Papers › NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion

24 Nov 2021arXiv:2111.12417archive 2025-07-28

Chenfei Wu, Jian Liang, Lei Ji, Fan Yang, Yuejian Fang, Daxin Jiang, Nan Duan

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2111.12417")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 3 ran · violated contract.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran; 2 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

lucidrains/nuwa-pytorch mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

3 samples harvested; 3 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3ran · violated contract

Licence: 2 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from lucidrains/nuwa-pytorch. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

cast_tuple lucidrains/nuwa-pytorch/nuwa_pytorch/nuwa_pytorch.py community (archive-listed) ran · violated contract fingerprinted MIT (permissive) · eb9b942eb2ad9e51 · report
default identical code first harvested elsewhere ran · violated contract fingerprinted licence of this copy not recorded · 60fff7c3c400d7ff · report
exists identical code first harvested elsewhere ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report

Tasks

DecoderImage GenerationText to Image GenerationText-to-Image GenerationText-to-Video GenerationVideo GenerationVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Image Generation COCO (Common Objects in Context) XMC-GAN (256 x 256) FID 9.3 #24 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) XMC-GAN (256 x 256) Inception score 30.5 #24 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) NÜWA (256 x 256) FID 12.9 #36 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) NÜWA (256 x 256) Inception score 27.2 #36 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) DM-GAN (256 x 256) FID 26.0 #51 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) DM-GAN (256 x 256) Inception score 32.2 #51 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) CogView (256 x 256) FID 27.1 #54 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) CogView (256 x 256) Inception score 18.2 #54 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) DALL-E (256 x 256) FID 27.5 #55 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) DALL-E (256 x 256) Inception score 17.9 #55 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) AttnGAN (256 x 256) FID 35.2 #62 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) AttnGAN (256 x 256) Inception score 23.3 #62 of 69 Archive leaderboard report
Text-to-Image Generation COCO (Common Objects in Context) DF-GAN (256 x 256) Inception score 18.7 #67 of 69 Archive leaderboard report
Text-to-Video Generation Kinetics NUWA (128×128) Accuracy 77.9 #1 of 1 Archive leaderboard report
Text-to-Video Generation MSR-VTT NUWA CLIP-FID 47.68 #17 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT NUWA CLIPSIM 0.2439 #17 of 18 Archive leaderboard report
Text-to-Video Generation MSR-VTT NUWA FID 47.68 #17 of 18 Archive leaderboard report
Video Generation BAIR Robot Pushing NUWA Cond 1 #3 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing NUWA FVD score 86.9 #3 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing NUWA Pred 15 #3 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing NUWA Train 15 #3 of 31 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1-bit Adam1cycle1x1 ConvolutionAdamLAMB

1 archive method tag without a method page not shown.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections