{"id":15601079,"url":"https://github.com/lucidrains/transframer-pytorch","last_synced_at":"2026-02-12T08:30:50.056Z","repository":{"id":96486697,"uuid":"525850034","full_name":"lucidrains/transframer-pytorch","owner":"lucidrains","description":"Implementation of Transframer, Deepmind's U-net + Transformer architecture for up to 30 seconds video generation, in Pytorch","archived":false,"fork":false,"pushed_at":"2022-08-23T20:33:15.000Z","size":163,"stargazers_count":70,"open_issues_count":3,"forks_count":6,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-03-30T14:51:10.319Z","etag":null,"topics":["artificial-intelligence","attention-mechanisms","deep-learning","transformers","unet","video-generation"],"latest_commit_sha":null,"homepage":"","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/lucidrains.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":"2022-08-17T15:20:47.000Z","updated_at":"2025-03-14T21:34:19.000Z","dependencies_parsed_at":null,"dependency_job_id":"a722e52c-60e3-482c-a264-d35391204f12","html_url":"https://github.com/lucidrains/transframer-pytorch","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransframer-pytorch","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransframer-pytorch/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransframer-pytorch/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Ftransframer-pytorch/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/transframer-pytorch/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":251675505,"owners_count":21625829,"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":["artificial-intelligence","attention-mechanisms","deep-learning","transformers","unet","video-generation"],"created_at":"2024-10-03T02:14:05.197Z","updated_at":"2026-02-12T08:30:50.028Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"./transframer.png\" width=\"400px\"\u003e\u003c/img\u003e\n\n## Transframer - Pytorch (wip)\n\nImplementation of \u003ca href=\"https://arxiv.org/abs/2203.09494\"\u003eTransframer\u003c/a\u003e, Deepmind's U-net + Transformer architecture for up to 30 seconds video generation, in Pytorch\n\nThe gist of the paper is the usage of a Unet as a multi-frame encoder, along with a regular transformer decoder cross attending and predicting the rest of the frames. The author builds upon his \u003ca href=\"https://arxiv.org/abs/2103.03841\"\u003eprior work\u003c/a\u003e where images are encoded as sparse discrete cosine transform (DCT) sequences.\n\nI will deviate from the implementation in this paper, using a \u003ca href=\"https://github.com/lucidrains/RQ-Transformer/blob/main/rq_transformer/hierarchical_causal_transformer.py\"\u003ehierarchical autoregressive transformer\u003c/a\u003e, and just a regular resnet block in place of the NF-net block (this design choice is just Deepmind reusing their own code, as \u003ca href=\"https://arxiv.org/abs/2102.06171\"\u003eNF-net\u003c/a\u003e was developed at Deepmind by Brock et al).\n\nUpdate: On further meditation, there is nothing new in this paper except for generative modeling on DCT representations\n\n## Appreciation\n\n- This work would not be possible without the generous sponsorship from \u003ca href=\"https://stability.ai/\"\u003eStability AI\u003c/a\u003e, as well as my other sponsors\n\n## Todo\n\n- [ ] figure out if dct can be directly extracted from images in jpeg format\n\n## Citations\n\n```bibtex\n@article{Nash2022TransframerAF,\n    title   = {Transframer: Arbitrary Frame Prediction with Generative Models},\n    author  = {Charlie Nash and Jo{\\~a}o Carreira and Jacob Walker and Iain Barr and Andrew Jaegle and Mateusz Malinowski and Peter W. Battaglia},\n    journal = {ArXiv},\n    year    = {2022},\n    volume  = {abs/2203.09494}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Ftransframer-pytorch","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Ftransframer-pytorch","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Ftransframer-pytorch/lists"}