{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/video-diffusion-models","title":"Video Diffusion Models","arxiv_id":"2204.03458","date":"2022-04-07","proceeding":null,"authors":["Jonathan Ho","Tim Salimans","Alexey Gritsenko","William Chan","Mohammad Norouzi","David J. Fleet"],"abstract":"Generating temporally coherent high fidelity video is an important milestone in generative modeling research. We make progress towards this milestone by proposing a diffusion model for video generation that shows very promising initial results. Our model is a natural extension of the standard image diffusion architecture, and it enables jointly training from image and video data, which we find to reduce the variance of minibatch gradients and speed up optimization. To generate long and higher resolution videos we introduce a new conditional sampling technique for spatial and temporal video extension that performs better than previously proposed methods. We present the first results on a large text-conditioned video generation task, as well as state-of-the-art results on established benchmarks for video prediction and unconditional video generation. Supplementary material is available at https://video-diffusion.github.io/","url_abs":"https://arxiv.org/abs/2204.03458v2","url_pdf":"https://arxiv.org/pdf/2204.03458v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"video-diffusion-models","repo_url":"https://github.com/coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"video-diffusion-models","repo_url":"https://github.com/eyeline-research/survey-video-diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"video-diffusion-models","repo_url":"https://github.com/lucidrains/make-a-video-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"video-diffusion-models","repo_url":"https://github.com/lucidrains/video-diffusion-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"video-diffusion-models","repo_url":"https://github.com/ndrwmlnk/awesome-video-diffusion-models","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"unconditional-video-generation","task_name":"Unconditional Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-generation-on-ucf-101-16-frames-64x64","task":"Video Generation","dataset":"UCF-101 16 frames, 64x64, Unconditional","model":"Video Diffusion Model","rank_in_archive_order":1,"of":7,"metrics":{"FID":"295","Inception Score":"57"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.03458","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.03458"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eyeline-research/survey-video-diffusion","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ndrwmlnk/awesome-video-diffusion-models","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/video-diffusion-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lucidrains/make-a-video-pytorch","reach":null}],"summary":{"ran":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"581b719228f51583","entry":"GaussianDiffusion","repo":"lucidrains/video-diffusion-pytorch","repo_kind":"listed","path":"video_diffusion_pytorch/video_diffusion_pytorch.py","file_url":"https://github.com/lucidrains/video-diffusion-pytorch/blob/HEAD/video_diffusion_pytorch/video_diffusion_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"581b719228f51583"}},{"code_sha256_prefix":"3ecc45bcc79b0f99","entry":"GaussianDiffusion","repo":"coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch","repo_kind":"listed","path":"diffusion.py","file_url":"https://github.com/coderpiaobozhe/classifier-free-diffusion-guidance-Pytorch/blob/HEAD/diffusion.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3ecc45bcc79b0f99"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}