{"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/ootdiffusion-outfitting-fusion-based-latent","title":"OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on","arxiv_id":"2403.01779","date":"2024-03-04","proceeding":null,"authors":["Yuhao Xu","Tao Gu","Weifeng Chen","Chengcai Chen"],"abstract":"We present OOTDiffusion, a novel network architecture for realistic and controllable image-based virtual try-on (VTON). We leverage the power of pretrained latent diffusion models, designing an outfitting UNet to learn the garment detail features. Without a redundant warping process, the garment features are precisely aligned with the target human body via the proposed outfitting fusion in the self-attention layers of the denoising UNet. In order to further enhance the controllability, we introduce outfitting dropout to the training process, which enables us to adjust the strength of the garment features through classifier-free guidance. Our comprehensive experiments on the VITON-HD and Dress Code datasets demonstrate that OOTDiffusion efficiently generates high-quality try-on results for arbitrary human and garment images, which outperforms other VTON methods in both realism and controllability, indicating an impressive breakthrough in virtual try-on. Our source code is available at https://github.com/levihsu/OOTDiffusion.","url_abs":"https://arxiv.org/abs/2403.01779v2","url_pdf":"https://arxiv.org/pdf/2403.01779v2.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":"ootdiffusion-outfitting-fusion-based-latent","repo_url":"https://github.com/levihsu/ootdiffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"ootdiffusion-outfitting-fusion-based-latent","repo_url":"https://github.com/shinechen1024/magicclothing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"virtual-try-on","task_name":"Virtual Try-on"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"dropout","method_name":"Dropout"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.01779","atlas_url":"https://app.syntology.ai/?focus=2403.01779","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.01779"}},"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/levihsu/ootdiffusion","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shinechen1024/magicclothing","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"6680a7cabb28a780","entry":"extend_arm_mask","repo":"levihsu/ootdiffusion","repo_kind":"official","path":"run/utils_ootd.py","file_url":"https://github.com/levihsu/ootdiffusion/blob/HEAD/run/utils_ootd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6680a7cabb28a780"}},{"code_sha256_prefix":"db4da19856d9a8f3","entry":"hole_fill","repo":"levihsu/ootdiffusion","repo_kind":"official","path":"run/utils_ootd.py","file_url":"https://github.com/levihsu/ootdiffusion/blob/HEAD/run/utils_ootd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"db4da19856d9a8f3"}},{"code_sha256_prefix":"672778efe4331be2","entry":"refine_mask","repo":"levihsu/ootdiffusion","repo_kind":"official","path":"run/utils_ootd.py","file_url":"https://github.com/levihsu/ootdiffusion/blob/HEAD/run/utils_ootd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"672778efe4331be2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}