{"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/low-rank-continual-personalization-of","title":"Low-Rank Continual Personalization of Diffusion Models","arxiv_id":"2410.04891","date":"2024-10-07","proceeding":null,"authors":["Łukasz Staniszewski","Katarzyna Zaleska","Kamil Deja"],"abstract":"Recent personalization methods for diffusion models, such as Dreambooth, allow fine-tuning pre-trained models to generate new concepts. However, applying these techniques across multiple tasks in order to include, e.g., several new objects or styles, leads to mutual interference between their adapters. While recent studies attempt to mitigate this issue by combining trained adapters across tasks after fine-tuning, we adopt a more rigorous regime and investigate the personalization of large diffusion models under a continual learning scenario, where such interference leads to catastrophic forgetting of previous knowledge. To that end, we evaluate the na\\\"ive continual fine-tuning of customized models and compare this approach with three methods for consecutive adapters' training: sequentially merging new adapters, merging orthogonally initialized adapters, and updating only relevant parameters according to the task. In our experiments, we show that the proposed approaches mitigate forgetting when compared to the na\\\"ive approach.","url_abs":"https://arxiv.org/abs/2410.04891v1","url_pdf":"https://arxiv.org/pdf/2410.04891v1.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":"low-rank-continual-personalization-of","repo_url":"https://github.com/luk-st/continual-lora","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.04891","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.04891"}},"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":"deterministic:regex_extraction","url":"https://github.com/luk-st/continual-lora","reach":null}],"summary":{"ran_draft_wrong":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":"7f50eff9d670c3d5","entry":"convert_metrics_to_arrays","repo":"luk-st/continual-lora","repo_kind":"official","path":"eval/eval_method.py","file_url":"https://github.com/luk-st/continual-lora/blob/HEAD/eval/eval_method.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7f50eff9d670c3d5"}},{"code_sha256_prefix":"96cf1359205573f6","entry":"get_order_seed_tasks","repo":"luk-st/continual-lora","repo_kind":"official","path":"eval/eval_method.py","file_url":"https://github.com/luk-st/continual-lora/blob/HEAD/eval/eval_method.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"96cf1359205573f6"}},{"code_sha256_prefix":"24ddb3e28337a406","entry":"merge_loras","repo":"luk-st/continual-lora","repo_kind":"official","path":"lora/train_dreambooth_lora_sdxl.py","file_url":"https://github.com/luk-st/continual-lora/blob/HEAD/lora/train_dreambooth_lora_sdxl.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"24ddb3e28337a406"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}