{"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/improving-diffusion-models-for-virtual-try-on","title":"Improving Diffusion Models for Authentic Virtual Try-on in the Wild","arxiv_id":"2403.05139","date":"2024-03-08","proceeding":null,"authors":["Yisol Choi","Sangkyung Kwak","Kyungmin Lee","Hyungwon Choi","Jinwoo Shin"],"abstract":"This paper considers image-based virtual try-on, which renders an image of a person wearing a curated garment, given a pair of images depicting the person and the garment, respectively. Previous works adapt existing exemplar-based inpainting diffusion models for virtual try-on to improve the naturalness of the generated visuals compared to other methods (e.g., GAN-based), but they fail to preserve the identity of the garments. To overcome this limitation, we propose a novel diffusion model that improves garment fidelity and generates authentic virtual try-on images. Our method, coined IDM-VTON, uses two different modules to encode the semantics of garment image; given the base UNet of the diffusion model, 1) the high-level semantics extracted from a visual encoder are fused to the cross-attention layer, and then 2) the low-level features extracted from parallel UNet are fused to the self-attention layer. In addition, we provide detailed textual prompts for both garment and person images to enhance the authenticity of the generated visuals. Finally, we present a customization method using a pair of person-garment images, which significantly improves fidelity and authenticity. Our experimental results show that our method outperforms previous approaches (both diffusion-based and GAN-based) in preserving garment details and generating authentic virtual try-on images, both qualitatively and quantitatively. Furthermore, the proposed customization method demonstrates its effectiveness in a real-world scenario. More visualizations are available in our project page: https://idm-vton.github.io","url_abs":"https://arxiv.org/abs/2403.05139v3","url_pdf":"https://arxiv.org/pdf/2403.05139v3.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":"improving-diffusion-models-for-virtual-try-on","repo_url":"https://github.com/yisol/IDM-VTON","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"virtual-try-on","task_name":"Virtual Try-on"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"pixel-prediction","method_name":"Inpainting"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/virtual-try-on-on-viton-hd","task":"Virtual Try-on","dataset":"VITON-HD","model":"IDM-VTON","rank_in_archive_order":2,"of":5,"metrics":{"FID":"6.290"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2403.05139","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.05139"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/yisol/IDM-VTON","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":6,"ran":2,"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":6,"samples":[{"code_sha256_prefix":"cee8fc91e868c8f9","entry":"mask_pil_to_torch","repo":"yisol/IDM-VTON","repo_kind":"official","path":"src/tryon_pipeline.py","file_url":"https://github.com/yisol/IDM-VTON/blob/HEAD/src/tryon_pipeline.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":"cee8fc91e868c8f9"}},{"code_sha256_prefix":"bea2d776a332f2b0","entry":"rescale_noise_cfg","repo":"yisol/IDM-VTON","repo_kind":"official","path":"src/tryon_pipeline.py","file_url":"https://github.com/yisol/IDM-VTON/blob/HEAD/src/tryon_pipeline.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bea2d776a332f2b0"}},{"code_sha256_prefix":"13618485a328150e","entry":"pil_to_tensor","repo":"yisol/IDM-VTON","repo_kind":"official","path":"inference.py","file_url":"https://github.com/yisol/IDM-VTON/blob/HEAD/inference.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"13618485a328150e"}},{"code_sha256_prefix":"72fd33f831a6b39a","entry":"prepare_mask_and_masked_image","repo":"yisol/IDM-VTON","repo_kind":"official","path":"src/tryon_pipeline.py","file_url":"https://github.com/yisol/IDM-VTON/blob/HEAD/src/tryon_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"72fd33f831a6b39a"}},{"code_sha256_prefix":"d952d20e01c93669","entry":"register_action","repo":"yisol/IDM-VTON","repo_kind":"official","path":"gradio_demo/apply_net.py","file_url":"https://github.com/yisol/IDM-VTON/blob/HEAD/gradio_demo/apply_net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d952d20e01c93669"}},{"code_sha256_prefix":"d81381b327c76edd","entry":"zero_module","repo":"yisol/IDM-VTON","repo_kind":"official","path":"src/unet_hacked_garmnet.py","file_url":"https://github.com/yisol/IDM-VTON/blob/HEAD/src/unet_hacked_garmnet.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d81381b327c76edd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}