{"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/towards-efficient-diffusion-based-image","title":"Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks","arxiv_id":"2401.07709","date":"2024-01-15","proceeding":null,"authors":["Siyu Zou","Jiji Tang","Yiyi Zhou","Jing He","Chaoyi Zhao","Rongsheng Zhang","Zhipeng Hu","Xiaoshuai Sun"],"abstract":"Diffusion-based Image Editing (DIE) is an emerging research hot-spot, which often applies a semantic mask to control the target area for diffusion-based editing. However, most existing solutions obtain these masks via manual operations or off-line processing, greatly reducing their efficiency. In this paper, we propose a novel and efficient image editing method for Text-to-Image (T2I) diffusion models, termed Instant Diffusion Editing(InstDiffEdit). In particular, InstDiffEdit aims to employ the cross-modal attention ability of existing diffusion models to achieve instant mask guidance during the diffusion steps. To reduce the noise of attention maps and realize the full automatics, we equip InstDiffEdit with a training-free refinement scheme to adaptively aggregate the attention distributions for the automatic yet accurate mask generation. Meanwhile, to supplement the existing evaluations of DIE, we propose a new benchmark called Editing-Mask to examine the mask accuracy and local editing ability of existing methods. To validate InstDiffEdit, we also conduct extensive experiments on ImageNet and Imagen, and compare it with a bunch of the SOTA methods. The experimental results show that InstDiffEdit not only outperforms the SOTA methods in both image quality and editing results, but also has a much faster inference speed, i.e., +5 to +6 times.","url_abs":"https://arxiv.org/abs/2401.07709v2","url_pdf":"https://arxiv.org/pdf/2401.07709v2.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":"towards-efficient-diffusion-based-image","repo_url":"https://github.com/xiaotianqing/instdiffedit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2401.07709","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.07709"}},"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/xiaotianqing/instdiffedit","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/xiaotianqing/InstDiffEdit","reach":{"status":"ok"}}],"summary":{"ran":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":6,"samples":[{"code_sha256_prefix":"44d6e9270531af10","entry":"aggregate_attention","repo":"xiaotianqing/InstDiffEdit","repo_kind":"official","path":"model/attention_store.py","file_url":"https://github.com/xiaotianqing/InstDiffEdit/blob/HEAD/model/attention_store.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44d6e9270531af10"}},{"code_sha256_prefix":"59f049f2eeb458df","entry":"get_data","repo":"xiaotianqing/InstDiffEdit","repo_kind":"official","path":"model/InstDiffEdit.py","file_url":"https://github.com/xiaotianqing/InstDiffEdit/blob/HEAD/model/InstDiffEdit.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"59f049f2eeb458df"}},{"code_sha256_prefix":"025ed00fbfda521d","entry":"get_or_latent","repo":"xiaotianqing/InstDiffEdit","repo_kind":"official","path":"model/util.py","file_url":"https://github.com/xiaotianqing/InstDiffEdit/blob/HEAD/model/util.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"025ed00fbfda521d"}},{"code_sha256_prefix":"a9a35b370a54f02b","entry":"init_latent","repo":"xiaotianqing/InstDiffEdit","repo_kind":"official","path":"model/util.py","file_url":"https://github.com/xiaotianqing/InstDiffEdit/blob/HEAD/model/util.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":"a9a35b370a54f02b"}},{"code_sha256_prefix":"64d70aad002bc229","entry":"register_attention_control","repo":"xiaotianqing/InstDiffEdit","repo_kind":"official","path":"model/attention_store.py","file_url":"https://github.com/xiaotianqing/InstDiffEdit/blob/HEAD/model/attention_store.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":"64d70aad002bc229"}},{"code_sha256_prefix":"695e430f399835f8","entry":"use_mask","repo":"xiaotianqing/InstDiffEdit","repo_kind":"official","path":"model/sample_use.py","file_url":"https://github.com/xiaotianqing/InstDiffEdit/blob/HEAD/model/sample_use.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":"695e430f399835f8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}