{"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/stylealign-analysis-and-applications-of-1","title":"StyleAlign: Analysis and Applications of Aligned StyleGAN Models","arxiv_id":"2110.11323","date":"2021-10-21","proceeding":"ICLR 2022 4","authors":["Zongze Wu","Yotam Nitzan","Eli Shechtman","Dani Lischinski"],"abstract":"In this paper, we perform an in-depth study of the properties and applications of aligned generative models. We refer to two models as aligned if they share the same architecture, and one of them (the child) is obtained from the other (the parent) via fine-tuning to another domain, a common practice in transfer learning. Several works already utilize some basic properties of aligned StyleGAN models to perform image-to-image translation. Here, we perform the first detailed exploration of model alignment, also focusing on StyleGAN. First, we empirically analyze aligned models and provide answers to important questions regarding their nature. In particular, we find that the child model's latent spaces are semantically aligned with those of the parent, inheriting incredibly rich semantics, even for distant data domains such as human faces and churches. Second, equipped with this better understanding, we leverage aligned models to solve a diverse set of tasks. In addition to image translation, we demonstrate fully automatic cross-domain image morphing. We further show that zero-shot vision tasks may be performed in the child domain, while relying exclusively on supervision in the parent domain. We demonstrate qualitatively and quantitatively that our approach yields state-of-the-art results, while requiring only simple fine-tuning and inversion.","url_abs":"https://arxiv.org/abs/2110.11323v2","url_pdf":"https://arxiv.org/pdf/2110.11323v2.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":"stylealign-analysis-and-applications-of-1","repo_url":"https://github.com/betterze/StyleAlign","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"image-morphing","task_name":"Image Morphing"},{"task_slug":"image-to-image-translation","task_name":"Image-to-Image Translation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"adaptive-instance-normalization","method_name":"Adaptive Instance Normalization"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"r1-regularization","method_name":"R1 Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.11323","atlas_url":"https://app.syntology.ai/?focus=2110.11323","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.11323"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/betterze/StyleAlign","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":8,"ran":7,"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":"5f29485b61b61e01","entry":"LoadImgs","repo":"betterze/StyleAlign","repo_kind":"official","path":"Compare.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/Compare.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5f29485b61b61e01"}},{"code_sha256_prefix":"4d32fab0d29f76e9","entry":"PadBE","repo":"betterze/StyleAlign","repo_kind":"official","path":"MergeFace.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/MergeFace.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4d32fab0d29f76e9"}},{"code_sha256_prefix":"6607c09e75863fdb","entry":"Truncation","repo":"betterze/StyleAlign","repo_kind":"official","path":"MultiModal.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/MultiModal.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6607c09e75863fdb"}},{"code_sha256_prefix":"c58660ddda6b037e","entry":"adjust_pixel_range","repo":"betterze/StyleAlign","repo_kind":"official","path":"visualizer.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/visualizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c58660ddda6b037e"}},{"code_sha256_prefix":"94f09a41da3392b4","entry":"get_blank_image","repo":"betterze/StyleAlign","repo_kind":"official","path":"visualizer.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/visualizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94f09a41da3392b4"}},{"code_sha256_prefix":"95227e49b00a5ef8","entry":"get_grid_shape","repo":"betterze/StyleAlign","repo_kind":"official","path":"visualizer.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/visualizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95227e49b00a5ef8"}},{"code_sha256_prefix":"0c45399f3741921e","entry":"lerp","repo":"betterze/StyleAlign","repo_kind":"official","path":"MergeFace.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/MergeFace.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c45399f3741921e"}},{"code_sha256_prefix":"6e1c6773a9fbe6dd","entry":"get_plugin","repo":"betterze/StyleAlign","repo_kind":"official","path":"dnnlib/tflib/custom_ops.py","file_url":"https://github.com/betterze/StyleAlign/blob/HEAD/dnnlib/tflib/custom_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e1c6773a9fbe6dd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}