{"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/nuwa-visual-synthesis-pre-training-for-neural","title":"NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion","arxiv_id":"2111.12417","date":"2021-11-24","proceeding":null,"authors":["Chenfei Wu","Jian Liang","Lei Ji","Fan Yang","Yuejian Fang","Daxin Jiang","Nan Duan"],"abstract":"This paper presents a unified multimodal pre-trained model called N\\\"UWA that can generate new or manipulate existing visual data (i.e., images and videos) for various visual synthesis tasks. To cover language, image, and video at the same time for different scenarios, a 3D transformer encoder-decoder framework is designed, which can not only deal with videos as 3D data but also adapt to texts and images as 1D and 2D data, respectively. A 3D Nearby Attention (3DNA) mechanism is also proposed to consider the nature of the visual data and reduce the computational complexity. We evaluate N\\\"UWA on 8 downstream tasks. Compared to several strong baselines, N\\\"UWA achieves state-of-the-art results on text-to-image generation, text-to-video generation, video prediction, etc. Furthermore, it also shows surprisingly good zero-shot capabilities on text-guided image and video manipulation tasks. Project repo is https://github.com/microsoft/NUWA.","url_abs":"https://arxiv.org/abs/2111.12417v1","url_pdf":"https://arxiv.org/pdf/2111.12417v1.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":"nuwa-visual-synthesis-pre-training-for-neural","repo_url":"https://github.com/lucidrains/nuwa-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"},{"task_slug":"text-to-video-generation","task_name":"Text-to-Video Generation"},{"task_slug":"video-generation","task_name":"Video Generation"},{"task_slug":"video-prediction","task_name":"Video Prediction"}],"methods":[{"method_slug":null,"method_name":"(USA Guide)"},{"method_slug":"1-bit-adam","method_name":"1-bit Adam"},{"method_slug":"1cycle","method_name":"1cycle"},{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"lamb","method_name":"LAMB"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"XMC-GAN (256 x 256)","rank_in_archive_order":24,"of":69,"metrics":{"FID":"9.3","Inception score":"30.5"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"NÜWA (256 x 256)","rank_in_archive_order":36,"of":69,"metrics":{"FID":"12.9","Inception score":" 27.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"DM-GAN (256 x 256)","rank_in_archive_order":51,"of":69,"metrics":{"FID":" 26.0","Inception score":"32.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"CogView (256 x 256)","rank_in_archive_order":54,"of":69,"metrics":{"FID":" 27.1","Inception score":"18.2"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"DALL-E (256 x 256)","rank_in_archive_order":55,"of":69,"metrics":{"FID":"27.5","Inception score":"17.9"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"AttnGAN (256 x 256)","rank_in_archive_order":62,"of":69,"metrics":{"FID":" 35.2","Inception score":"23.3"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-image-generation-on-coco","task":"Text-to-Image Generation","dataset":"COCO (Common Objects in Context)","model":"DF-GAN (256 x 256)","rank_in_archive_order":67,"of":69,"metrics":{"Inception score":"18.7"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-video-generation-on-kinetics","task":"Text-to-Video Generation","dataset":"Kinetics","model":"NUWA (128×128)","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-video-generation-on-msr-vtt","task":"Text-to-Video Generation","dataset":"MSR-VTT","model":"NUWA","rank_in_archive_order":17,"of":18,"metrics":{"CLIP-FID":"47.68","CLIPSIM":"0.2439","FID":"47.68"},"uses_additional_data":false},{"leaderboard":"/sota/video-generation-on-bair-robot-pushing","task":"Video Generation","dataset":"BAIR Robot Pushing","model":"NUWA","rank_in_archive_order":3,"of":31,"metrics":{"Cond":"1","FVD score":"86.9","Pred":"15","Train":"15"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2111.12417","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.12417"}},"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/lucidrains/nuwa-pytorch","reach":null}],"summary":{"ran_violates":3},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"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":2,"samples":[{"code_sha256_prefix":"eb9b942eb2ad9e51","entry":"cast_tuple","repo":"lucidrains/nuwa-pytorch","repo_kind":"listed","path":"nuwa_pytorch/nuwa_pytorch.py","file_url":"https://github.com/lucidrains/nuwa-pytorch/blob/HEAD/nuwa_pytorch/nuwa_pytorch.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eb9b942eb2ad9e51"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}