Papers › MaskBit: Embedding-free Image Generation via Bit Tokens

MaskBit: Embedding-free Image Generation via Bit Tokens

24 Sep 2024arXiv:2409.16211archive 2025-07-28

Mark Weber, Lijun Yu, Qihang Yu, Xueqing Deng, Xiaohui Shen, Daniel Cremers, Liang-Chieh Chen

Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subsequent Transformer model for image generation within latent space - these frameworks offer promising avenues for image synthesis. In this study, we present two primary contributions: Firstly, an empirical and systematic examination of VQGANs, leading to a modernized VQGAN. Secondly, a novel embedding-free generation network operating directly on bit tokens - a binary quantized representation of tokens with rich semantics. The first contribution furnishes a transparent, reproducible, and high-performing VQGAN model, enhancing accessibility and matching the performance of current state-of-the-art methods while revealing previously undisclosed details. The second contribution demonstrates that embedding-free image generation using bit tokens achieves a new state-of-the-art FID of 1.52 on the ImageNet 256x256 benchmark, with a compact generator model of mere 305M parameters. The code for this project is available on https://github.com/markweberdev/maskbit.

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="2409.16211")

Code

Syntology Ran 8 of 9 code samples harvested from 1 repository linked to this paper; 1 has no recorded run. Of those that ran: 8 ran with no contract checked.

By repository: official repository: 9 samples from 1 repository, 8 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

markweberdev/maskbit officialmentioned in papermentioned on GitHubpytorchApache-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

9 samples harvested; 8 ran; 0 honoured the contract we drafted; 1 has no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

8ran
1unverified

Licence: 0 of the 9 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 markweberdev/maskbit. “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.

GroupNorm markweberdev/maskbit/modeling/modules/autoencoder.py official repository ran Apache-2.0 (permissive) · 1b67cc51b6ce545e · report
combine_factorized_tokens markweberdev/maskbit/modeling/modules/factorization.py official repository ran Apache-2.0 (permissive) · 888ad2f4676204ef · report
gaussian markweberdev/maskbit/evaluator/evaluator.py official repository ran fingerprinted Apache-2.0 (permissive) · 14e3dcfc8720603e · report
gaussian_or_uniform_kernel markweberdev/maskbit/evaluator/evaluator.py official repository ran Apache-2.0 (permissive) · 5e50e645acfa2ea4 · report
get_parameter_device markweberdev/maskbit/modeling/modules/base_model.py official repository ran Apache-2.0 (permissive) · 15b15fd38b1be58f · report
get_parameter_dtype markweberdev/maskbit/modeling/modules/base_model.py official repository ran Apache-2.0 (permissive) · b446f315513cb2bb · report
split_factorized_tokens markweberdev/maskbit/modeling/modules/factorization.py official repository ran Apache-2.0 (permissive) · bd83bc035cdd8b3c · report
uniform markweberdev/maskbit/evaluator/evaluator.py official repository ran fingerprinted Apache-2.0 (permissive) · 3695852af4744be5 · report
get_config markweberdev/maskbit/demo_utils.py official repository unverified Apache-2.0 (permissive) · 0472c7f5a63917e6 · report

Tasks

Conditional Image GenerationImage GenerationImage Reconstruction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation ImageNet 256x256 MaskBit FID 1.52 #21 of 94 Archive leaderboard report
Image Reconstruction ImageNet MaskBit (16x16) FID 1.66 #10 of 15 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