Papers › NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

20 Jul 2022arXiv:2207.09814archive 2025-07-28

Chenfei Wu, Jian Liang, Xiaowei Hu, Zhe Gan, JianFeng Wang, Lijuan Wang, Zicheng Liu, Yuejian Fang, Nan Duan

In this paper, we present NUWA-Infinity, a generative model for infinite visual synthesis, which is defined as the task of generating arbitrarily-sized high-resolution images or long-duration videos. An autoregressive over autoregressive generation mechanism is proposed to deal with this variable-size generation task, where a global patch-level autoregressive model considers the dependencies between patches, and a local token-level autoregressive model considers dependencies between visual tokens within each patch. A Nearby Context Pool (NCP) is introduced to cache-related patches already generated as the context for the current patch being generated, which can significantly save computation costs without sacrificing patch-level dependency modeling. An Arbitrary Direction Controller (ADC) is used to decide suitable generation orders for different visual synthesis tasks and learn order-aware positional embeddings. Compared to DALL-E, Imagen and Parti, NUWA-Infinity can generate high-resolution images with arbitrary sizes and support long-duration video generation additionally. Compared to NUWA, which also covers images and videos, NUWA-Infinity has superior visual synthesis capabilities in terms of resolution and variable-size generation. The GitHub link is https://github.com/microsoft/NUWA. The homepage link is https://nuwa-infinity.microsoft.com.

PaperPDFCode

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

Code

microsoft/nuwa officialmentioned in papermentioned on GitHub 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image OutpaintingText-to-Image GenerationVideo Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Outpainting LHQC NUWA-Infinity w/o text Block-FID (Right Extend) 6.43 #1 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity w/o text Block-FID (Down Extend) 11.47 #1 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity w/o text Block-FID (Left Extend) 6.71 #1 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity w/o text Block-FID (Up Extend) 8.03 #1 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity Block-FID (Right Extend) 6.45 #2 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity Block-FID (Down Extend) 9.84 #2 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity Block-FID (Left Extend) 6.72 #2 of 4 Archive leaderboard report
Image Outpainting LHQC NUWA-Infinity Block-FID (Up Extend) 7.43 #2 of 4 Archive leaderboard report
Text-to-Image Generation LHQC NUWA-Infinity Block-FID 9.71 #1 of 3 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.

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