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 NÜWA 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 NÜWA on 8 downstream tasks. Compared to several strong baselines, NÜWA 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 View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 3 code samples: 1 from 1 repository linked to this paper, 2 identical to code harvested from another paper's repository. Across all 3: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); 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.

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 3 samples that ran have no recorded date.

lucidrains/nuwa-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified 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 (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 3 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is 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. 2 samples are listed last, in a group without a repository. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

lucidrains/nuwa-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
cast_tuple in 58 papers nuwa_pytorch/nuwa_pytorch.py ran · violated contract fingerprinted MIT (permissive) · eb9b942eb2ad9e51 · report fixture: signature val:tuple/1/int, size:int/0/int · returned tuple · level recorded 2026-09-22
Repository not located 2 samples, 2 ran (0 instrument-failed) · 0 unverified
2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
default in 430 papers repository not located ran · violated contract fingerprinted licence of this copy not recorded · 60fff7c3c400d7ff · report fixture: signature val:int/0/int, d:int/0/int · returned int · level recorded, date not recorded
exists in 528 papers
census: 5 implementations from 103 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 1, kind int, dtype int64
repository not located ran · violated contract licence of this copy not recorded · aa5486a3650902d8 · report fixture: signature val:Tensor/1/int · returned bool · level recorded, date not recorded

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