{"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/unleashing-transformers-parallel-token","title":"Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes","arxiv_id":"2111.12701","date":"2021-11-24","proceeding":null,"authors":["Sam Bond-Taylor","Peter Hessey","Hiroshi Sasaki","Toby P. Breckon","Chris G. Willcocks"],"abstract":"Whilst diffusion probabilistic models can generate high quality image content, key limitations remain in terms of both generating high-resolution imagery and their associated high computational requirements. Recent Vector-Quantized image models have overcome this limitation of image resolution but are prohibitively slow and unidirectional as they generate tokens via element-wise autoregressive sampling from the prior. By contrast, in this paper we propose a novel discrete diffusion probabilistic model prior which enables parallel prediction of Vector-Quantized tokens by using an unconstrained Transformer architecture as the backbone. During training, tokens are randomly masked in an order-agnostic manner and the Transformer learns to predict the original tokens. This parallelism of Vector-Quantized token prediction in turn facilitates unconditional generation of globally consistent high-resolution and diverse imagery at a fraction of the computational expense. In this manner, we can generate image resolutions exceeding that of the original training set samples whilst additionally provisioning per-image likelihood estimates (in a departure from generative adversarial approaches). Our approach achieves state-of-the-art results in terms of Density (LSUN Bedroom: 1.51; LSUN Churches: 1.12; FFHQ: 1.20) and Coverage (LSUN Bedroom: 0.83; LSUN Churches: 0.73; FFHQ: 0.80), and performs competitively on FID (LSUN Bedroom: 3.64; LSUN Churches: 4.07; FFHQ: 6.11) whilst offering advantages in terms of both computation and reduced training set requirements.","url_abs":"https://arxiv.org/abs/2111.12701v1","url_pdf":"https://arxiv.org/pdf/2111.12701v1.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":"unleashing-transformers-parallel-token","repo_url":"https://github.com/samb-t/unleashing-transformers","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unleashing-transformers-parallel-token","repo_url":"https://github.com/Arktis2022/mini-vq-discrete-absorbing-diffusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"unleashing-transformers-parallel-token","repo_url":"https://github.com/samb-t/x2ct-vqvae","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-generation","task_name":"Image Generation"}],"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-ffhq-256-x-256","task":"Image Generation","dataset":"FFHQ 256 x 256","model":"Unleashing Transformers","rank_in_archive_order":28,"of":51,"metrics":{"FID":"6.11"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-ffhq-256-x-256","task":"Image Generation","dataset":"FFHQ 256 x 256","model":"Unleashing Transformers (DINOv2)","rank_in_archive_order":45,"of":51,"metrics":{"FD":"393.45","Precision":"0.76","Recall":"0.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-256-x-256","task":"Image Generation","dataset":"LSUN Bedroom 256 x 256","model":"Unleashing Transformers","rank_in_archive_order":7,"of":32,"metrics":{"FID":"3.64"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-lsun-bedroom-256-x-256","task":"Image Generation","dataset":"LSUN Bedroom 256 x 256","model":"Unleashing Transformers (DINOv2)","rank_in_archive_order":25,"of":32,"metrics":{"FD":"440.04","Precision":"0.78","Recall":"0.41"},"uses_additional_data":false},{"leaderboard":"/sota/image-generation-on-lsun-churches-256-x-256","task":"Image Generation","dataset":"LSUN Churches 256 x 256","model":"Unleashing Transformers","rank_in_archive_order":14,"of":27,"metrics":{"FID":"4.07"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.12701","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}