{"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/interpreting-the-weight-space-of-customized","title":"Interpreting the Weight Space of Customized Diffusion Models","arxiv_id":"2406.09413","date":"2024-06-13","proceeding":null,"authors":["Amil Dravid","Yossi Gandelsman","Kuan-Chieh Wang","Rameen Abdal","Gordon Wetzstein","Alexei A. Efros","Kfir Aberman"],"abstract":"We investigate the space of weights spanned by a large collection of customized diffusion models. We populate this space by creating a dataset of over 60,000 models, each of which is a base model fine-tuned to insert a different person's visual identity. We model the underlying manifold of these weights as a subspace, which we term weights2weights. We demonstrate three immediate applications of this space that result in new diffusion models -- sampling, editing, and inversion. First, sampling a set of weights from this space results in a new model encoding a novel identity. Next, we find linear directions in this space corresponding to semantic edits of the identity (e.g., adding a beard), resulting in a new model with the original identity edited. Finally, we show that inverting a single image into this space encodes a realistic identity into a model, even if the input image is out of distribution (e.g., a painting). We further find that these linear properties of the diffusion model weight space extend to other visual concepts. Our results indicate that the weight space of fine-tuned diffusion models can behave as an interpretable meta-latent space producing new models.","url_abs":"https://arxiv.org/abs/2406.09413v3","url_pdf":"https://arxiv.org/pdf/2406.09413v3.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":"interpreting-the-weight-space-of-customized","repo_url":"https://github.com/snap-research/weights2weights","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.09413","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.09413"}},"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/snap-research/weights2weights","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_honours":1,"ran":3,"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":8,"samples":[{"code_sha256_prefix":"32380a050ca033d4","entry":"b2mb","repo":"snap-research/weights2weights","repo_kind":"official","path":"train_dreambooth.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/train_dreambooth.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"32380a050ca033d4"}},{"code_sha256_prefix":"6015ab268a8c8cec","entry":"debias","repo":"snap-research/weights2weights","repo_kind":"official","path":"editing.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/editing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6015ab268a8c8cec"}},{"code_sha256_prefix":"7e175f3d5a77d724","entry":"get_direction","repo":"snap-research/weights2weights","repo_kind":"official","path":"editing.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/editing.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7e175f3d5a77d724"}},{"code_sha256_prefix":"ddb9257aed90e222","entry":"inference","repo":"snap-research/weights2weights","repo_kind":"official","path":"utils.py","file_url":"https://github.com/snap-research/weights2weights/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":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ddb9257aed90e222"}},{"code_sha256_prefix":"1614dd4e41f6caec","entry":"edit_inference","repo":"snap-research/weights2weights","repo_kind":"official","path":"editing.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/editing.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1614dd4e41f6caec"}},{"code_sha256_prefix":"2f00b39db5a81466","entry":"import_model_class_from_model_name_or_path","repo":"snap-research/weights2weights","repo_kind":"official","path":"train_dreambooth.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/train_dreambooth.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f00b39db5a81466"}},{"code_sha256_prefix":"a1b7c201b4b5e735","entry":"invert","repo":"snap-research/weights2weights","repo_kind":"official","path":"inversion.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/inversion.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a1b7c201b4b5e735"}},{"code_sha256_prefix":"f5bc09ecb185eb8d","entry":"parse_args","repo":"snap-research/weights2weights","repo_kind":"official","path":"train_dreambooth.py","file_url":"https://github.com/snap-research/weights2weights/blob/HEAD/train_dreambooth.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"f5bc09ecb185eb8d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}