{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/an-image-is-worth-32-tokens-for","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","arxiv_id":"2406.07550","date":"2024-06-11","proceeding":null,"authors":["Qihang Yu","Mark Weber","Xueqing Deng","Xiaohui Shen","Daniel Cremers","Liang-Chieh Chen"],"abstract":"Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational demands compared to directly processing pixels and enhances the effectiveness and efficiency of the generation process. Prior methods, such as VQGAN, typically utilize 2D latent grids with fixed downsampling factors. However, these 2D tokenizations face challenges in managing the inherent redundancies present in images, where adjacent regions frequently display similarities. To overcome this issue, we introduce Transformer-based 1-Dimensional Tokenizer (TiTok), an innovative approach that tokenizes images into 1D latent sequences. TiTok provides a more compact latent representation, yielding substantially more efficient and effective representations than conventional techniques. For example, a 256 x 256 x 3 image can be reduced to just 32 discrete tokens, a significant reduction from the 256 or 1024 tokens obtained by prior methods. Despite its compact nature, TiTok achieves competitive performance to state-of-the-art approaches. Specifically, using the same generator framework, TiTok attains 1.97 gFID, outperforming MaskGIT baseline significantly by 4.21 at ImageNet 256 x 256 benchmark. The advantages of TiTok become even more significant when it comes to higher resolution. At ImageNet 512 x 512 benchmark, TiTok not only outperforms state-of-the-art diffusion model DiT-XL/2 (gFID 2.74 vs. 3.04), but also reduces the image tokens by 64x, leading to 410x faster generation process. Our best-performing variant can significantly surpasses DiT-XL/2 (gFID 2.13 vs. 3.04) while still generating high-quality samples 74x faster.","url_abs":"https://arxiv.org/abs/2406.07550v1","url_pdf":"https://arxiv.org/pdf/2406.07550v1.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":"an-image-is-worth-32-tokens-for","repo_url":"https://github.com/bytedance/1d-tokenizer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"an-image-is-worth-32-tokens-for","repo_url":"https://github.com/lukaslaobeyer/token-opt","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"TiTok-S-128","rank_in_archive_order":46,"of":94,"metrics":{"FID":"1.97"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"TiTok-B-64","rank_in_archive_order":60,"of":94,"metrics":{"FID":"2.48"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-256x256","task":"Image Generation","dataset":"ImageNet 256x256","model":"TiTok-B-32","rank_in_archive_order":63,"of":94,"metrics":{"FID":"2.77"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-512x512","task":"Image Generation","dataset":"ImageNet 512x512","model":"TiTok-B-128","rank_in_archive_order":29,"of":52,"metrics":{"FID":"2.13"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-imagenet-512x512","task":"Image Generation","dataset":"ImageNet 512x512","model":"TiTok-L-64","rank_in_archive_order":34,"of":52,"metrics":{"FID":"2.49"},"uses_additional_data":false},{"leaderboard":"/sota/image-reconstruction-on-imagenet","task":"Image Reconstruction","dataset":"ImageNet","model":"TiTok-S-128","rank_in_archive_order":11,"of":15,"metrics":{"FID":"1.71"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.07550","atlas_url":"https://app.syntology.ai/?focus=2406.07550","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2406.07550"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2406.07550\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2406.07550"},"call":"get_concepts_for_paper(arxiv_id=\"2406.07550\")"}],"by_repo":[{"repo":"bytedance/1d-tokenizer","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2503.10772"],"harvested_for_calls":[{"arxiv_id":"2503.10772","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2503.10772"},"call":"get_harvested_code_for_paper(arxiv_id=\"2503.10772\")"}]},{"repo":"lukaslaobeyer/token-opt","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"eeda7a79a2b28438ddeb0e3bc5d0d4b533026de2c0d014b1acdbad6afb39f26f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}