{"id":26475595,"url":"https://github.com/stability-ai/stable-virtual-camera","last_synced_at":"2025-10-18T03:53:36.187Z","repository":{"id":283113986,"uuid":"935494387","full_name":"Stability-AI/stable-virtual-camera","owner":"Stability-AI","description":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","archived":false,"fork":false,"pushed_at":"2025-04-01T18:25:44.000Z","size":57809,"stargazers_count":1150,"open_issues_count":8,"forks_count":70,"subscribers_count":13,"default_branch":"main","last_synced_at":"2025-04-10T02:18:31.524Z","etag":null,"topics":["diffusion-model","image-to-video","novel-view-synthesis","stable-virtual-camera"],"latest_commit_sha":null,"homepage":"https://stable-virtual-camera.github.io","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Stability-AI.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"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":"2025-02-19T14:36:47.000Z","updated_at":"2025-04-10T02:05:51.000Z","dependencies_parsed_at":"2025-03-18T16:47:16.648Z","dependency_job_id":"7c7e80a6-5c94-428a-ba5e-a7273f5b55f1","html_url":"https://github.com/Stability-AI/stable-virtual-camera","commit_stats":null,"previous_names":["stability-ai/stable-virtual-camera"],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstable-virtual-camera","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstable-virtual-camera/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstable-virtual-camera/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Stability-AI%2Fstable-virtual-camera/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Stability-AI","download_url":"https://codeload.github.com/Stability-AI/stable-virtual-camera/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248142906,"owners_count":21054672,"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":["diffusion-model","image-to-video","novel-view-synthesis","stable-virtual-camera"],"created_at":"2025-03-19T23:31:57.165Z","updated_at":"2025-10-18T03:53:36.178Z","avatar_url":"https://github.com/Stability-AI.png","language":"Python","readme":"\u003cdiv align=\"center\"\u003e\n\u003ch1\u003eStable Virtual Camera: Generative View Synthesis with Diffusion Models\u003c/h1\u003e\n\n\u003ca href=\"https://stable-virtual-camera.github.io\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%8F%A0%20Project%20Page-gray.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"http://arxiv.org/abs/2503.14489\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%93%84%20arXiv-2503.14489-B31B1B.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://stability.ai/news/introducing-stable-virtual-camera-multi-view-video-generation-with-3d-camera-control\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%93%83%20Blog-Stability%20AI-orange.svg\"\u003e\u003c/a\u003e\n\u003ca href=\"https://huggingface.co/stabilityai/stable-virtual-camera\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%A4%97%20Model_Card-Huggingface-orange\"\u003e\u003c/a\u003e\n\u003ca href=\"https://huggingface.co/spaces/stabilityai/stable-virtual-camera\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%9A%80%20Gradio%20Demo-Huggingface-orange\"\u003e\u003c/a\u003e\n\u003ca href=\"https://www.youtube.com/channel/UCLLlVDcS7nNenT_zzO3OPxQ\"\u003e\u003cimg src=\"https://img.shields.io/badge/%F0%9F%8E%AC%20Video-YouTube-orange\"\u003e\u003c/a\u003e\n\n[Jensen (Jinghao) Zhou](https://shallowtoil.github.io/)\\*, [Hang Gao](https://hangg7.com/)\\*\n\u003cbr\u003e\n[Vikram Voleti](https://voletiv.github.io/), [Aaryaman Vasishta](https://www.aaryaman.net/), [Chun-Han Yao](https://chhankyao.github.io/), [Mark Boss](https://markboss.me/)\n\u003cbr\u003e\n[Philip Torr](https://eng.ox.ac.uk/people/philip-torr/), [Christian Rupprecht](https://chrirupp.github.io/), [Varun Jampani](https://varunjampani.github.io/)\n\u003cbr\u003e\n\u003cbr\u003e\n[Stability AI](https://stability.ai/), [University of Oxford](https://www.robots.ox.ac.uk/~vgg/), [UC Berkeley](https://bair.berkeley.edu/)\n\n\u003c/div\u003e\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"assets/spiral.gif\" width=\"100%\" alt=\"Teaser\" style=\"border-radius:10px;\"/\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\" border-radius=\"10px\"\u003e\n  \u003cimg src=\"assets/benchmark.png\" width=\"100%\" alt=\"teaser_page1\"/\u003e\n\u003c/p\u003e\n\n# Overview\n\n`Stable Virtual Camera (SEVA)` is a generalist diffusion model for Novel View Synthesis (NVS), generating 3D consistent novel views of a scene, given any number of input views and target cameras.\n\n# :tada: News\n\n- June 2025 - Release v`1.1` model checkpoint.\n- March 2025 - `Stable Virtual Camera` is out everywhere.\n\n# :gear: Versions\n\n| Model Version | \\#Parameter | Resolution |                                               Download Link                                                |                                           Update Notes                                           |\n| :-----------: | :---------: | :--------: | :--------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------: |\n|     `1.1`     |    1.3B     |    576P    | 🤗 [Huggingface](https://huggingface.co/stabilityai/stable-virtual-camera/blob/main/modelv1.1.safetensors) | Fixing known issues of foreground objects sometimes being detached from the background in v`1.0` |\n|     `1.0`     |    1.3B     |    576P    |   🤗 [Huggingface](https://huggingface.co/stabilityai/stable-virtual-camera/blob/main/model.safetensors)   |                                         Initial release                                          |\n\nYou can specify the version via, for example, `load_model(..., model_version=1.1)` in the script.\n\n# :wrench: Installation\n\n```bash\ngit clone --recursive https://github.com/Stability-AI/stable-virtual-camera\ncd stable-virtual-camera\npip install -e .\n```\n\nPlease note that you will need `python\u003e=3.10` and `torch\u003e=2.6.0`.\n\nCheck [INSTALL.md](docs/INSTALL.md) for other dependencies if you want to use our demos or develop from this repo.\nFor windows users, please use WSL as flash attention isn't supported on native Windows [yet](https://github.com/pytorch/pytorch/issues/108175).\n\n# :open_book: Usage\n\nYou need to properly authenticate with Hugging Face to download our model weights. Once set up, our code will handle it automatically at your first run. You can authenticate by running\n\n```bash\n# This will prompt you to enter your Hugging Face credentials.\nhuggingface-cli login\n```\n\nOnce authenticated, go to our model card [here](https://huggingface.co/stabilityai/stable-virtual-camera) and enter your information for access.\n\nWe provide two demos for you to interact with `Stable Virtual Camera`.\n\n### :rocket: Gradio demo\n\nThis gradio demo is a GUI interface that requires no expert knowledge, suitable for general users. Simply run\n\n```bash\npython demo_gr.py\n```\n\nFor a more detailed guide, follow [GR_USAGE.md](docs/GR_USAGE.md).\n\n### :computer: CLI demo\n\nThis cli demo allows you to pass in more options and control the model in a fine-grained way, suitable for power users and academic researchers. An example command line looks as simple as\n\n```bash\npython demo.py --data_path \u003cdata_path\u003e [additional arguments]\n```\n\nFor a more detailed guide, follow [CLI_USAGE.md](docs/CLI_USAGE.md).\n\nFor users interested in benchmarking NVS models using command lines, check [`benchmark`](benchmark/) containing the details about scenes, splits, and input/target views we reported in the \u003ca href=\"http://arxiv.org/abs/2503.14489\"\u003epaper\u003c/a\u003e.\n\n# :question: Q\u0026A\n\n- Training script? See issue https://github.com/Stability-AI/stable-virtual-camera/issues/27, https://github.com/Stability-AI/stable-virtual-camera/issues/42. [@nviolante25](https://www.github.com/nviolante25) has made a pull request (https://github.com/Stability-AI/stable-virtual-camera/pull/51) based on the dicussions.\n- License for the output? See issue https://github.com/Stability-AI/stable-virtual-camera/issues/26. The output follows the same non-commercial license.\n\n# :books: Citing\n\nIf you find this repository useful, please consider giving a star :star: and citation.\n\n```\n@article{zhou2025stable,\n    title={Stable Virtual Camera: Generative View Synthesis with Diffusion Models},\n    author={Jensen (Jinghao) Zhou and Hang Gao and Vikram Voleti and Aaryaman Vasishta and Chun-Han Yao and Mark Boss and\n    Philip Torr and Christian Rupprecht and Varun Jampani\n    },\n    journal={arXiv preprint arXiv:2503.14489},\n    year={2025}\n}\n```\n","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstability-ai%2Fstable-virtual-camera","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstability-ai%2Fstable-virtual-camera","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstability-ai%2Fstable-virtual-camera/lists"}