{"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-implicit-assumptions-in-text-to-image","title":"Editing Implicit Assumptions in Text-to-Image Diffusion Models","arxiv_id":"2303.08084","date":"2023-03-14","proceeding":"ICCV 2023 1","authors":["Hadas Orgad","Bahjat Kawar","Yonatan Belinkov"],"abstract":"Text-to-image diffusion models often make implicit assumptions about the world when generating images. While some assumptions are useful (e.g., the sky is blue), they can also be outdated, incorrect, or reflective of social biases present in the training data. Thus, there is a need to control these assumptions without requiring explicit user input or costly re-training. In this work, we aim to edit a given implicit assumption in a pre-trained diffusion model. Our Text-to-Image Model Editing method, TIME for short, receives a pair of inputs: a \"source\" under-specified prompt for which the model makes an implicit assumption (e.g., \"a pack of roses\"), and a \"destination\" prompt that describes the same setting, but with a specified desired attribute (e.g., \"a pack of blue roses\"). TIME then updates the model's cross-attention layers, as these layers assign visual meaning to textual tokens. We edit the projection matrices in these layers such that the source prompt is projected close to the destination prompt. Our method is highly efficient, as it modifies a mere 2.2% of the model's parameters in under one second. To evaluate model editing approaches, we introduce TIMED (TIME Dataset), containing 147 source and destination prompt pairs from various domains. Our experiments (using Stable Diffusion) show that TIME is successful in model editing, generalizes well for related prompts unseen during editing, and imposes minimal effect on unrelated generations.","url_abs":"https://arxiv.org/abs/2303.08084v2","url_pdf":"https://arxiv.org/pdf/2303.08084v2.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-implicit-assumptions-in-text-to-image","repo_url":"https://github.com/bahjat-kawar/time-diffusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"editing-implicit-assumptions-in-text-to-image","repo_url":"https://github.com/technion-cs-nlp/llmsknow","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"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=2303.08084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.08084"}},"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/technion-cs-nlp/llmsknow","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/bahjat-kawar/time-diffusion","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"19c640f553dba8a9","entry":"train_closed_form","repo":"bahjat-kawar/time-diffusion","repo_kind":"official","path":"train_funcs.py","file_url":"https://github.com/bahjat-kawar/time-diffusion/blob/HEAD/train_funcs.py","link_basis":"first_harvest_node","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":"19c640f553dba8a9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}