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://arxiv.org/abs/2104.00650) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2104.00650)  | - | - |ICCV, 2021 |\n|[MSR-VTT: A Large Video Description Dataset for Bridging Video and Language](https://openaccess.thecvf.com/content_cvpr_2016/html/Xu_MSR-VTT_A_Large_CVPR_2016_paper.html) |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://openaccess.thecvf.com/content_cvpr_2016/html/Xu_MSR-VTT_A_Large_CVPR_2016_paper.html) | -| -| CVPR, 2016|\n\n\n\n\n### Category-level\n\n\n| Title | arXiv | Github| WebSite | Pub. \u0026 Date\n|:-----:|:-----:|:-----:|:-----:|:-----:|\n|[UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild](https://arxiv.org/abs/1212.0402)|  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/1212.0402) |   - | - | Dec., 2012\n|[First Order Motion Model for Image Animation](https://arxiv.org/abs/2003.00196) |     [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2003.00196) | -|- | May, 2023 |\n|[Learning to Generate Time-Lapse Videos Using Multi-Stage Dynamic Generative Adversarial Networks](https://arxiv.org/abs/1709.07592) |   [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/1709.07592) | -| -| CVPR,2018|\n\n\n\n### Metric and BenchMark\n\n| Title | arXiv | Github| WebSite | Pub. \u0026 Date\n|:-----:|:-----:|:-----:|:-----:|:-----:|\n| [OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation](https://arxiv.org/abs/2505.20292) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2505.20292) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/OpenS2V-Nexus.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/OpenS2V-Nexus)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/OpenS2V-Nexus) | May, 2025 |\n|[Fréchet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos](https://arxiv.org/abs/2407.16124) |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2407.16124)|   [![Star](https://img.shields.io/github/stars/DSL-Lab/FVMD-frechet-video-motion-distance.svg?style=social\u0026label=Star)](https://github.com/DSL-Lab/FVMD-frechet-video-motion-distance)| -  | Jul., 2024 |\n|[ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation](https://arxiv.org/abs/2406.18522) |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.18522)|   [![Star](https://img.shields.io/github/stars/PKU-YuanGroup/ChronoMagic-Bench.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/ChronoMagic-Bench)| [![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/ChronoMagic-Bench/)  | NeurIPS, 2024 |\n| [STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models](https://arxiv.org/abs/2403.09669) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.09669) |[![Star](https://img.shields.io/github/stars/pro2nit/STREAM.svg?style=social\u0026label=Star)](https://github.com/pro2nit/STREAM)|- | ICLR, 2024\n| [Subjective-Aligned Dateset and Metric for Text-to-Video Quality Assessment](https://arxiv.org/abs/2403.11956) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.11956) |-|- | Mar, 2024\n| [Towards A Better Metric for Text-to-Video Generation](https://arxiv.org/abs/2401.07781) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.07781) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://showlab.github.io/T2VScore/) | Jan, 2024\n|[AIGCBench: Comprehensive Evaluation of Image-to-Video Content Generated by AI](https://arxiv.org/abs/2401.01651) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.01651)  |   - | - | Jan, 2024 |\n| [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://arxiv.org/abs/2311.17982) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.17982) |[![Star](https://img.shields.io/github/stars/Vchitect/VBench.svg?style=social\u0026label=Star)](https://github.com/Vchitect/VBench)|[![Website](https://img.shields.io/badge/Website-9cf)](https://vchitect.github.io/VBench-project/) | Nov, 2023\n|[FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation](https://arxiv.org/abs/2311.01813) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.01813)  |   - | - | NeurIPS, 2023 |\n|[CVPR 2023 Text Guided Video Editing Competition](https://arxiv.org/abs/2310.16003) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.16003)  |   - | - | Oct., 2023 |\n|[EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://arxiv.org/abs/2310.11440) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.11440)  | [![Star](https://img.shields.io/github/stars/evalcrafter/EvalCrafter.svg?style=social\u0026label=Star)](https://github.com/evalcrafter/EvalCrafter)|[![Website](https://img.shields.io/badge/Website-9cf)](https://huggingface.co/datasets/RaphaelLiu/EvalCrafter_T2V_Dataset) | Oct., 2023 |\n|[Measuring the Quality of Text-to-Video Model Outputs: Metrics and Dataset](https://arxiv.org/abs/2309.08009) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.08009)  |   - | - | Sep., 2023 |\n\n\n\n\n\n## Text-to-Video Generation\n### Training-based \n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n| [Helios: Real Real-Time Long Video Generation Model](https://arxiv.org/abs/2603.04379) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2603.04379) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/Helios.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/Helios)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/Helios-Page/) | Arxiv, 2026\n| [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/abs/2411.17440) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2411.17440) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/ConsisID.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/ConsisID)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/ConsisID/) | CVPR, 2025\n| [Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning](https://arxiv.org/abs/2410.24219) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2410.24219) |[![Star](https://img.shields.io/github/stars/PR-Ryan/DEMO.svg?style=social\u0026label=Star)](https://github.com/PR-Ryan/DEMO)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pr-ryan.github.io/DEMO-project/)| NeurIPS 2024\n| [Movie Gen](https://ai.meta.com/research/movie-gen/) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://ai.meta.com/static-resource/movie-gen-research-paper) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://ai.meta.com/research/movie-gen/) | Oct, 2024\n| [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://arxiv.org/abs/2408.06072) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2408.06072) |[![Star](https://img.shields.io/github/stars/THUDM/CogVideo.svg?style=social\u0026label=Star)](https://github.com/THUDM/CogVideo)|-| Oct, 2024\n| [Grid Diffusion Models for Text-to-Video Generation](https://arxiv.org/abs/2404.00234) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2404.00234) |[![Star](https://img.shields.io/github/stars/taegyeong-lee/Grid-Diffusion-Models-for-Text-to-Video-Generation.svg?style=social\u0026label=Star)](https://github.com/taegyeong-lee/Grid-Diffusion-Models-for-Text-to-Video-Generation)|[![Website](https://img.shields.io/badge/Website-9cf)](https://taegyeong-lee.github.io/text2video) | CVPR, 2024\n| [MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators](https://arxiv.org/abs/2404.05014) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2404.05014) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/MagicTime.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/MagicTime)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/MagicTime/) | Apr., 2024\n| [Mora: Enabling Generalist Video Generation via A Multi-Agent Framework](https://arxiv.org/abs/2403.13248) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.13248) |-|- | Mar., 2024\n| [VSTAR: Generative Temporal Nursing for Longer Dynamic Video Synthesis](https://arxiv.org/abs/2403.13501) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.13501) |-|- | Mar., 2024\n| [Genie: Generative Interactive Environments](https://arxiv.org/abs/2402.15391) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.15391) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://sites.google.com/view/genie-2024/home) | Feb., 2024\n| [Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis](https://arxiv.org/abs/2402.14797) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.14797) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://snap-research.github.io/snapvideo/) | Feb., 2024\n| [Lumiere: A Space-Time Diffusion Model for Video Generation](https://arxiv.org/abs/2401.12945) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.12945) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://lumiere-video.github.io/) | Jan, 2024\n| [UNIVG: TOWARDS UNIFIED-MODAL VIDEO GENERATION](https://arxiv.org/abs/2401.09084) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.09084) |-| [![Website](https://img.shields.io/badge/Website-9cf)](https://univg-baidu.github.io/) | Jan, 2024\n| [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://arxiv.org/abs/2401.09047) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.09047) |[![Star](https://img.shields.io/github/stars/VideoCrafter/VideoCrafter.svg?style=social\u0026label=Star)](https://github.com/VideoCrafter/VideoCrafter)|[![Website](https://img.shields.io/badge/Website-9cf)](https://ailab-cvc.github.io/videocrafter/) | Jan, 2024\n| [360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model](https://arxiv.org/abs/2401.06578) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.06578) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://akaneqwq.github.io/360DVD/) | Jan, 2024\n| [MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation](https://arxiv.org/abs/2401.04468) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.04468) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://magicvideov2.github.io/) | Jan, 2024\n| [VideoDrafter: Content-Consistent Multi-Scene Video Generation with LLM](https://arxiv.org/abs/2401.01256) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.01256) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://videodrafter.github.io/) | Jan, 2024\n| [A Recipe for Scaling up Text-to-Video Generation with Text-free Videos](https://arxiv.org/abs/2312.15770) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.15770) |[![Star](https://img.shields.io/github/stars/damo-vilab/i2vgen-xl.svg?style=social\u0026label=Star)](https://github.com/damo-vilab/i2vgen-xl)|[![Website](https://img.shields.io/badge/Website-9cf)](https://tf-t2v.github.io/) | Dec, 2023\n| [InstructVideo: Instructing Video Diffusion Models with Human Feedback](https://arxiv.org/abs/2312.12490) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.12490) |[![Star](https://img.shields.io/github/stars/damo-vilab/i2vgen-xl.svg?style=social\u0026label=Star)](https://github.com/damo-vilab/i2vgen-xl)|[![Website](https://img.shields.io/badge/Website-9cf)](https://instructvideo.github.io/) | Dec, 2023\n| [VideoLCM: Video Latent Consistency Model](https://arxiv.org/abs/2312.09109) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.09109) |-|- | Dec, 2023\n| [Photorealistic Video Generation with Diffusion Models](https://arxiv.org/abs/2312.06662) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.06662) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://walt-video-diffusion.github.io/) | Dec, 2023\n| [Hierarchical Spatio-temporal Decoupling for Text-to-Video Generation](https://arxiv.org/abs/2312.04483) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.04483) |[![Star](https://img.shields.io/github/stars/damo-vilab/i2vgen-xl.svg?style=social\u0026label=Star)](https://github.com/damo-vilab/i2vgen-xl)|[![Website](https://img.shields.io/badge/Website-9cf)](https://higen-t2v.github.io/) | Dec, 2023\n| [Delving Deep into Diffusion Transformers for Image and Video Generation](https://arxiv.org/abs/2312.04557) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.04557) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://www.shoufachen.com/gentron_website/) | Dec, 2023\n| [StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter](https://arxiv.org/abs/2312.00330) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.00330) |[![Star](https://img.shields.io/github/stars/GongyeLiu/StyleCrafter.svg?style=social\u0026label=Star)](https://github.com/GongyeLiu/StyleCrafter)|[![Website](https://img.shields.io/badge/Website-9cf)](https://gongyeliu.github.io/StyleCrafter.github.io/) | Nov, 2023\n| [MicroCinema: A Divide-and-Conquer Approach for Text-to-Video Generation](https://arxiv.org/abs/2311.18829) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.18829) |- |[![Website](https://img.shields.io/badge/Website-9cf)](https://wangyanhui666.github.io/MicroCinema.github.io/) | Nov, 2023\n| [ART•V: Auto-Regressive Text-to-Video Generation with Diffusion Models](https://arxiv.org/abs/2311.18834) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.18834) |[![Star](https://img.shields.io/github/stars/WarranWeng/ART.V.svg?style=social\u0026label=Star)](https://github.com/WarranWeng/ART.V) |[![Website](https://img.shields.io/badge/Website-9cf)](https://warranweng.github.io/art.v) | Nov, 2023\n| [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://arxiv.org/abs/2311.15127) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.15127) |[![Star](https://img.shields.io/github/stars/Stability-AI/generative-models.svg?style=social\u0026label=Star)](https://github.com/Stability-AI/generative-models)|[![Website](https://img.shields.io/badge/Website-9cf)](https://huggingface.co/stabilityai/stable-video-diffusion-img2vid) | Nov, 2023\n| [FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline](https://arxiv.org/abs/2311.13073) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.13073) | [![Star](https://img.shields.io/github/stars/ai-forever/KandinskyVideo.svg?style=social\u0026label=Star)](https://github.com/ai-forever/KandinskyVideo) |[![Website](https://img.shields.io/badge/Website-9cf)](https://ai-forever.github.io/kandinsky-video/)| Nov, 2023\n| [MoVideo: Motion-Aware Video Generation with Diffusion Models](https://arxiv.org/abs/2311.11325) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.11325) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://jingyunliang.github.io/MoVideo/)| Nov, 2023\n| [Make Pixels Dance: High-Dynamic Video Generation](https://arxiv.org/abs/2311.10982) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.10982) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://makepixelsdance.github.io/)| Nov, 2023\n| [Emu Video: Factorizing Text-to-Video Generation by Explicit Image Conditioning](https://arxiv.org/abs/2311.10709) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.10709) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://emu-video.metademolab.com/)| Nov, 2023\n| [Optimal Noise pursuit for Augmenting Text-to-Video Generation](https://arxiv.org/abs/2311.00949) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.00949) |-|-| Nov, 2023\n| [VideoDreamer: Customized Multi-Subject Text-to-Video Generation with Disen-Mix Finetuning](https://arxiv.org/abs/2311.00990) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.00990) |-|[![Website](https://img.shields.io/badge/Website-9cf)](https://videodreamer23.github.io/) | Nov, 2023\n| [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://arxiv.org/abs/2310.19512) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.19512) |[![Star](https://img.shields.io/github/stars/VideoCrafter/VideoCrafter.svg?style=social\u0026label=Star)](https://github.com/VideoCrafter/VideoCrafter)|[![Website](https://img.shields.io/badge/Website-9cf)](https://ailab-cvc.github.io/videocrafter/) | Oct, 2023\n|[SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction](https://arxiv.org/abs/2310.20700) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.20700)  | [![Star](https://img.shields.io/github/stars/Vchitect/SEINE?style=social)](https://github.com/Vchitect/SEINE) | [![Website](https://img.shields.io/badge/Website-9cf)](https://vchitect.github.io/SEINE-project/) | Oct, 2023 |\n|[DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://arxiv.org/abs/2310.12190) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.12190) | [![Star](https://img.shields.io/github/stars/AILab-CVC/VideoCrafter.svg?style=social\u0026label=Star)](https://github.com/AILab-CVC/VideoCrafter) | [![Website](https://img.shields.io/badge/Website-9cf)](https://ailab-cvc.github.io/videocrafter/) | Oct., 2023 |\n|[LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation](https://arxiv.org/abs/2310.10769) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.10769) | [![Star](https://img.shields.io/github/stars/RQ-Wu/LAMP.svg?style=social\u0026label=Star)](https://github.com/RQ-Wu/LAMP) | [![Website](https://img.shields.io/badge/Website-9cf)](https://rq-wu.github.io/projects/LAMP/) | Oct., 2023 |\n|[DrivingDiffusion: Layout-Guided multi-view driving scene video generation with latent diffusion model](https://arxiv.org/abs/2310.07771) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.07771) | [![Star](https://img.shields.io/github/stars/shalfun/DrivingDiffusion.svg?style=social\u0026label=Star)](https://github.com/shalfun/DrivingDiffusion) | [![Website](https://img.shields.io/badge/Website-9cf)](https://drivingdiffusion.github.io/) | Oct, 2023 |\n|[MotionDirector: Motion Customization of Text-to-Video Diffusion Models](https://arxiv.org/abs/2310.08465) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.08465)  | [![Star](https://img.shields.io/github/stars/showlab/MotionDirector?style=social)](https://github.com//showlab/MotionDirector) | [![Website](https://img.shields.io/badge/Website-9cf)](https://showlab.github.io/MotionDirector/) | Oct, 2023 |\n|[VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://arxiv.org/abs/2309.15091) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.15091)  |   [![Star](https://img.shields.io/github/stars/HL-hanlin/VideoDirectorGPT.svg?style=social\u0026label=Star)](https://github.com/HL-hanlin/VideoDirectorGPT) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://videodirectorgpt.github.io/) | Sep., 2023 |\n|[Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://arxiv.org/abs/2309.15818) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.15818)  | [![Star](https://img.shields.io/github/stars/showlab/Show-1?style=social)](https://github.com//showlab/Show-1) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://showlab.github.io/Show-1/) | Sep., 2023 |\n|[LaVie: High-Quality Video Generation with Cascaded Latent Diffusion Models](https://arxiv.org/abs/2309.15103) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.15103)  |   [![Star](https://img.shields.io/github/stars/Vchitect/LaVie.svg?style=social\u0026label=Star)](https://github.com/Vchitect/LaVie) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://vchitect.github.io/LaVie-project/) | Sep., 2023 |\n|[Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation](https://arxiv.org/abs/2309.03549) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.03549)  |   [![Star](https://img.shields.io/github/stars/anonymous0x233/ReuseAndDiffuse.svg?style=social\u0026label=Star)](https://github.com/anonymous0x233/ReuseAndDiffuse) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://anonymous0x233.github.io/ReuseAndDiffuse/) | Sep., 2023 |\n|[VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation](https://arxiv.org/abs/2309.00398) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.00398)  |   - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://videogen.github.io/VideoGen/) | Sep., 2023 |\n|[MobileVidFactory: Automatic Diffusion-Based Social Media Video Generation for Mobile Devices from Text](https://arxiv.org/abs/2307.16371) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2307.16371) | - | - | Jul., 2023 |\n|[Text2Performer: Text-Driven Human Video Generation](https://arxiv.org/abs/2304.08483) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.08483) | [![Star](https://img.shields.io/github/stars/yumingj/Text2Performer.svg?style=social\u0026label=Star)](https://github.com/yumingj/Text2Performer) | [![Website](https://img.shields.io/badge/Website-9cf)](https://yumingj.github.io/projects/Text2Performer) | Apr., 2023 |\n|[AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://arxiv.org/abs/2307.04725) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2307.04725) | [![Star](https://img.shields.io/github/stars/guoyww/animatediff.svg?style=social\u0026label=Star)](https://github.com/guoyww/animatediff/) | [![Website](https://img.shields.io/badge/Website-9cf)](https://animatediff.github.io/) | Jul., 2023 |\n|[Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models](https://arxiv.org/abs/2308.13812) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.13812)  |   - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://haofei.vip/Dysen-VDM/) | Aug., 2023 |\n|[SimDA: Simple Diffusion Adapter for Efficient Video Generation](https://arxiv.org/abs/2308.09710) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.09710)  | [![Star](https://img.shields.io/github/stars/ChenHsing/SimDA.svg?style=social\u0026label=Star)](https://github.com/ChenHsing/SimDA)  |   [![Website](https://img.shields.io/badge/Website-9cf)](https://chenhsing.github.io/SimDA/) | CVPR, 2024 |\n|[Dual-Stream Diffusion Net for Text-to-Video Generation](https://arxiv.org/abs/2308.08316) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.08316)  |   - |   - | Aug., 2023 |\n|[ModelScope Text-to-Video Technical Report](https://arxiv.org/abs/2308.06571) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.06571)  |   [![Star](https://img.shields.io/github/stars/modelscope/modelscope.svg?style=social\u0026label=Star)](https://github.com/modelscope/modelscope) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://modelscope.cn/models/damo/text-to-video-synthesis/summary) | Aug., 2023 |\n|[InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation](https://arxiv.org/abs/2307.06942) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2307.06942)  | [![Star](https://img.shields.io/github/stars/OpenGVLab/InternVideo.svg?style=social\u0026label=Star)](https://github.com/OpenGVLab/InternVideo/tree/main/Data/InternVid)  | - | Jul., 2023 |\n|[VideoFactory: Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation](https://arxiv.org/abs/2305.10874) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.10874) | - | - | May, 2023 |\n|[Preserve Your Own Correlation: A Noise Prior for Video Diffusion Models](https://arxiv.org/abs/2305.10474) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.10474) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://research.nvidia.com/labs/dir/pyoco/) | May, 2023 |\n|[Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://arxiv.org/abs/2304.08818) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.08818) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://research.nvidia.com/labs/toronto-ai/VideoLDM/) | - | CVPR 2023 |\n|[Latent-Shift: Latent Diffusion with Temporal Shift](https://arxiv.org/abs/2304.08477) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.08477) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://latent-shift.github.io/) | - | Apr., 2023 |\n|[Probabilistic Adaptation of Text-to-Video Models](https://arxiv.org/abs/2306.01872) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2306.01872) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://video-adapter.github.io/video-adapter/) | Jun., 2023 |\n|[NUWA-XL: Diffusion over Diffusion for eXtremely Long Video Generation](https://arxiv.org/abs/2303.12346) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2303.12346) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://msra-nuwa.azurewebsites.net/#/NUWAXL) | Mar., 2023 |\n|[ED-T2V: An Efficient Training Framework for Diffusion-based Text-to-Video Generation](https://ieeexplore.ieee.org/abstract/document/10191565) | - | - | - | IJCNN, 2023 |\n|[MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://arxiv.org/abs/2211.11018) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2211.11018) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://magicvideo.github.io/#) | - | Nov., 2022 |\n|[Phenaki: Variable Length Video Generation From Open Domain Textual Description](https://arxiv.org/abs/2210.02399) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2210.02399) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://phenaki.video/) | - | Oct., 2022 |\n|[Imagen Video: High Definition Video Generation With Diffusion Models](https://arxiv.org/abs/2210.02303) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2210.02303) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://imagen.research.google/video/) | - | Oct., 2022 |\n|[VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://arxiv.org/abs/2303.08320) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2303.08320) | [![Star](https://img.shields.io/github/stars/modelscope/modelscope.svg?style=social\u0026label=Star)](https://github.com/modelscope/modelscope) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://modelscope.cn/models/damo/text-to-video-synthesis/summary) | - | CVPR 2023 |\n|[MAGVIT: Masked Generative Video Transformer](https://arxiv.org/abs/2212.05199) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2212.05199) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://magvit.cs.cmu.edu/) | Dec., 2022 |\n|[Make-A-Video: Text-to-Video Generation without Text-Video Data](https://arxiv.org/abs/2209.14792) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2209.14792) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://makeavideo.studio) | - | ICLR 2023 |\n|[Latent Video Diffusion Models for High-Fidelity Video Generation With Arbitrary Lengths](https://arxiv.org/abs/2211.13221) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2211.13221) | [![Star](https://img.shields.io/github/stars/YingqingHe/LVDM.svg?style=social\u0026label=Star)](https://github.com/YingqingHe/LVDM) |   [![Website](https://img.shields.io/badge/Website-9cf)](https://yingqinghe.github.io/LVDM/) | Nov., 2022 |\n|[CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://arxiv.org/abs/2205.15868) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2205.15868) | [![Star](https://img.shields.io/github/stars/THUDM/CogVideo.svg?style=social\u0026label=Star)](https://github.com/THUDM/CogVideo) | - | May, 2022 |\n|[Video Diffusion Models](https://arxiv.org/abs/2204.03458) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2204.03458) | - |   [![Website](https://img.shields.io/badge/Website-9cf)](https://video-diffusion.github.io/) | - | Apr., 2022 |\n\n\n\n\n\n\n\n\n### Training-free\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n| [A²RD: Agentic Autoregressive Diffusion for Long Video Consistency](https://arxiv.org/abs/2605.06924) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2605.06924) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://dxlong2000.github.io/AARD/) | May, 2026 |\n| [VISTA: A Test-Time Self-Improving Video Generation Agent](https://arxiv.org/abs/2510.15831) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2510.15831) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://g-vista.github.io/) | CVPR, 2026 |\n|[InfLVG: Reinforce Inference-Time Consistent Long Video Generation with GRPO](https://arxiv.org/abs/2505.17574) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2505.17574) | [![Star](https://img.shields.io/github/stars/MAPLE-AIGC/InfLVG.svg?style=social\u0026label=Star)](https://github.com/MAPLE-AIGC/InfLVG)  |  -  | May, 2025 |\n|[VideoElevator: Elevating Video Generation Quality with Versatile Text-to-Image Diffusion Models](https://arxiv.org/abs/2403.05438) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.05438) | [![Star](https://img.shields.io/github/stars/YBYBZhang/VideoElevator.svg?style=social\u0026label=Star)](https://github.com/YBYBZhang/VideoElevator)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://videoelevator.github.io/) | Mar, 2024 |\n|[TRAILBLAZER: TRAJECTORY CONTROL FOR DIFFUSION-BASED VIDEO GENERATION](https://arxiv.org/abs/2401.00896) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.00896) | [![Star](https://img.shields.io/github/stars/hohonu-vicml/Trailblazer.svg?style=social\u0026label=Star)](https://github.com/hohonu-vicml/Trailblazer)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://hohonu-vicml.github.io/Trailblazer.Page/) | Jan, 2024 |\n|[FreeInit: Bridging Initialization Gap in Video Diffusion Models](https://arxiv.org/abs/2312.07537) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.07537) | [![Star](https://img.shields.io/github/stars/TianxingWu/FreeInit.svg?style=social\u0026label=Star)](https://github.com/TianxingWu/FreeInit)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://tianxingwu.github.io/pages/FreeInit/) | Dec, 2023 |\n|[MTVG : Multi-text Video Generation with Text-to-Video Models](https://arxiv.org/abs/2312.04086) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.04086) | -  | [![Website](https://img.shields.io/badge/Website-9cf)](https://kuai-lab.github.io/mtvg-page/) | Dec, 2023 |\n|[F3-Pruning: A Training-Free and Generalized Pruning Strategy towards Faster and Finer Text-to-Video Synthesis](https://arxiv.org/abs/2312.03459) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.03459) | -  | - | Nov, 2023 |\n|[AdaDiff: Adaptive Step Selection for Fast Diffusion](https://arxiv.org/abs/2311.14768) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.14768) | -  | - | Nov, 2023 |\n|[FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax](https://arxiv.org/abs/2311.15813) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.15813) | [![Star](https://img.shields.io/github/stars/aniki-ly/FlowZero.svg?style=social\u0026label=Star)](https://github.com/aniki-ly/FlowZero)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://flowzero-video.github.io/) | Nov, 2023 |\n|[🏀GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning](https://arxiv.org/abs/2311.12631) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.12631) | [![Star](https://img.shields.io/github/stars/jiaxilv/GPT4Motion.svg?style=social\u0026label=Star)](https://github.com/jiaxilv/GPT4Motion) | [![Website](https://img.shields.io/badge/Website-9cf)](https://gpt4motion.github.io/) | Nov, 2023 |\n|[FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling](https://arxiv.org/abs/2310.15169) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.15169) | [![Star](https://img.shields.io/github/stars/arthur-qiu/LongerCrafter.svg?style=social\u0026label=Star)](https://github.com/arthur-qiu/LongerCrafter)  | [![Website](https://img.shields.io/badge/Website-9cf)](http://haonanqiu.com/projects/FreeNoise.html) | Oct, 2023 |\n|[ConditionVideo: Training-Free Condition-Guided Text-to-Video Generation](https://arxiv.org/abs/2310.07697) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2310.07697) | [![Star](https://img.shields.io/github/stars/pengbo807/ConditionVideo.svg?style=social\u0026label=Star)](https://github.com/pengbo807/ConditionVideo)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://pengbo807.github.io/conditionvideo-website/) | Oct, 2023 |\n|[LLM-grounded Video Diffusion Models](https://arxiv.org/abs/2309.17444) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.17444) | [![Star](https://img.shields.io/github/stars/TonyLianLong/LLM-groundedVideoDiffusion.svg?style=social\u0026label=Star)](https://github.com/TonyLianLong/LLM-groundedVideoDiffusion) | [![Website](https://img.shields.io/badge/Website-9cf)](https://llm-grounded-video-diffusion.github.io/) | Oct, 2023 |\n|[Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator](https://arxiv.org/abs/2309.14494) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.14494) | [![Star](https://img.shields.io/github/stars/SooLab/Free-Bloom.svg?style=social\u0026label=Star)](https://github.com/SooLab/Free-Bloom) | - | NeurIPS, 2023 |\n|[DiffSynth: Latent In-Iteration Deflickering for Realistic Video Synthesis](https://arxiv.org/abs/2308.03463) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.03463) | [![Star](https://img.shields.io/github/stars/alibaba/EasyNLP/tree/master/diffusion/DiffSynth.svg?style=social\u0026label=Star)](https://github.com/alibaba/EasyNLP/tree/master/diffusion/DiffSynth) | [![Website](https://img.shields.io/badge/Website-9cf)](https://anonymous456852.github.io/) | Aug, 2023 |\n|[Large Language Models are Frame-level Directors for Zero-shot Text-to-Video Generation](https://arxiv.org/abs/2305.14330) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.14330) | [![Star](https://img.shields.io/github/stars/KU-CVLAB/DirecT2V.svg?style=social\u0026label=Star)](https://github.com/KU-CVLAB/DirecT2V) | - | May, 2023 |\n|[Text2video-Zero: Text-to-Image Diffusion Models Are Zero-Shot Video Generators](https://arxiv.org/abs/2303.13439) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2303.13439) | [![Star](https://img.shields.io/github/stars/Picsart-AI-Research/Text2Video-Zero.svg?style=social\u0026label=Star)](https://github.com/Picsart-AI-Research/Text2Video-Zero) | [![Website](https://img.shields.io/badge/Website-9cf)](https://text2video-zero.github.io/) | Mar., 2023 |\n| [PEEKABOO: Interactive Video Generation via Masked-Diffusion](https://arxiv.org/abs/2312.07509) 🫣 |  [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.07509) | [![Star](https://img.shields.io/github/stars/microsoft/Peekaboo.svg?style=social\u0026label=Star)](https://github.com/microsoft/Peekaboo) | [![Website](https://img.shields.io/badge/Website-9cf)](https://jinga-lala.github.io/projects/Peekaboo/) | CVPR, 2024 |\n\n\n\n\n\n\n## Video Generation with other conditions\n\n### Pose-guided Video Generation\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[Hand2World: Autoregressive Egocentric Interaction Generation via Free-Space Hand Gestures](https://arxiv.org/abs/2602.09600) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2602.09600) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://hand2world.github.io/) | Feb., 2026 |\n|[EgoControl: Controllable Egocentric Video Generation via 3D Full-Body Poses](https://arxiv.org/abs/2511.18173) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2511.18173) | [![Star](https://img.shields.io/github/stars/CVG-Bonn/EgoControl.svg?style=social\u0026label=Star)](https://github.com/CVG-Bonn/EgoControl/) | [![Website](https://img.shields.io/badge/Website-9cf)](https://cvg-bonn.github.io/EgoControl/) | CVPR 2026 |\n|🔥🔥\u003cb\u003e[StableAnimator: High-Quality Identity-Preserving Human Image Animation](https://arxiv.org/abs/2411.17697)\u003c/b\u003e🔥🔥 | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2411.17697) | [![Star](https://img.shields.io/github/stars/Francis-Rings/StableAnimator.svg?style=social\u0026label=Star)](https://github.com/Francis-Rings/StableAnimator) | [![Website](https://img.shields.io/badge/Website-9cf)](https://francis-rings.github.io/StableAnimator/) | Nov., 2024 |\n|[MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model](https://arxiv.org/abs/2405.20222) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2405.20222) | [![Star](https://img.shields.io/github/stars/MyNiuuu/MOFA-Video.svg?style=social\u0026label=Star)](https://github.com/MyNiuuu/MOFA-Video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://myniuuu.github.io/MOFA_Video/) | ECCV 2024 |\n|[MimicMotion: High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance](https://arxiv.org/abs/2406.19680) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.19680) | [![Star](https://img.shields.io/github/stars/Tencent/MimicMotion.svg?style=social\u0026label=Star)](https://github.com/Tencent/MimicMotion) | [![Website](https://img.shields.io/badge/Website-9cf)](https://tencent.github.io/MimicMotion/) | Jul., 2024 |\n|[Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://arxiv.org/abs/2403.14781) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.14781) | [![Star](https://img.shields.io/github/stars/fudan-generative-vision/champ.svg?style=social\u0026label=Star)](https://github.com/fudan-generative-vision/champ) | [![Website](https://img.shields.io/badge/Website-9cf)](https://fudan-generative-vision.github.io/champ/) | Mar., 2024 |\n|[Action Reimagined: Text-to-Pose Video Editing for Dynamic Human Actions](https://arxiv.org/abs/2403.07198) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.07198) | - | - | Mar., 2024 |\n|[Do You Guys Want to Dance: Zero-Shot Compositional Human Dance Generation with Multiple Persons](https://arxiv.org/abs/2401.13363) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.13363) | - | - | Jan., 2024 |\n|[DreaMoving: A Human Dance Video Generation Framework based on Diffusion Models](https://arxiv.org/abs/2312.05107) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.05107) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://dreamoving.github.io/dreamoving/) | Dec., 2023 |\n|[MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://arxiv.org/abs/2311.16498) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.16498) | [![Star](https://img.shields.io/github/stars/magic-research/magic-animate.svg?style=social\u0026label=Star)](https://github.com/magic-research/magic-animate) | [![Website](https://img.shields.io/badge/Website-9cf)](https://showlab.github.io/magicanimate/) | Nov., 2023 |\n|[Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://arxiv.org/abs/2311.17117) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.17117) | [![Star](https://img.shields.io/github/stars/HumanAIGC/AnimateAnyone.svg?style=social\u0026label=Star)](https://github.com/HumanAIGC/AnimateAnyone) | [![Website](https://img.shields.io/badge/Website-9cf)](https://humanaigc.github.io/animate-anyone/) | Nov., 2023 |\n|[MagicDance: Realistic Human Dance Video Generation with Motions \u0026 Facial Expressions Transfer](https://arxiv.org/abs/2311.12052) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.12052) | [![Star](https://img.shields.io/github/stars/Boese0601/MagicDance.svg?style=social\u0026label=Star)](https://github.com/Boese0601/MagicDance) | [![Website](https://img.shields.io/badge/Website-9cf)](https://boese0601.github.io/magicdance/) | Nov., 2023 |\n|[DisCo: Disentangled Control for Referring Human Dance Generation in Real World](https://arxiv.org/abs/2307.00040) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2307.00040) | [![Star](https://img.shields.io/github/stars/Wangt-CN/DisCo.svg?style=social\u0026label=Star)](https://github.com/Wangt-CN/DisCo) | [![Website](https://img.shields.io/badge/Website-9cf)](https://disco-dance.github.io/) | Jul., 2023 |\n|[Dancing Avatar: Pose and Text-Guided Human Motion Videos Synthesis with Image Diffusion Model](https://arxiv.org/pdf/2308.07749.pdf) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2308.07749.pdf) | - | - | Aug., 2023 |\n|[DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion](https://arxiv.org/abs/2304.06025) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.06025) | [![Star](https://img.shields.io/github/stars/johannakarras/DreamPose.svg?style=social\u0026label=Star)](https://github.com/johannakarras/DreamPose) | [![Website](https://img.shields.io/badge/Website-9cf)](https://grail.cs.washington.edu/projects/dreampose/) | Apr., 2023 |\n|[Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos](https://arxiv.org/abs/2304.01186) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.01186) | [![Star](https://img.shields.io/github/stars/mayuelala/FollowYourPose.svg?style=social\u0026label=Star)](https://github.com/mayuelala/FollowYourPose) | [![Website](https://img.shields.io/badge/Website-9cf)](https://follow-your-pose.github.io/) | Apr., 2023 |\n\n\n\n\n\n\n### Motion-guided  Video Generation\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance](https://arxiv.org/abs/2503.16421) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2503.16421) | [![Star](https://img.shields.io/github/stars/quanhaol/MagicMotion.svg?style=social\u0026label=Star)](https://github.com/quanhaol/MagicMotion) | [![Website](https://img.shields.io/badge/Website-9cf)](https://quanhaol.github.io/magicmotion-site/) | Mar. 2025 |\n|[MOTIONCLONE: TRAINING-FREE MOTION CLONING FOR CONTROLLABLE VIDEO GENERATION](https://arxiv.org/pdf/2406.05338) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2406.05338) | [![Star](https://img.shields.io/github/stars/alibaba/Tora.svg?style=social\u0026label=Star)](https://github.com/LPengYang/MotionClone) | [![Website](https://img.shields.io/badge/Website-9cf)](https://bujiazi.github.io/motionclone.github.io/) | Jun., 2024 |\n|[Tora: Trajectory-oriented Diffusion Transformer for Video Generation](https://arxiv.org/abs/2407.21705) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2407.21705) | [![Star](https://img.shields.io/github/stars/alibaba/Tora.svg?style=social\u0026label=Star)](https://github.com/alibaba/Tora) | [![Website](https://img.shields.io/badge/Website-9cf)](https://ali-videoai.github.io/tora_video/) | CVPR 2025 |\n|[MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model](https://arxiv.org/abs/2405.20222) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2405.20222) | [![Star](https://img.shields.io/github/stars/MyNiuuu/MOFA-Video.svg?style=social\u0026label=Star)](https://github.com/MyNiuuu/MOFA-Video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://myniuuu.github.io/MOFA_Video/) | ECCV 2024 |\n|[Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://arxiv.org/abs/2403.14781) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.14781) | [![Star](https://img.shields.io/github/stars/fudan-generative-vision/champ.svg?style=social\u0026label=Star)](https://github.com/fudan-generative-vision/champ) | [![Website](https://img.shields.io/badge/Website-9cf)](https://fudan-generative-vision.github.io/champ/) | Mar., 2024 |\n|[Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling](https://arxiv.org/abs/2401.15977) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.15977) | - | - | Jan., 2024 |\n|[Motion-Zero: Zero-Shot Moving Object Control Framework for Diffusion-Based Video Generation](https://arxiv.org/abs/2401.10150) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.10150) | - | - | Jan., 2024 |\n|[Customizing Motion in Text-to-Video Diffusion Models](https://arxiv.org/abs/2312.04966) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.04966) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://joaanna.github.io/customizing_motion/) | Dec., 2023 |\n|[VMC: Video Motion Customization using Temporal Attention Adaption for Text-to-Video Diffusion Models](https://arxiv.org/abs/2312.00845) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.00845) |  [![Star](https://img.shields.io/github/stars/HyeonHo99/Video-Motion-Customization.svg?style=social\u0026label=Star)](https://github.com/HyeonHo99/Video-Motion-Customization) | [![Website](https://img.shields.io/badge/Website-9cf)](https://video-motion-customization.github.io/) | CVPR 2024 |\n|[AnimateAnything: Fine-Grained Open Domain Image Animation with Motion Guidance](https://arxiv.org/abs/2311.12886) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.12886) | [![Star](https://img.shields.io/github/stars/alibaba/animate-anything.svg?style=social\u0026label=Star)](https://github.com/alibaba/animate-anything) | [![Website](https://img.shields.io/badge/Website-9cf)](https://animationai.github.io/AnimateAnything/) | Nov., 2023 |\n|[Motion-Conditioned Diffusion Model for Controllable Video Synthesis](https://arxiv.org/abs/2304.14404) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.14404) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://tsaishien-chen.github.io/MCDiff/) | Apr., 2023 |\n|[DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory](https://arxiv.org/abs/2308.08089) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.08089) | - | - | Aug., 2023 |\n\n\n\n\n\n### Sound-guided Video Generation\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation](https://arxiv.org/pdf/2406.08801) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2406.08801) | [![Star](https://img.shields.io/github/stars/fudan-generative-vision/hallo?style=social)](https://github.com/fudan-generative-vision/hallo) | [![Website](https://img.shields.io/badge/Website-9cf)](https://fudan-generative-vision.github.io/hallo/#/) | Jun., 2024 |\n|[Context-aware Talking Face Video Generation](https://arxiv.org/abs/2402.18092) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.18092) | - | - | Feb., 2024 |\n|[EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions](https://arxiv.org/abs/2402.17485) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.17485) | [![Star](https://img.shields.io/github/stars/HumanAIGC/EMO.svg?style=social\u0026label=Star)](https://github.com/HumanAIGC/EMO) | [![Website](https://img.shields.io/badge/Website-9cf)](https://humanaigc.github.io/emote-portrait-alive/) | Feb., 2024 |\n|[The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion](https://arxiv.org/abs/2309.04509) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.04509) | - | - | ICCV, 2023 |\n|[Generative Disco: Text-to-Video Generation for Music Visualization](https://arxiv.org/abs/2304.08551) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.08551) | - | - | Apr., 2023 |\n| [AADiff: Audio-Aligned Video Synthesis with Text-to-Image Diffusion](https://arxiv.org/abs/2305.04001) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.04001) | - | - | CVPRW, 2023 |\n\n\n\n\n\n\n\n\n### Image-guided Video Generation\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|-------------|\n| [Identity-Preserving Text-to-Video Generation by Frequency Decomposition](https://arxiv.org/abs/2411.17440) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2411.17440) |[![Star](https://img.shields.io/github/stars/PKU-YuanGroup/ConsisID.svg?style=social\u0026label=Star)](https://github.com/PKU-YuanGroup/ConsisID)|[![Website](https://img.shields.io/badge/Website-9cf)](https://pku-yuangroup.github.io/ConsisID/) | Nov., 2024 |\n|[PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation](https://arxiv.org/pdf/2409.18964) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2409.18964) | [![Star](https://img.shields.io/github/stars/stevenlsw/physgen.svg?style=social\u0026label=Star)](https://github.com/stevenlsw/physgen) |  [![Website](https://img.shields.io/badge/Website-9cf)](https://stevenlsw.github.io/physgen/)  | ECCV 2024   |\n|[TI2V-Zero: Zero-Shot Image Conditioning for Text-to-Video Diffusion Models](https://arxiv.org/pdf/2404.16306) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2404.16306) | [![Star](https://img.shields.io/github/stars/merlresearch/TI2V-Zero.svg?style=social\u0026label=Star)](https://github.com/merlresearch/TI2V-Zero) |  [![Website](https://img.shields.io/badge/Website-9cf)](https://merl.com/research/highlights/TI2V-Zero)  | CVPR 2024   |\n|[Identifying and Solving Conditional Image Leakage in Image-to-Video Diffusion Model](https://arxiv.org/abs/2406.15735) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.15735) | [![Star](https://img.shields.io/github/stars/thu-ml/cond-image-leakage.svg?style=social\u0026label=Star)](https://github.com/thu-ml/cond-image-leakage/tree/main?tab=readme-ov-file) |  [![Website](https://img.shields.io/badge/Website-9cf)](https://cond-image-leak.github.io/) | NeurIPS 2024 |\n|[Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation](https://arxiv.org/abs/2403.02827) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.02827) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://noise-rectification.github.io/) | Mar., 2024  |\n|[AtomoVideo: High Fidelity Image-to-Video Generation](https://arxiv.org/abs/2403.01800) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.01800) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://atomo-video.github.io/) | Mar., 2024  |\n|[Animated Stickers: Bringing Stickers to Life with Video Diffusion](https://arxiv.org/abs/2402.06088) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.06088) | - | - | Feb., 2024  |\n|[CONSISTI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://arxiv.org/abs/2402.04324) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.04324) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://tiger-ai-lab.github.io/ConsistI2V) | Feb., 2024  |\n|[I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models](https://arxiv.org/abs/2312.16693) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.16693) | - | - | Dec., 2023  |\n|[PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models](https://arxiv.org/abs/2312.13964) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.13964) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://pi-animator.github.io/) | Dec., 2023  |\n|[DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance](https://arxiv.org/abs/2312.03018) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.03018) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://anonymous0769.github.io/DreamVideo/) | Nov., 2023  |\n|[LivePhoto: Real Image Animation with Text-guided Motion Control](https://arxiv.org/abs/2312.02928) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.02928) | [![Star](https://img.shields.io/github/stars/XavierCHEN34/LivePhoto.svg?style=social\u0026label=Star)](https://github.com/XavierCHEN34/LivePhoto) | [![Website](https://img.shields.io/badge/Website-9cf)](https://xavierchen34.github.io/LivePhoto-Page/) | Nov., 2023  |\n|[VideoBooth: Diffusion-based Video Generation with Image Prompts](https://arxiv.org/abs/2312.00777) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.00777) | [![Star](https://img.shields.io/github/stars/Vchitect/VideoBooth.svg?style=social\u0026label=Star)](https://github.com/Vchitect/VideoBooth) | [![Website](https://img.shields.io/badge/Website-9cf)](https://vchitect.github.io/VideoBooth-project/) | Nov., 2023  |\n|[Decouple Content and Motion for Conditional Image-to-Video Generation](https://arxiv.org/abs/2311.14294) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.14294) | - | - | Nov, 2023   |\n|[I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models](https://arxiv.org/abs/2311.04145) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.04145) | - | - | Nov, 2023   |\n|[Make-It-4D: Synthesizing a Consistent Long-Term Dynamic Scene Video from a Single Image](https://arxiv.org/abs/2308.10257) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.10257) | - | - | MM, 2023    |\n|[Generative Image Dynamics](https://arxiv.org/abs/2309.07906) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.07906) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://generative-dynamics.github.io/) | Sep., 2023  |\n|[LaMD: Latent Motion Diffusion for Video Generation](https://arxiv.org/abs/2304.11603) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2304.11603) | - | - | Apr., 2023  |\n|[Conditional Image-to-Video Generation with Latent Flow Diffusion Models](https://arxiv.org/abs/2303.13744) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2303.13744) | [![Star](https://img.shields.io/github/stars/nihaomiao/CVPR23_LFDM.svg?style=social\u0026label=Star)](https://github.com/nihaomiao/CVPR23_LFDM) | - | CVPR 2023   |\n|[NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis](https://arxiv.org/abs/2207.09814) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2207.09814) | [![Star](https://img.shields.io/github/stars/microsoft/NUWA.svg?style=social\u0026label=Star)](https://github.com/microsoft/NUWA) | [![Website](https://img.shields.io/badge/Website-9cf)](https://nuwa-infinity.microsoft.com/#/NUWAInfinity) | CVPR 2022   |\n\n\n\n\n\n### Brain-guided Video Generation\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties](https://arxiv.org/abs/2402.01590) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.01590) | - | - | Feb., 2024 |\n|[Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity](https://arxiv.org/abs/2305.11675) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.11675) | [![Star](https://img.shields.io/github/stars/jqin4749/MindVideo.svg?style=social\u0026label=Star)](https://github.com/jqin4749/MindVideo) | [![Website](https://img.shields.io/badge/Website-9cf)](https://mind-video.com/) | NeurIPS, 2023 |\n\n\n## Depth-guided Video Generation\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[StableV2V: Stablizing Shape Consistency in Video-to-Video Editing](https://arxiv.org/pdf/2411.11045) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)]([https://arxiv.org/abs/2307.06940](https://arxiv.org/pdf/2411.11045)) | [![Star](https://img.shields.io/github/stars/AlonzoLeeeooo/StableV2V.svg?style=social\u0026label=Star)](https://github.com/AlonzoLeeeooo/StableV2V) | [![Website](https://img.shields.io/badge/Website-9cf)](https://alonzoleeeooo.github.io/StableV2V/) | Nov., 2024 |\n|[Animate-A-Story: Storytelling with Retrieval-Augmented Video Generation](https://arxiv.org/abs/2307.06940) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2307.06940) | [![Star](https://img.shields.io/github/stars/VideoCrafter/Animate-A-Story.svg?style=social\u0026label=Star)](https://github.com/VideoCrafter/Animate-A-Story) | [![Website](https://img.shields.io/badge/Website-9cf)](https://videocrafter.github.io/Animate-A-Story/) | Jul., 2023 |\n|[Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance](https://arxiv.org/abs/2306.00943) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2306.00943) | [![Star](https://img.shields.io/github/stars/VideoCrafter/Make-Your-Video.svg?style=social\u0026label=Star)](https://github.com/VideoCrafter/Make-Your-Video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://doubiiu.github.io/projects/Make-Your-Video/) | Jun., 2023 |\n\n\n\n\n\n\n\n\n\n\n\n\n\n### Multi-modal guided Video Generation\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control](https://arxiv.org/abs/2403.02332) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.02332) | - | - | Mar., 2024 |\n|[Magic-Me: Identity-Specific Video Customized Diffusion](https://arxiv.org/abs/2402.09368) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.09368) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://github.com/Zhen-Dong/Magic-Me) | Feb., 2024 |\n|[InteractiveVideo: User-Centric Controllable Video Generation with Synergistic Multimodal Instructions](https://arxiv.org/abs/2402.03040) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.03040) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://invictus717.github.io/InteractiveVideo/) | Feb., 2024 |\n|[Direct-a-Video: Customized Video Generation with User-Directed Camera Movement and Object Motion](https://arxiv.org/abs/2402.03162) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.03162) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://direct-a-video.github.io/) | Feb., 2024 |\n|[Boximator: Generating Rich and Controllable Motions for Video Synthesis](https://arxiv.org/abs/2402.01566) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.01566) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://boximator.github.io/) | Feb., 2024 |\n|[AnimateLCM: Accelerating the Animation of Personalized Diffusion Models and Adapters with Decoupled Consistency Learning](https://arxiv.org/abs/2402.00769) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.00769) | - | -| Jan., 2024 |\n|[ActAnywhere: Subject-Aware Video Background Generation](https://arxiv.org/abs/2401.10822) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.10822) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://actanywhere.github.io/) | Jan., 2024 |\n|[CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects](https://arxiv.org/abs/2401.09962) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.09962) | - | - | Jan., 2024 |\n|[MoonShot: Towards Controllable Video Generation and Editing with Multimodal Conditions](https://arxiv.org/abs/2401.01827) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.01827) | [![Star](https://img.shields.io/github/stars/salesforce/LAVIS.svg?style=social\u0026label=Star)](https://github.com/salesforce/LAVIS) | [![Website](https://img.shields.io/badge/Website-9cf)](https://showlab.github.io/Moonshot/) | Jan., 2024 |\n|[PEEKABOO: Interactive Video Generation via Masked-Diffusion](https://arxiv.org/abs/2312.07509) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.07509) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://jinga-lala.github.io/projects/Peekaboo/) | Dec., 2023 |\n|[CMMD: Contrastive Multi-Modal Diffusion for Video-Audio Conditional Modeling](https://arxiv.org/abs/2312.05412) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.05412) | - | - | Dec., 2023 |\n|[Fine-grained Controllable Video Generation via Object Appearance and Context](https://arxiv.org/abs/2312.02919) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.02919) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://hhsinping.github.io/factor/) | Nov., 2023 |\n|[GPT4Video: A Unified Multimodal Large Language Model for Instruction-Followed Understanding and Safety-Aware Generation](https://arxiv.org/abs/2311.16511) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.16511) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://gpt4video.github.io/) | Nov., 2023 |\n|[Panacea: Panoramic and Controllable Video Generation for Autonomous Driving](https://arxiv.org/abs/2311.16813) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.16813) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://panacea-ad.github.io/) | Nov., 2023 |\n|[SparseCtrl: Adding Sparse Controls to Text-to-Video Diffusion Models](https://arxiv.org/abs/2311.16933) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.16933) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://guoyww.github.io/projects/SparseCtrl/) | Nov., 2023 |\n|[VideoComposer: Compositional Video Synthesis with Motion Controllability](https://arxiv.org/abs/2306.02018) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2306.02018) | [![Star](https://img.shields.io/github/stars/damo-vilab/videocomposer.svg?style=social\u0026label=Star)](https://github.com/damo-vilab/videocomposer) | [![Website](https://img.shields.io/badge/Website-9cf)](https://videocomposer.github.io/) | Jun., 2023 |\n|[NExT-GPT: Any-to-Any Multimodal LLM](https://arxiv.org/abs/2309.05519) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.05519) | - | - | Sep, 2023 |\n|[MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images](https://arxiv.org/pdf/2306.07257.pdf) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2306.07257.pdf) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://www.bilibili.com/video/BV1qj411Q76P/) | Jun, 2023 |\n|[Any-to-Any Generation via Composable Diffusion](https://arxiv.org/abs/2305.11846) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.11846) | [![Star](https://img.shields.io/github/stars/microsoft/i-Code.svg?style=social\u0026label=Star)](https://github.com/microsoft/i-Code/tree/main/i-Code-V3) | [![Website](https://img.shields.io/badge/Website-9cf)](https://codi-gen.github.io/) | May, 2023 |\n|[Mm-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation](https://arxiv.org/abs/2212.09478) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2212.09478) | [![Star](https://img.shields.io/github/stars/researchmm/MM-Diffusion.svg?style=social\u0026label=Star)](https://github.com/researchmm/MM-Diffusion) | - | CVPR 2023 |\n\n\n\n\n\n\n\n\n## Unconditional Video Generation\n\n### U-Net based\n\n\n| Title | arXiv | Github                                                                                                                       | WebSite | Pub. \u0026 Date |\n|---|---|------------------------------------------------------------------------------------------------------------------------------|---|---|\n|[Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation](https://arxiv.org/abs/2402.13729) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.13729) | [![Star](https://img.shields.io/github/stars/hxngiee/HVDM.svg?style=social\u0026label=Star)](https://github.com/hxngiee/HVDM)     | [![Website](https://img.shields.io/badge/Website-9cf)](https://hxngiee.github.io/HVDM/) | Feb. 2024 |\n|[Video Probabilistic Diffusion Models in Projected Latent Space](https://arxiv.org/abs/2302.07685) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2302.07685) | [![Star](https://img.shields.io/github/stars/sihyun-yu/PVDM.svg?style=social\u0026label=Star)](https://github.com/sihyun-yu/PVDM) | [![Website](https://img.shields.io/badge/Website-9cf)](https://sihyun.me/PVDM/) | CVPR 2023 |\n|[VIDM: Video Implicit Diffusion Models](https://arxiv.org/abs/2212.00235) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2212.00235) | [![Star](https://img.shields.io/github/stars/MKFMIKU/VIDM.svg?style=social\u0026label=Star)](https://github.com/MKFMIKU/VIDM)     | [![Website](https://img.shields.io/badge/Website-9cf)](https://kfmei.page/vidm/) | AAAI 2023 |\n|[GD-VDM: Generated Depth for better Diffusion-based Video Generation](https://arxiv.org/abs/2306.11173) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2306.11173) | [![Star](https://img.shields.io/github/stars/lapid92/GD-VDM.svg?style=social\u0026label=Star)](https://github.com/lapid92/GD-VDM) | - | Jun., 2023 |\n|[LEO: Generative Latent Image Animator for Human Video Synthesis](https://arxiv.org/pdf/2305.03989.pdf) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2305.03989.pdf) | [![Star](https://img.shields.io/github/stars/wyhsirius/LEO.svg?style=social\u0026label=Star)](https://github.com/wyhsirius/LEO)   | [![Website](https://img.shields.io/badge/Website-9cf)](https://wyhsirius.github.io/LEO-project/) | May., 2023 |\n\n### Transformer based\n\n| Title | arXiv | Github | WebSite | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[FEAT: Full-Dimensional Efficient Attention Transformer for Medical Video Generation](https://arxiv.org/pdf/2506.04956) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2506.04956) | [![Star](https://img.shields.io/github/stars/Yaziwel/FEAT.svg?style=social\u0026label=Star)](https://github.com/Yaziwel/FEAT) |- | Jun., 2025 |\n|[Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach](https://arxiv.org/pdf/2410.03160) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2410.03160) | [![Star](https://img.shields.io/github/stars/Yaofang-Liu/FVDM.svg?style=social\u0026label=Star)](https://github.com/Yaofang-Liu/FVDM) |- | Oct., 2024 |\n|[Latte: Latent Diffusion Transformer for Video Generation](https://arxiv.org/abs/2401.03048) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.03048) | [![Star](https://img.shields.io/github/stars/Vchitect/Latte.svg?style=social\u0026label=Star)](https://github.com/Vchitect/Latte) | [![Website](https://img.shields.io/badge/Website-9cf)](https://maxin-cn.github.io/latte_project/) | Jan., 2024 |\n|[VDT: An Empirical Study on Video Diffusion with Transformers](https://arxiv.org/abs/2305.13311) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.13311) | [![Star](https://img.shields.io/github/stars/RERV/VDT.svg?style=social\u0026label=Star)](https://github.com/RERV/VDT) | - | May, 2023 |\n|[Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer](https://arxiv.org/abs/2204.03638) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2204.03638) | [![Star](https://img.shields.io/github/stars/SongweiGe/TATS.svg?style=social\u0026label=Star)](https://github.com/SongweiGe/TATS) | [![Website](https://img.shields.io/badge/Website-9cf)](https://songweige.github.io/projects/tats/index.html) | May, 2023 |\n\n\n\n\n\n\n## Video Completion\n\n### Video Enhancement and Restoration\n\n| Title | arXiv | Github | WebSite| Pub. \u0026 Date |\n|---|---|---|---|---|\n|[Towards Language-Driven Video Inpainting via Multimodal Large Language Models](https://arxiv.org/abs/2401.10226) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.10226) | [![Star](https://img.shields.io/github/stars/jianzongwu/Language-Driven-Video-Inpainting.svg?style=social\u0026label=Star)](https://github.com/jianzongwu/Language-Driven-Video-Inpainting) | [![Website](https://img.shields.io/badge/Website-9cf)](https://jianzongwu.github.io/projects/rovi/) | Jan., 2024 |\n|[Inflation with Diffusion: Efficient Temporal Adaptation for Text-to-Video Super-Resolution](https://openaccess.thecvf.com/content/WACV2024W/VAQ/papers/Yuan_Inflation_With_Diffusion_Efficient_Temporal_Adaptation_for_Text-to-Video_Super-Resolution_WACVW_2024_paper.pdf) | - | - | - | WACW, 2023 |\n|[Upscale-A-Video: Temporal-Consistent Diffusion Model for Real-World Video Super-Resolution](https://arxiv.org/abs/2312.06640) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.06640) | [![Star](https://img.shields.io/github/stars/sczhou/Upscale-A-Video.svg?style=social\u0026label=Star)](https://github.com/sczhou/Upscale-A-Video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://shangchenzhou.com/projects/upscale-a-video/) | Dec., 2023 |\n|[AVID: Any-Length Video Inpainting with Diffusion Model](https://arxiv.org/abs/2312.03816) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.03816) | [![Star](https://img.shields.io/github/stars/zhang-zx/AVID.svg?style=social\u0026label=Star)](https://github.com/zhang-zx/AVID) | [![Website](https://img.shields.io/badge/Website-9cf)](https://zhang-zx.github.io/AVID/) | Dec., 2023 |\n|[Motion-Guided Latent Diffusion for Temporally Consistent Real-world Video Super-resolution](https://arxiv.org/abs/2312.00853) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.00853) | [![Star](https://img.shields.io/github/stars/IanYeung/MGLD-VSR.svg?style=social\u0026label=Star)](https://github.com/IanYeung/MGLD-VSR) | -| CVPR 2023 |\n|[LDMVFI: Video Frame Interpolation with Latent Diffusion Models](https://arxiv.org/abs/2303.09508) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2303.09508) | - |- | Mar., 2023 |\n|[CaDM: Codec-aware Diffusion Modeling for Neural-enhanced Video Streaming](https://arxiv.org/abs/2211.08428) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2211.08428) | - | - | Nov., 2022 |\n| [Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos](https://arxiv.org/pdf/2305.16301.pdf) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2305.16301.pdf) | - | - | May., 2023 |\n \n\n\n\n\n\n### Video Prediction\n\n| Title | arXiv | Github | Website | Pub. \u0026 Date |\n|---|---|---|---|---|\n|[SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction](https://arxiv.org/abs/2503.18933) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2503.18933) | [![Star](https://img.shields.io/github/stars/PallottaEnrico/SyncVP.svg?style=social\u0026label=Star)](https://github.com/PallottaEnrico/SyncVP)                                                       | [![Website](https://img.shields.io/badge/Website-9cf)](https://syncvp.github.io/) | CVPR, 2025   |\n|[AID: Adapting Image2Video Diffusion Models for Instruction-guided Video Prediction](https://arxiv.org/abs/2406.06465) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.06465) | [![Star](https://img.shields.io/github/stars/Chenhsing/AID.svg?style=social\u0026label=Star)](https://github.com/Chenhsing/AID) | [![Website](https://img.shields.io/badge/Website-9cf)](https://chenhsing.github.io/AID) | Jun, 2024 |\n|[STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction](https://arxiv.org/abs/2312.06486) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.06486) | [![Star](https://img.shields.io/github/stars/XiYe20/STDiffProject.svg?style=social\u0026label=Star)](https://github.com/XiYe20/STDiffProject) | - | Dec, 2023 |\n|[Video Diffusion Models with Local-Global Context Guidance](https://arxiv.org/pdf/2306.02562.pdf) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/pdf/2306.02562.pdf) | [![Star](https://img.shields.io/github/stars/exisas/LGC-VD.svg?style=social\u0026label=Star)](https://github.com/exisas/LGC-VD) | - | IJCAI, 2023 |\n|[Seer: Language Instructed Video Prediction with Latent Diffusion Models](https://arxiv.org/abs/2303.14897) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2303.14897) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://seervideodiffusion.github.io/) | Mar., 2023 |\n|[MaskViT: Masked Visual Pre-Training for Video Prediction](https://arxiv.org/abs/2206.11894) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2206.11894) | [![Star](https://img.shields.io/github/stars/agrimgupta92/maskvit.svg?style=social\u0026label=Star)](https://github.com/agrimgupta92/maskvit) | [![Website](https://img.shields.io/badge/Website-9cf)](https://maskedvit.github.io/) | Jun, 2022 |\n|[Diffusion Models for Video Prediction and Infilling](https://arxiv.org/abs/2206.07696) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2206.07696) | [![Star](https://img.shields.io/github/stars/Tobi-r9/RaMViD.svg?style=social\u0026label=Star)](https://github.com/Tobi-r9/RaMViD) | [![Website](https://img.shields.io/badge/Website-9cf)](https://sites.google.com/view/video-diffusion-prediction) | TMLR 2022 |\n|[McVd: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation](https://arxiv.org/abs/2205.09853) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2205.09853) | [![Star](https://img.shields.io/github/stars/Tobi-r9/RaMViD.svg?style=social\u0026label=Star)](https://github.com/voletiv/mcvd-pytorch) | [![Website](https://img.shields.io/badge/Website-9cf)](https://mask-cond-video-diffusion.github.io) | NeurIPS 2022 |\n|[Diffusion Probabilistic Modeling for Video Generation](https://arxiv.org/abs/2203.09481) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2203.09481) | [![Star](https://img.shields.io/github/stars/buggyyang/RVD.svg?style=social\u0026label=Star)](https://github.com/buggyyang/RVD) | - | Mar., 2022 |\n|[Flexible Diffusion Modeling of Long Videos](https://arxiv.org/abs/2205.11495) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2205.11495) | [![Star](https://img.shields.io/github/stars/plai-group/flexible-video-diffusion-modeling.svg?style=social\u0026label=Star)](https://github.com/plai-group/flexible-video-diffusion-modeling) | [![Website](https://img.shields.io/badge/Website-9cf)](https://fdmolv.github.io/) | May, 2022 |\n|[Control-A-Video: Controllable Text-to-Video Generation with Diffusion Models](https://arxiv.org/abs/2305.13840) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2305.13840) | [![Star](https://img.shields.io/github/stars/Weifeng-Chen/control-a-video.svg?style=social\u0026label=Star)](https://github.com/Weifeng-Chen/control-a-video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://controlavideo.github.io/) | May, 2023 |\n\n\n\n\n\n\n## Video Editing \n\n### General Editing Model\n\n\n\n\n\n\n| Title | arXiv | Github | Website | Pub. Date |\n|---|---|---|---|---|\n| [VIA: A Spatiotemporal Video Adaptation Framework for Global and Local Video Editing](https://arxiv.org/abs/2406.12831) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.12831) |[![Star](https://img.shields.io/github/stars/eric-ai-lab/via-video.svg?style=social\u0026label=Star)](https://github.com/eric-ai-lab/via-video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://via-video.github.io/)| Jun, 2024 |\n| [FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation](https://arxiv.org/abs/2403.12962) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.12962) |-|- | Mar., 2024\n| [FastVideoEdit: Leveraging Consistency Models for Efficient Text-to-Video Editing](https://arxiv.org/abs/2403.06269) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.06269) |-|- | Mar., 2024\n| [DreamMotion: Space-Time Self-Similarity Score Distillation for Zero-Shot Video Editing](https://arxiv.org/abs/2403.12002) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.12002) |  -  | [![Website](https://img.shields.io/badge/Website-9cf)](https://hyeonho99.github.io/dreammotion/) | Mar, 2024 |\n| [Video Editing via Factorized Diffusion Distillation](https://arxiv.org/abs/2403.09334) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.09334) |  -  | - | Mar, 2024 |\n| [FlowVid: Taming Imperfect Optical Flows for Consistent Video-to-Video Synthesis](https://arxiv.org/abs/2312.17681) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.17681) |  [![Star](https://img.shields.io/github/stars/Jeff-LiangF/FlowVid.svg?style=social\u0026label=Star)](https://github.com/Jeff-LiangF/FlowVid)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://jeff-liangf.github.io/projects/flowvid/) | Dec, 2023 |\n| [MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers](https://arxiv.org/abs/2312.12468) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.12468) |  - | [![Website](https://img.shields.io/badge/Website-9cf)](https://maskint.github.io/) | Dec, 2023 |\n| [Neutral Editing Framework for Diffusion-based Video Editing](https://arxiv.org/abs/2312.06708) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.06708) |  - | [![Website](https://img.shields.io/badge/Website-9cf)](https://neuedit.github.io/) | Dec, 2023 |\n| [VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence](https://arxiv.org/abs/2312.02087) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.02087) |  - | [![Website](https://img.shields.io/badge/Website-9cf)](https://videoswap.github.io/) | Nov, 2023 |\n| [VIDiff: Translating Videos via Multi-Modal Instructions with Diffusion Models](https://arxiv.org/abs/2311.18837) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.18837) |  [![Star](https://img.shields.io/github/stars/ChenHsing/VIDiff.svg?style=social\u0026label=Star)](https://github.com/ChenHsing/VIDiff) | [![Website](https://img.shields.io/badge/Website-9cf)](https://chenhsing.github.io/VIDiff/) | Nov, 2023 |\n| [Motion-Conditioned Image Animation for Video Editing](https://arxiv.org/abs/2311.18827) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2311.18827) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://facebookresearch.github.io/MoCA/) | Nov, 2023 |\n| [MagicProp: Diffusion-based Video Editing via Motion-aware Appearance Propagation](https://arxiv.org/abs/2309.00908) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2309.00908) | - | - | Sep, 2023 |\n| [MagicEdit: High-Fidelity and Temporally Coherent Video Editing](https://arxiv.org/abs/2308.14749) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.14749) | - | - | Aug, 2023 |\n| [Edit Temporal-Consistent Videos with Image Diffusion Model](https://arxiv.org/abs/2308.09091) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2308.09091) | - | - | Aug, 2023 |\n| [Structure and Content-Guided Video Synthesis With Diffusion Models](https://arxiv.org/abs/2302.03011) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2302.03011) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://research.runwayml.com/gen2) | ICCV, 2023 |\n| [Dreamix: Video Diffusion Models Are General Video Editors](https://arxiv.org/abs/2302.01329) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2302.01329) | - | [![Website](https://img.shields.io/badge/Website-9cf)](https://dreamix-video-editing.github.io/) | Feb, 2023 |\n\n\n\n\n\n\n\n\n### Training-free Editing Model\n\n| Title | arXiv | Github | Website | Pub. Date |\n|---|---|---|---|---|\n| [MVOC: a training-free multiple video object composition method with diffusion models](https://arxiv.org/abs/2406.15829) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.15829) |[![Star](https://img.shields.io/github/stars/SobeyMIL/MVOC.svg?style=social\u0026label=Star)](https://github.com/SobeyMIL/MVOC)  | [![Website](https://img.shields.io/badge/Website-9cf)](https://sobeymil.github.io/mvoc.com/)| Jun, 2024 |\n| [VIA: A Spatiotemporal Video Adaptation Framework for Global and Local Video Editing](https://arxiv.org/abs/2406.12831) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2406.12831) |[![Star](https://img.shields.io/github/stars/eric-ai-lab/via-video.svg?style=social\u0026label=Star)](https://github.com/eric-ai-lab/via-video) | [![Website](https://img.shields.io/badge/Website-9cf)](https://via-video.github.io/)| Jun, 2024 |\n|[EVA: Zero-shot Accurate Attributes and Multi-Object Video Editing](https://arxiv.org/abs/2403.16111) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2403.16111) |[![Star](https://img.shields.io/github/stars/knightyxp/EVA_Video_Edit.svg?style=social\u0026label=Star)](https://github.com/knightyxp/EVA_Video_Edit) | [![Website](https://img.shields.io/badge/Website-9cf)](https://knightyxp.github.io/EVA/) | March, 2024 |\n|[UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing](https://arxiv.org/abs/2402.13185) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2402.13185) |- | [![Website](https://img.shields.io/badge/Website-9cf)](https://jianhongbai.github.io/UniEdit/) | Feb, 2024 |\n|[Object-Centric Diffusion for Efficient Video Editing](https://arxiv.org/abs/2401.05735) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2401.05735) | - | - | Jan, 2024 |\n|[RealCraft: Attention Control as A Solution for Zero-shot Long Video Editing](https://arxiv.org/abs/2312.12635) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.12635) | - | - | Dec, 2023 |\n|[VidToMe: Video Token Merging for Zero-Shot Video Editing](https://arxiv.org/abs/2312.10656) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.10656) | [![Star](https://img.shields.io/github/stars/lixirui142/VidToMe.svg?style=social\u0026label=Star)](https://github.com/lixirui142/VidToMe) | [![Website](https://img.shields.io/badge/Website-9cf)](https://vidtome-diffusion.github.io/) | Dec, 2023 |\n|[A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing](https://arxiv.org/abs/2312.05856) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.05856) | [![Star](https://img.shields.io/github/stars/STEM-Inv/stem-inv.svg?style=social\u0026label=Star)](https://github.com/STEM-Inv/stem-inv) | [![Website](https://img.shields.io/badge/Website-9cf)](https://stem-inv.github.io/page/) | Dec, 2023 |\n|[AnimateZero: Video Diffusion Models are Zero-Shot Image Animators](https://arxiv.org/abs/2312.03793) | [![arXiv](https://img.shields.io/badge/arXiv-b31b1b.svg)](https://arxiv.org/abs/2312.03793) | [![Star](https://img.shi","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/chenhsing%2Fawesome-video-diffusion-models/projects"}