{"id":28653877,"url":"https://github.com/tiger-ai-lab/videogenhub","last_synced_at":"2025-10-17T09:37:46.511Z","repository":{"id":234281445,"uuid":"781658997","full_name":"TIGER-AI-Lab/VideoGenHub","owner":"TIGER-AI-Lab","description":"A one-stop library to standardize the inference and evaluation of all the conditional video generation models.","archived":false,"fork":false,"pushed_at":"2025-02-13T08:27:00.000Z","size":35041,"stargazers_count":48,"open_issues_count":2,"forks_count":7,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-05-29T08:58:17.237Z","etag":null,"topics":["deep-learning","diffusion-models","generative-ai","pytorch","video-generation"],"latest_commit_sha":null,"homepage":"https://pypi.org/project/videogen-hub/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/TIGER-AI-Lab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/Contributing/basics.md","funding":null,"license":"LICENSE","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}},"created_at":"2024-04-03T19:54:13.000Z","updated_at":"2025-03-06T14:53:35.000Z","dependencies_parsed_at":"2024-04-23T21:55:41.023Z","dependency_job_id":"f503ac47-fe1d-4806-9fa2-c5e840fc2d39","html_url":"https://github.com/TIGER-AI-Lab/VideoGenHub","commit_stats":null,"previous_names":["tiger-ai-lab/videogenhub"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/TIGER-AI-Lab/VideoGenHub","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FVideoGenHub","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FVideoGenHub/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FVideoGenHub/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FVideoGenHub/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/TIGER-AI-Lab","download_url":"https://codeload.github.com/TIGER-AI-Lab/VideoGenHub/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/TIGER-AI-Lab%2FVideoGenHub/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":259599331,"owners_count":22882357,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","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"}},"keywords":["deep-learning","diffusion-models","generative-ai","pytorch","video-generation"],"created_at":"2025-06-13T07:07:58.009Z","updated_at":"2025-10-17T09:37:41.476Z","avatar_url":"https://github.com/TIGER-AI-Lab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# VideoGenHub\n\n[![contributors](https://img.shields.io/github/contributors/TIGER-AI-Lab/VideoGenHub)](https://github.com/TIGER-AI-Lab/VideoGenHub/graphs/contributors)\n[![license](https://img.shields.io/github/license/TIGER-AI-Lab/VideoGenHub.svg)](https://github.com/TIGER-AI-Lab/VidenGenHub/blob/main/LICENSE)\n[![GitHub](https://img.shields.io/github/stars/TIGER-AI-Lab/VideoGenHub?style=social)](https://github.com/TIGER-AI-Lab/VideoGenHub)\n[![Hits](https://hits.seeyoufarm.com/api/count/incr/badge.svg?url=https%3A%2F%2Fgithub.com%2FTIGER-AI-Lab%2FVideoGenHub\u0026count_bg=%23C83DB9\u0026title_bg=%23555555\u0026icon=\u0026icon_color=%23E7E7E7\u0026title=visitors\u0026edge_flat=false)](https://hits.seeyoufarm.com)\n\nVideoGenHub is a one-stop library to standardize the inference and evaluation of all the conditional video generation models.\n![DALL·E 2025-02-13 03 26 01 - A highly detailed and ultra-high-quality image of a person sitting at a desk watching videos on a computer  The screen displays a video player with a ](https://github.com/user-attachments/assets/88d7268c-56f9-48bf-a8e4-19b223516b76)\n\n* We define 2 prominent generation tasks (Text-to-Video and Image-to-Video).\n* We built a unified inference pipeline to ensure fair comparison. We currently support around 10 models.\n\n## 📰 News\n* 2024 Jun 10: [GenAI-Arena](https://arxiv.org/abs/2406.04485v1) Paper is out. It is featured on [Huggingface Daily Papers](https://huggingface.co/papers?date=2024-06-10).\n\n## 📄 Table of Contents\n\n- [🛠️ Installation](#%EF%B8%8F-installation-)\n- [👨‍🏫 Get Started](#-get-started-)\n- [🎫 License](#-license-)\n- [🖊️ Citation](#%EF%B8%8F-citation-)\n\n## 🛠️ Installation [🔝](#-table-of-contents)\nTo install from pypi:\n```commandline\npip install videogen-hub\n```\n\nTo install from github:\n```python\ngit clone https://github.com/TIGER-AI-Lab/VideoGenHub.git\ncd VideoGenHub\ncd env_cfg\npip install -r requirements.txt\ncd ..\npip install -e .\n```\nThe requirement of opensora is in `env_cfg/opensora.txt`\n\nFor some models like show one, you need to login through `huggingface-cli`.\n\n```shell\nhuggingface-cli login\n```\n\n## 👨‍🏫 Get Started [🔝](#-table-of-contents)\n\n### Benchmarking\nTo reproduce our experiment using benchmark.\n\nFor text-to-video generation: \n```commandline\n./t2v_inference.sh --\u003cmodel_name\u003e --\u003cdevice\u003e\n```\n\n### Infering one model\n```python\nimport videogen_hub\n\nmodel = videogen_hub.load('VideoCrafter2')\nvideo = model.infer_one_video(prompt=\"A child excitedly swings on a rusty swing set, laughter filling the air.\")\n\n# Here video is a torch tensor of shape torch.Size([16, 3, 320, 512])\n```\nSee Google Colab here: https://colab.research.google.com/drive/145UMsBOe5JLqZ2m0LKqvvqsyRJA1IeaE?usp=sharing\n\n\n## 🧠 Philosophy [🔝](#-philosophy-)\nBy streamlining research and collaboration, VideoGenHub plays a pivotal role in propelling the field of Video Generation.\n\n* Purity of Evaluation: We ensure a fair and consistent evaluation for all models, eliminating biases.\n* Research Roadmap: By defining tasks and curating datasets, we provide clear direction for researchers. \n* Open Collaboration: Our platform fosters the exchange and cooperation of related technologies, bringing together minds and innovations.\n\n### Implemented Models\nWe included more than 10 Models in video generation.\n\n|    Method     \t    | Venue  \t  |        Type           \t         |\n|:------------------:|:---------:|:-------------------------------:|\n|     LaVie   \t     |    - \t    |   Text-To-Video Generation \t    |\n| VideoCrafter2   \t |    - \t    |   Text-To-Video Generation \t    |\n|   ModelScope   \t   |    - \t    |   Text-To-Video Generation \t    |\n|  StreamingT2V   \t |    - \t    |   Text-To-Video Generation \t    |\n|     Show 1  \t     |    - \t    |   Text-To-Video Generation \t    |\n|    OpenSora  \t     |    - \t    |   Text-To-Video Generation \t    |\n|    OpenSora-Plan   |    - \t    |   Text-To-Video Generation \t    |\n|    T2V-Turbo  \t   |    - \t    |   Text-To-Video Generation \t    |\n| DynamiCrafter2   \t |    - \t    |   Image-To-Video Generation \t   |\n|     SEINE   \t     | ICLR'24 \t  |   Image-To-Video Generation \t   |\n|    Consisti2v \t   |    - \t    |   Image-To_Video Generation \t   |\n|      I2VGenXL      |    - \t    |   Image-To_Video Generation \t   |\n\n## TODO\n\n* [ ] Add ComfyUI Support \n* [ ] Add Metrics Support\n* [ ] Add Visualization Support (Similar to [ImagenHub](https://chromaica.github.io/#imagen-museum))\n* [ ] Add Video Editing Task\n\n## 🎫 License [🔝](#-table-of-contents)\n\nThis project is released under the [License](LICENSE).\n\n## 🖊️ Citation [🔝](#-table-of-contents)\n\nThis work is a part of GenAI-Arena work.\n\nPlease kindly cite our paper if you use our code, data, models or results:\n\n```bibtex\n@misc{jiang2024genai,\n      title={GenAI Arena: An Open Evaluation Platform for Generative Models}, \n      author={Dongfu Jiang and Max Ku and Tianle Li and Yuansheng Ni and Shizhuo Sun and Rongqi Fan and Wenhu Chen},\n      year={2024},\n      eprint={2406.04485},\n      archivePrefix={arXiv},\n      primaryClass={cs.AI}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftiger-ai-lab%2Fvideogenhub","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftiger-ai-lab%2Fvideogenhub","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftiger-ai-lab%2Fvideogenhub/lists"}