{"url":"/sota/style-transfer-on-stylebench","task":{"name":"Style Transfer","url":"/task/style-transfer","note":null},"dataset":{"name":"StyleBench","url":"/dataset/stylebench"},"category":"Computer Vision","categories":["Computer Vision"],"category_note":null,"description":"**Style Transfer** is a technique in computer vision and graphics that involves generating a new image by combining the content of one image with the style of another image. The goal of style transfer is to create an image that preserves the content of the original image while applying the visual style of another image.\r\n\r\n<span style=\"color:grey; opacity: 0.6\">( Image credit: [A Neural Algorithm of Artistic Style](https://arxiv.org/pdf/1508.06576v2.pdf) )</span>\r\n\r\n1. \"T\" as a sofa:\r\n\r\nThe \"T\" horizontal strip can mimic the back of a sofa with a delicate cushion or details of the uphols or appliances with the color button.\r\n\r\nThe \"T\" vertical strip can show a feet or arm of the sofa, shiny, yet firm.\r\n\r\n\r\n\r\n2. Merge \"P\":\r\n\r\nPut \"P\" next to \"T\", your curve to delicately with the top \"T.\" It is intertwined. The circular part of \"P\" can show a cushion or a curved chair and synchronize the subject of furniture.\r\n\r\nMake sure \"P\" is visually relying on \"T\", which reflects the relationship of cohesion and balance.\r\n\r\n\r\n\r\n5. Coherence of \"B\" and \"I\":\r\n\r\n\"B\" can be aligned as a pair of cushions or a modern chair, with mild curves with glossy and modern aesthetics.\r\n\r\n\"I\" can be a symbol of a shiny furniture or a vertical light bar and completes the shapes without overburdess them.\r\n\r\n\r\n\r\nColor palette 4:\r\n\r\nIncludes soft soil colors such as beige, top and gray shades, along with silent or silver gold tips to touch elegance.\r\n\r\nConsider a slope effect to enhance modernity, to keep colors elegant and complex.\r\n\r\n\r\n\r\n5. Connect the letters:\r\n\r\nUse the overlap or intertwined edges that the letters meet for the symbol of unity.\r\n\r\nThe plan should allow viewers to distinguish each letter while feeling part of the same \"structure\".\r\n\r\n\r\n\r\n6. Background patterns:\r\n\r\nUse delicate geometric patterns or textures that mimic fabrics or furniture materials such as wood seeds or woven fibers.\r\n\r\nThese patterns must remain minimalist and focus on highlighting the logo, while maintaining communication.\r\n\r\n\r\n\r\n\r\nWhile it deals with the subject of furniture and design, this concept conveys modernity, creativity and professional. If you like, I can create a draft design for better visualization.","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["CLIP Score"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"CLIP Score":"higher"}},"counts":{"rows":7,"rows_with_code":7,"rows_with_paper_page":7,"rows_dated":7,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"StyleShot","metrics":{"CLIP Score":"0.660"},"uses_additional_data":false,"paper_date":"2024-07-01","paper":"/paper/styleshot-a-snapshot-on-any-style","paper_url":"https://arxiv.org/abs/2407.01414v1","paper_title":"StyleShot: A Snapshot on Any Style","code":"https://github.com/open-mmlab/StyleShot","n_code_links":2,"syntology":{"n_ran":5,"n_unverified":4,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":2,"model":"StyleID","metrics":{"CLIP Score":"0.604"},"uses_additional_data":false,"paper_date":"2023-12-11","paper":"/paper/style-injection-in-diffusion-a-training-free","paper_url":"https://arxiv.org/abs/2312.09008v2","paper_title":"Style Injection in Diffusion: A Training-free Approach for Adapting Large-scale Diffusion Models for Style Transfer","code":"https://github.com/jiwoogit/StyleID","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}},{"rank_in_archive_order":3,"model":"StrTR-2","metrics":{"CLIP Score":"0.586"},"uses_additional_data":false,"paper_date":"2022-01-01","paper":"/paper/stytr2-image-style-transfer-with-transformers","paper_url":"http://openaccess.thecvf.com//content/CVPR2022/html/Deng_StyTr2_Image_Style_Transfer_With_Transformers_CVPR_2022_paper.html","paper_title":"StyTr2: Image Style Transfer With Transformers","code":"https://github.com/diyiiyiii/StyTR-2","n_code_links":3,"syntology":null},{"rank_in_archive_order":4,"model":"CAST","metrics":{"CLIP Score":"0.575"},"uses_additional_data":false,"paper_date":"2022-05-19","paper":"/paper/domain-enhanced-arbitrary-image-style","paper_url":"https://arxiv.org/abs/2205.09542v2","paper_title":"Domain Enhanced Arbitrary Image Style Transfer via Contrastive Learning","code":"https://github.com/zyxelsa/cast_pytorch","n_code_links":1,"syntology":{"n_ran":4,"n_unverified":5,"n_samples":9,"n_pointer_only_licence":0}},{"rank_in_archive_order":5,"model":"AdaAttN","metrics":{"CLIP Score":"0.569"},"uses_additional_data":false,"paper_date":"2021-08-08","paper":"/paper/adaattn-revisit-attention-mechanism-in","paper_url":"https://arxiv.org/abs/2108.03647v2","paper_title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","code":"https://github.com/huage001/adaattn","n_code_links":3,"syntology":{"n_ran":5,"n_unverified":0,"n_samples":5,"n_pointer_only_licence":4}},{"rank_in_archive_order":6,"model":"InST","metrics":{"CLIP Score":"0.569"},"uses_additional_data":false,"paper_date":"2022-11-23","paper":"/paper/inversion-based-creativity-transfer-with","paper_url":"https://arxiv.org/abs/2211.13203v3","paper_title":"Inversion-Based Style Transfer with Diffusion Models","code":"https://github.com/zyxelsa/InST","n_code_links":1,"syntology":null},{"rank_in_archive_order":7,"model":"EFDM","metrics":{"CLIP Score":"0.561"},"uses_additional_data":false,"paper_date":"2022-03-15","paper":"/paper/exact-feature-distribution-matching-for","paper_url":"https://arxiv.org/abs/2203.07740v2","paper_title":"Exact Feature Distribution Matching for Arbitrary Style Transfer and Domain Generalization","code":"https://github.com/ybzh/efdm","n_code_links":2,"syntology":{"n_ran":4,"n_unverified":11,"n_samples":15,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,264 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6264,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":3316},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":5,"rows_with_any_sample_ran":5,"distinct_papers_with_graph_line":5,"distinct_papers_with_any_sample_ran":5,"samples_over_distinct_papers":{"n_ran":21,"n_unverified":20,"n_samples":41,"n_pointer_only_licence":4,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":21,"n_unverified":20,"n_samples":41,"n_pointer_only_licence":4,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}