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 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 10 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 10 ran (9 with no instrument failure; 1 where Syntology's instrument failed). 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 between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/magvit officialmentioned on GitHubjaxApache-2.0Syntology: 10 samples, 10 ran (1 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

10 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 1 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.

1ran · our draft was wrong
9ran

Licence: 1 of the 10 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. 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.

google-research/magvit official repository 10 samples, 10 ran (1 instrument-failed) · 0 unverified
frame_interpolation_cond videogvt/train_lib/cond_utils.py ran Apache-2.0 (permissive) · 1a792a8e5a6e134c · report fixture: signature input_video:ArrayImpl/5/float, cond_frames:int/0/int, cond_padding:str/0/str, cond_latent_frames:int/0/int, latent_shape:tuple/1/int · returned dict · level recorded 2026-09-25
frame_prediction_cond videogvt/train_lib/cond_utils.py ran Apache-2.0 (permissive) · 0f46f383ab81bf4b · report fixture: signature input_video:ArrayImpl/5/float, cond_frames:int/0/int, cond_padding:str/0/str, cond_latent_frames:int/0/int, latent_shape:tuple/1/int, prefix_condition:bool/0/bool · returned dict · level recorded 2026-09-25
get_norm_layer in 111 papers videogvt/models/model_utils.py ran Apache-2.0 (permissive) · b87899e786e53909 · report fixture: signature norm_type:str/0/str, dtype:callable/0/? · returned partial · level recorded 2026-09-25
l2_normalize in 40 papers
census: 15 implementations from 13 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
videogvt/models/vqvae.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 6355c1dcf1ced438 · report fixture: signature x:ArrayImpl/2/float, axis:NoneType/0/?, epsilon:float/0/float · returned ArrayImpl · level recorded 2026-09-22
latent_frame_prediction_cond videogvt/train_lib/cond_utils.py ran Apache-2.0 (permissive) · d73c517c7648170b · report fixture: signature input_video:ArrayImpl/5/float, cond_latent_frames:int/0/int, latent_shape:tuple/1/int · returned dict · level recorded 2026-09-25
sinusoidal_init videogvt/models/transformer_lm.py ran Apache-2.0 (permissive) · 0fd41694a130f120 · report fixture: signature max_len:int/0/int, min_scale:float/0/float, max_scale:float/0/float · returned function · level recorded 2026-09-25
tensorflow_style_avg_pooling videogvt/models/model_utils.py ran Apache-2.0 (permissive) · 38e696a22dc81a6f · report fixture: signature x:ArrayImpl/4/float, window_shape:tuple/1/int, strides:tuple/1/int, padding:str/0/str · returned ArrayImpl · level recorded 2026-09-26
truncated_normal in 12 papers videogvt/models/simplified_bert.py ran Apache-2.0 (permissive) · 4d2dd72078f90cca · report fixture: signature stddev:float/0/float, dtype:callable/0/? · returned function · level recorded 2026-09-25
truncated_normal in 12 papers videogvt/models/t5_bert.py ran Apache-2.0 (permissive) · 0c839479ca2b7173 · report fixture: signature stddev:float/0/float, dtype:callable/0/? · returned function · level recorded 2026-09-25
vmap_t_dim videogvt/models/model_utils.py ran Apache-2.0 (permissive) · ac4f595178d50862 · report fixture: signature module:callable/0/? · returned type · level recorded 2026-09-25

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