{"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/a-closer-look-at-parameter-efficient-tuning","title":"A Closer Look at Parameter-Efficient Tuning in Diffusion Models","arxiv_id":"2303.18181","date":"2023-03-31","proceeding":null,"authors":["Chendong Xiang","Fan Bao","Chongxuan Li","Hang Su","Jun Zhu"],"abstract":"Large-scale diffusion models like Stable Diffusion are powerful and find various real-world applications while customizing such models by fine-tuning is both memory and time inefficient. Motivated by the recent progress in natural language processing, we investigate parameter-efficient tuning in large diffusion models by inserting small learnable modules (termed adapters). In particular, we decompose the design space of adapters into orthogonal factors -- the input position, the output position as well as the function form, and perform Analysis of Variance (ANOVA), a classical statistical approach for analyzing the correlation between discrete (design options) and continuous variables (evaluation metrics). Our analysis suggests that the input position of adapters is the critical factor influencing the performance of downstream tasks. Then, we carefully study the choice of the input position, and we find that putting the input position after the cross-attention block can lead to the best performance, validated by additional visualization analyses. Finally, we provide a recipe for parameter-efficient tuning in diffusion models, which is comparable if not superior to the fully fine-tuned baseline (e.g., DreamBooth) with only 0.75 \\% extra parameters, across various customized tasks.","url_abs":"https://arxiv.org/abs/2303.18181v2","url_pdf":"https://arxiv.org/pdf/2303.18181v2.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":"a-closer-look-at-parameter-efficient-tuning","repo_url":"https://github.com/Xiang-cd/unet-finetune","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"efficient-diffusion-personalization","task_name":"Efficient Diffusion Personalization"},{"task_slug":null,"task_name":"Position"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.18181","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.18181"}},"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/Xiang-cd/unet-finetune","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_violates":3,"ran_honours":1,"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":14,"ran":13,"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":"fe5dd5258046898c","entry":"always","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/x_transformer.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/x_transformer.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":"fe5dd5258046898c"}},{"code_sha256_prefix":"8241c0562bc710fd","entry":"chunk","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"sample.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/sample.py","link_basis":"plan_row","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":"8241c0562bc710fd"}},{"code_sha256_prefix":"424012cb37b31172","entry":"default","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"424012cb37b31172"}},{"code_sha256_prefix":"4cb732f513d69dfd","entry":"disabled_train","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/models/diffusion/classifier.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/models/diffusion/classifier.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4cb732f513d69dfd"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"d5726f9e3a5684c3","entry":"get_bert_token_for_string","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/embedding_manager.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/embedding_manager.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d5726f9e3a5684c3"}},{"code_sha256_prefix":"7e334d1575bdaede","entry":"get_clip_token_for_string","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/embedding_manager.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/embedding_manager.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":"7e334d1575bdaede"}},{"code_sha256_prefix":"71c2df28a1008d03","entry":"get_embedding_for_clip_token","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/embedding_manager.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/embedding_manager.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"71c2df28a1008d03"}},{"code_sha256_prefix":"b1368330cf0f5642","entry":"isimage","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/util.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":"b1368330cf0f5642"}},{"code_sha256_prefix":"d72762b700feee6f","entry":"ismap","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/util.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":"d72762b700feee6f"}},{"code_sha256_prefix":"f41710299c49d36d","entry":"log_txt_as_img","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/util.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/util.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":"f41710299c49d36d"}},{"code_sha256_prefix":"d48d8354986e3b0e","entry":"uniform_on_device","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/models/diffusion/ddpm.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/models/diffusion/ddpm.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d48d8354986e3b0e"}},{"code_sha256_prefix":"9a299fe5ae09e407","entry":"uniq","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"ldm/modules/attention.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/ldm/modules/attention.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9a299fe5ae09e407"}},{"code_sha256_prefix":"87fbedd0c27cf378","entry":"nondefault_trainer_args","repo":"Xiang-cd/unet-finetune","repo_kind":"official","path":"main_dream_booth.py","file_url":"https://github.com/Xiang-cd/unet-finetune/blob/HEAD/main_dream_booth.py","link_basis":"harvester_set","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":"87fbedd0c27cf378"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}