{"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/editing-massive-concepts-in-text-to-image","title":"Editing Massive Concepts in Text-to-Image Diffusion Models","arxiv_id":"2403.13807","date":"2024-03-20","proceeding":null,"authors":["Tianwei Xiong","Enze Xie","Yue Wu","Zhenguo Li","Xihui Liu"],"abstract":"Text-to-image diffusion models suffer from the risk of generating outdated, copyrighted, incorrect, and biased content. While previous methods have mitigated the issues on a small scale, it is essential to handle them simultaneously in larger-scale real-world scenarios. We propose a two-stage method, Editing Massive Concepts In Diffusion Models (EMCID). The first stage performs memory optimization for each individual concept with dual self-distillation from text alignment loss and diffusion noise prediction loss. The second stage conducts massive concept editing with multi-layer, closed form model editing. We further propose a comprehensive benchmark, named ImageNet Concept Editing Benchmark (ICEB), for evaluating massive concept editing for T2I models with two subtasks, free-form prompts, massive concept categories, and extensive evaluation metrics. Extensive experiments conducted on our proposed benchmark and previous benchmarks demonstrate the superior scalability of EMCID for editing up to 1,000 concepts, providing a practical approach for fast adjustment and re-deployment of T2I diffusion models in real-world applications.","url_abs":"https://arxiv.org/abs/2403.13807v1","url_pdf":"https://arxiv.org/pdf/2403.13807v1.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":"editing-massive-concepts-in-text-to-image","repo_url":"https://github.com/silentview/emcid","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"model-editing","task_name":"Model Editing"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.13807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.13807"}},"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/silentview/emcid","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"ran":5,"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":"d6d94bce4a83bfa2","entry":"dilate","repo":"silentview/emcid","repo_kind":"official","path":"emcid/compute_ks.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/emcid/compute_ks.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":"d6d94bce4a83bfa2"}},{"code_sha256_prefix":"ff33c03524dcaefd","entry":"get_accum_time_blocks","repo":"silentview/emcid","repo_kind":"official","path":"emcid/emcid_hparams.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/emcid/emcid_hparams.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":"ff33c03524dcaefd"}},{"code_sha256_prefix":"920b394e7ad80c53","entry":"hierarchical_subsequence","repo":"silentview/emcid","repo_kind":"official","path":"util/nethook.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/util/nethook.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":"920b394e7ad80c53"}},{"code_sha256_prefix":"70f6ab8bde55420e","entry":"recursive_copy","repo":"silentview/emcid","repo_kind":"official","path":"util/nethook.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/util/nethook.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"70f6ab8bde55420e"}},{"code_sha256_prefix":"440ff98c2b1ae1aa","entry":"subsequence","repo":"silentview/emcid","repo_kind":"official","path":"util/nethook.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/util/nethook.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":"440ff98c2b1ae1aa"}},{"code_sha256_prefix":"47f2399903cc9e85","entry":"get_i2p_editing_requests","repo":"silentview/emcid","repo_kind":"official","path":"dsets/global_concepts.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/dsets/global_concepts.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":"47f2399903cc9e85"}},{"code_sha256_prefix":"08f8b9cb2e59954d","entry":"preprocess_img","repo":"silentview/emcid","repo_kind":"official","path":"emcid/compute_z.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/emcid/compute_z.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":"08f8b9cb2e59954d"}},{"code_sha256_prefix":"77fce57b16a1e579","entry":"tokenize_prompts","repo":"silentview/emcid","repo_kind":"official","path":"emcid/compute_z.py","file_url":"https://github.com/silentview/emcid/blob/HEAD/emcid/compute_z.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":"77fce57b16a1e579"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}