{"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/meissonic-revitalizing-masked-generative","title":"Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis","arxiv_id":"2410.08261","date":"2024-10-10","proceeding":null,"authors":["Jinbin Bai","Tian Ye","Wei Chow","Enxin Song","Qing-Guo Chen","Xiangtai Li","Zhen Dong","Lei Zhu","Shuicheng Yan"],"abstract":"We present Meissonic, which elevates non-autoregressive masked image modeling (MIM) text-to-image to a level comparable with state-of-the-art diffusion models like SDXL. By incorporating a comprehensive suite of architectural innovations, advanced positional encoding strategies, and optimized sampling conditions, Meissonic substantially improves MIM's performance and efficiency. Additionally, we leverage high-quality training data, integrate micro-conditions informed by human preference scores, and employ feature compression layers to further enhance image fidelity and resolution. Our model not only matches but often exceeds the performance of existing models like SDXL in generating high-quality, high-resolution images. Extensive experiments validate Meissonic's capabilities, demonstrating its potential as a new standard in text-to-image synthesis. We release a model checkpoint capable of producing $1024 \\times 1024$ resolution images.","url_abs":"https://arxiv.org/abs/2410.08261v3","url_pdf":"https://arxiv.org/pdf/2410.08261v3.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":"meissonic-revitalizing-masked-generative","repo_url":"https://github.com/viiika/Meissonic","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-compression","task_name":"Feature Compression"},{"task_slug":"image-generation","task_name":"Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.08261","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.08261"}},"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/viiika/Meissonic","reach":null}],"summary":{"ran":1,"ran_fixture":3,"unverified":8},"by_repo_kind":{"official":{"samples":12,"ran":4,"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":"d7869221fbf85eed","entry":"FluxPosEmbed","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d7869221fbf85eed"}},{"code_sha256_prefix":"5267e615858f198f","entry":"get_1d_rotary_pos_embed","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5267e615858f198f"}},{"code_sha256_prefix":"648219193abb0da5","entry":"get_2d_rotary_pos_embed","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"648219193abb0da5"}},{"code_sha256_prefix":"7baace01d2459d49","entry":"get_3d_rotary_pos_embed","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7baace01d2459d49"}},{"code_sha256_prefix":"b5bd4bc3ff1420f4","entry":"ConvMlmLayer","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"b5bd4bc3ff1420f4"}},{"code_sha256_prefix":"76e74eb4929058d0","entry":"FusedFluxAttnProcessor2_0","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"76e74eb4929058d0"}},{"code_sha256_prefix":"65d68c48e8af4c9e","entry":"Simple_UVitBlock","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"65d68c48e8af4c9e"}},{"code_sha256_prefix":"f738ac02f57b6614","entry":"SingleTransformerBlock","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"f738ac02f57b6614"}},{"code_sha256_prefix":"a11765e9087a4203","entry":"Transformer2DModel","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"a11765e9087a4203"}},{"code_sha256_prefix":"8d6351d29b4f55c6","entry":"TransformerBlock","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"8d6351d29b4f55c6"}},{"code_sha256_prefix":"2c3b0dc5adf5f251","entry":"UVit2DConvEmbed","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"2c3b0dc5adf5f251"}},{"code_sha256_prefix":"837ad33d0af915e3","entry":"get_2d_rotary_pos_embed_from_grid","repo":"viiika/Meissonic","repo_kind":"official","path":"src/transformer.py","file_url":"https://github.com/viiika/Meissonic/blob/HEAD/src/transformer.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":"837ad33d0af915e3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}