{"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/subject-diffusion-open-domain-personalized","title":"Subject-Diffusion:Open Domain Personalized Text-to-Image Generation without Test-time Fine-tuning","arxiv_id":"2307.11410","date":"2023-07-21","proceeding":null,"authors":["Jian Ma","Junhao Liang","Chen Chen","Haonan Lu"],"abstract":"Recent progress in personalized image generation using diffusion models has been significant. However, development in the area of open-domain and non-fine-tuning personalized image generation is proceeding rather slowly. In this paper, we propose Subject-Diffusion, a novel open-domain personalized image generation model that, in addition to not requiring test-time fine-tuning, also only requires a single reference image to support personalized generation of single- or multi-subject in any domain. Firstly, we construct an automatic data labeling tool and use the LAION-Aesthetics dataset to construct a large-scale dataset consisting of 76M images and their corresponding subject detection bounding boxes, segmentation masks and text descriptions. Secondly, we design a new unified framework that combines text and image semantics by incorporating coarse location and fine-grained reference image control to maximize subject fidelity and generalization. Furthermore, we also adopt an attention control mechanism to support multi-subject generation. Extensive qualitative and quantitative results demonstrate that our method outperforms other SOTA frameworks in single, multiple, and human customized image generation. Please refer to our \\href{https://oppo-mente-lab.github.io/subject_diffusion/}{project page}","url_abs":"https://arxiv.org/abs/2307.11410v2","url_pdf":"https://arxiv.org/pdf/2307.11410v2.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":"subject-diffusion-open-domain-personalized","repo_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"diffusion-personalization","task_name":"Diffusion Personalization"},{"task_slug":"diffusion-personalization-tuning-free","task_name":"Diffusion Personalization Tuning Free"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"personalized-image-generation","task_name":"Personalized Image Generation"},{"task_slug":"text-to-image-generation-1","task_name":"Text to Image Generation"},{"task_slug":"text-to-image-generation","task_name":"Text-to-Image Generation"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2307.11410","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2307.11410"}},"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/OPPO-Mente-Lab/Subject-Diffusion","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":4},"by_repo_kind":{"official":{"samples":8,"ran":4,"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":"3bb14723b94dbad9","entry":"add_module_args","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/model_utils.py","link_basis":"first_harvest_node","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":"3bb14723b94dbad9"}},{"code_sha256_prefix":"791cc02a10597101","entry":"custom_decoder","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"custom_dataset.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/custom_dataset.py","link_basis":"first_harvest_node","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":"791cc02a10597101"}},{"code_sha256_prefix":"1bcf7e8c5b5dbb4e","entry":"is_valid_bbox","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"custom_dataset.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/custom_dataset.py","link_basis":"first_harvest_node","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":"1bcf7e8c5b5dbb4e"}},{"code_sha256_prefix":"b552e39bb399319c","entry":"numpy_to_pil","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"b552e39bb399319c"}},{"code_sha256_prefix":"7db516620082545a","entry":"get_default_update_params","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"model_utils.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/model_utils.py","link_basis":"first_harvest_node","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":"7db516620082545a"}},{"code_sha256_prefix":"9e127980111732d8","entry":"load_clip","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"9e127980111732d8"}},{"code_sha256_prefix":"5cb0da1c3320f58c","entry":"load_config","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"utils.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/utils.py","link_basis":"first_harvest_node","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":"5cb0da1c3320f58c"}},{"code_sha256_prefix":"c32854253998ea81","entry":"replace_clip_embeddings","repo":"OPPO-Mente-Lab/Subject-Diffusion","repo_kind":"official","path":"replace_clip_embedding.py","file_url":"https://github.com/OPPO-Mente-Lab/Subject-Diffusion/blob/HEAD/replace_clip_embedding.py","link_basis":"first_harvest_node","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":"c32854253998ea81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}