Papers › MAGVIT: Masked Generative Video Transformer

MAGVIT: Masked Generative Video Transformer

10 Dec 2022CVPR 2023 1arXiv:2212.05199archive 2025-07-28

Lijun Yu, Yong Cheng, Kihyuk Sohn, José Lezama, Han Zhang, Huiwen Chang, Alexander G. Hauptmann, Ming-Hsuan Yang, Yuan Hao, Irfan Essa, Lu Jiang

We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spatial-temporal visual tokens and propose an embedding method for masked video token modeling to facilitate multi-task learning. We conduct extensive experiments to demonstrate the quality, efficiency, and flexibility of MAGVIT. Our experiments show that (i) MAGVIT performs favorably against state-of-the-art approaches and establishes the best-published FVD on three video generation benchmarks, including the challenging Kinetics-600. (ii) MAGVIT outperforms existing methods in inference time by two orders of magnitude against diffusion models and by 60x against autoregressive models. (iii) A single MAGVIT model supports ten diverse generation tasks and generalizes across videos from different visual domains. The source code and trained models will be released to the public at https://magvit.cs.cmu.edu.

PaperPDFConference PDFCodeCode 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="2212.05199")

Code

Syntology Ran 1 of 10 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 10 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

google-research/magvit officialmentioned on GitHubjaxApache-2.0 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

10 samples harvested; 1 ran; 0 honoured the contract we drafted; 9 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.

1ran · our draft was wrong
9unverified

Licence: 0 of the 10 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 google-research/magvit. “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.

l2_normalize google-research/magvit/videogvt/models/vqvae.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 6355c1dcf1ced438 · report
frame_interpolation_cond google-research/magvit/videogvt/train_lib/cond_utils.py official repository unverified Apache-2.0 (permissive) · 1a792a8e5a6e134c · report
frame_prediction_cond google-research/magvit/videogvt/train_lib/cond_utils.py official repository unverified Apache-2.0 (permissive) · 0f46f383ab81bf4b · report
get_norm_layer google-research/magvit/videogvt/models/model_utils.py official repository unverified Apache-2.0 (permissive) · b87899e786e53909 · report
latent_frame_prediction_cond google-research/magvit/videogvt/train_lib/cond_utils.py official repository unverified Apache-2.0 (permissive) · d73c517c7648170b · report
sinusoidal_init google-research/magvit/videogvt/models/transformer_lm.py official repository unverified Apache-2.0 (permissive) · 0fd41694a130f120 · report
tensorflow_style_avg_pooling google-research/magvit/videogvt/models/model_utils.py official repository unverified Apache-2.0 (permissive) · 38e696a22dc81a6f · report
truncated_normal google-research/magvit/videogvt/models/simplified_bert.py official repository unverified Apache-2.0 (permissive) · 4d2dd72078f90cca · report
truncated_normal google-research/magvit/videogvt/models/t5_bert.py official repository unverified Apache-2.0 (permissive) · 0c839479ca2b7173 · report
vmap_t_dim google-research/magvit/videogvt/models/model_utils.py official repository unverified Apache-2.0 (permissive) · ac4f595178d50862 · report

Tasks

Multi-Task LearningText-to-Video GenerationVideo GenerationVideo Prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Text-to-Video Generation Something-Something V2 MAGVIT FVD 79.1 #1 of 1 Archive leaderboard report
Video Generation BAIR Robot Pushing MAGVIT Cond 1 #1 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MAGVIT FVD score 62 #1 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MAGVIT Pred 15 #1 of 31 Archive leaderboard report
Video Generation BAIR Robot Pushing MAGVIT Train 15 #1 of 31 Archive leaderboard report
Video Generation Kinetics-600 12 frames, 64x64 MAGVIT FVD 9.9 #3 of 4 Archive leaderboard report
Video Generation UCF-101 MAGVIT (-L-CG, 128x128, class-conditional) FVD16 76±2 #7 of 48 Archive leaderboard report
Video Generation UCF-101 MAGVIT (-L-CG, 128x128, class-conditional) Inception Score 89.27±0.15 #7 of 48 Archive leaderboard report
Video Generation UCF-101 MAGVIT (-B-CG, 128x128, class-conditional) FVD16 159±2 #12 of 48 Archive leaderboard report
Video Generation UCF-101 MAGVIT (-B-CG, 128x128, class-conditional) Inception Score 83.55±0.14 #12 of 48 Archive leaderboard report
Video Generation UCF-101 MAGVIT (AR) FVD16 265 #19 of 48 Archive leaderboard report
Video Prediction BAIR Robot Pushing MAGVIT (-L-FP) FVD 62±0.1 #1 of 6 Archive leaderboard report
Video Prediction BAIR Robot Pushing MAGVIT (-B-FP) FVD 76±0.1 #2 of 6 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 MAGVIT (-L-FP) Cond 5 #5 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 MAGVIT (-L-FP) FVD 9.9±0.3 #5 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 MAGVIT (-L-FP) Pred 11 #5 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 MAGVIT (-B-FP) Cond 5 #9 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 MAGVIT (-B-FP) FVD 24.5±0.9 #9 of 16 Archive leaderboard report
Video Prediction Kinetics-600 12 frames, 64x64 MAGVIT (-B-FP) Pred 11 #9 of 16 Archive leaderboard report
Video Prediction Something-Something V2 MAGVIT FVD 28.5 #1 of 1 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDiffusionDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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