{"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/anymaker-zero-shot-general-object","title":"CustAny: Customizing Anything from A Single Example","arxiv_id":"2406.11643","date":"2024-06-17","proceeding":"CVPR 2025 1","authors":["Lingjie Kong","Kai Wu","Xiaobin Hu","Wenhui Han","Jinlong Peng","Chengming Xu","Donghao Luo","Mengtian Li","Jiangning Zhang","Chengjie Wang","Yanwei Fu"],"abstract":"Recent advances in diffusion-based text-to-image models have simplified creating high-fidelity images, but preserving the identity (ID) of specific elements, like a personal dog, is still challenging. Object customization, using reference images and textual descriptions, is key to addressing this issue. Current object customization methods are either object-specific, requiring extensive fine-tuning, or object-agnostic, offering zero-shot customization but limited to specialized domains. The primary issue of promoting zero-shot object customization from specific domains to the general domain is to establish a large-scale general ID dataset for model pre-training, which is time-consuming and labor-intensive. In this paper, we propose a novel pipeline to construct a large dataset of general objects and build the Multi-Category ID-Consistent (MC-IDC) dataset, featuring 315k text-image samples across 10k categories. With the help of MC-IDC, we introduce Customizing Anything (CustAny), a zero-shot framework that maintains ID fidelity and supports flexible text editing for general objects. CustAny features three key components: a general ID extraction module, a dual-level ID injection module, and an ID-aware decoupling module, allowing it to customize any object from a single reference image and text prompt. Experiments demonstrate that CustAny outperforms existing methods in both general object customization and specialized domains like human customization and virtual try-on. Our contributions include a large-scale dataset, the CustAny framework and novel ID processing to advance this field. Code and dataset will be released soon in https://github.com/LingjieKong-fdu/CustAny.","url_abs":"https://arxiv.org/abs/2406.11643v4","url_pdf":"https://arxiv.org/pdf/2406.11643v4.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":"anymaker-zero-shot-general-object","repo_url":"https://github.com/lingjiekong-fdu/anymaker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"anymaker-zero-shot-general-object","repo_url":"https://github.com/lingjiekong-fdu/custany","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"virtual-try-on","task_name":"Virtual Try-on"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.11643","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}