{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/maskbit-embedding-free-image-generation-via","title":"MaskBit: Embedding-free Image Generation via Bit Tokens","arxiv_id":"2409.16211","date":"2024-09-24","proceeding":null,"authors":["Mark Weber","Lijun Yu","Qihang Yu","Xueqing Deng","Xiaohui Shen","Daniel Cremers","Liang-Chieh Chen"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2409.16211v2","url_pdf":"https://arxiv.org/pdf/2409.16211v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"maskbit-embedding-free-image-generation-via","repo_url":"https://github.com/markweberdev/maskbit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"conditional-image-generation","task_name":"Conditional Image Generation"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"MaskBit","rank_in_archive_order":21,"of":94,"metrics":{"FID":"1.52"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-imagenet","task":"Image Reconstruction","dataset":"ImageNet","model":"MaskBit (16x16)","rank_in_archive_order":10,"of":15,"metrics":{"FID":"1.66"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.16211","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.16211"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/markweberdev/maskbit","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":8,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"1b67cc51b6ce545e","entry":"GroupNorm","repo":"markweberdev/maskbit","repo_kind":"official","path":"modeling/modules/autoencoder.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/modeling/modules/autoencoder.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b67cc51b6ce545e"}},{"code_sha256_prefix":"888ad2f4676204ef","entry":"combine_factorized_tokens","repo":"markweberdev/maskbit","repo_kind":"official","path":"modeling/modules/factorization.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/modeling/modules/factorization.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"888ad2f4676204ef"}},{"code_sha256_prefix":"14e3dcfc8720603e","entry":"gaussian","repo":"markweberdev/maskbit","repo_kind":"official","path":"evaluator/evaluator.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/evaluator/evaluator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14e3dcfc8720603e"}},{"code_sha256_prefix":"5e50e645acfa2ea4","entry":"gaussian_or_uniform_kernel","repo":"markweberdev/maskbit","repo_kind":"official","path":"evaluator/evaluator.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/evaluator/evaluator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e50e645acfa2ea4"}},{"code_sha256_prefix":"15b15fd38b1be58f","entry":"get_parameter_device","repo":"markweberdev/maskbit","repo_kind":"official","path":"modeling/modules/base_model.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/modeling/modules/base_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15b15fd38b1be58f"}},{"code_sha256_prefix":"b446f315513cb2bb","entry":"get_parameter_dtype","repo":"markweberdev/maskbit","repo_kind":"official","path":"modeling/modules/base_model.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/modeling/modules/base_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b446f315513cb2bb"}},{"code_sha256_prefix":"bd83bc035cdd8b3c","entry":"split_factorized_tokens","repo":"markweberdev/maskbit","repo_kind":"official","path":"modeling/modules/factorization.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/modeling/modules/factorization.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd83bc035cdd8b3c"}},{"code_sha256_prefix":"3695852af4744be5","entry":"uniform","repo":"markweberdev/maskbit","repo_kind":"official","path":"evaluator/evaluator.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/evaluator/evaluator.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3695852af4744be5"}},{"code_sha256_prefix":"0472c7f5a63917e6","entry":"get_config","repo":"markweberdev/maskbit","repo_kind":"official","path":"demo_utils.py","file_url":"https://github.com/markweberdev/maskbit/blob/HEAD/demo_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0472c7f5a63917e6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}