{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QJKDGRY7QLKYXLTKGVKZLG3KL3","short_pith_number":"pith:QJKDGRY7","schema_version":"1.0","canonical_sha256":"825433471f82d58bae6a3555959b6a5ed75232455fd30b1ac478d51aea06b3a7","source":{"kind":"arxiv","id":"2210.11427","version":1},"attestation_state":"computed","paper":{"title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guillaume Couairon, Holger Schwenk, Jakob Verbeek, Matthieu Cord","submitted_at":"2022-10-20T17:16:37Z","abstract_excerpt":"Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned diffusion models for the task of semantic image editing, where the goal is to edit an image based on a text query. Semantic image editing is an extension of image generation, with the additional constraint that the generated image should be as similar as possible to a given input image. Current editing methods based on diffusion models usually require to pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2210.11427","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-20T17:16:37Z","cross_cats_sorted":[],"title_canon_sha256":"1e809cd9e39fd11e1d835a0330edbc99b5177c0b84236785dc962b19bdcb122b","abstract_canon_sha256":"e23201684b7a3047c6597b2aebc0a05c9ca4dce28dbc145d87ef3bb6c7002ef3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:48.124025Z","signature_b64":"TqnDDndTXmStYHF4+YHHsT7L3orlqj1Kc3C5kVMc4X36SfB5qSvwUHWVdrzjpmRVROKqWIYSvvsD6rmWaTTkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"825433471f82d58bae6a3555959b6a5ed75232455fd30b1ac478d51aea06b3a7","last_reissued_at":"2026-07-05T05:08:48.123621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:48.123621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guillaume Couairon, Holger Schwenk, Jakob Verbeek, Matthieu Cord","submitted_at":"2022-10-20T17:16:37Z","abstract_excerpt":"Image generation has recently seen tremendous advances, with diffusion models allowing to synthesize convincing images for a large variety of text prompts. In this article, we propose DiffEdit, a method to take advantage of text-conditioned diffusion models for the task of semantic image editing, where the goal is to edit an image based on a text query. Semantic image editing is an extension of image generation, with the additional constraint that the generated image should be as similar as possible to a given input image. Current editing methods based on diffusion models usually require to pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11427","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.11427/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2210.11427","created_at":"2026-07-05T05:08:48.123677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11427v1","created_at":"2026-07-05T05:08:48.123677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11427","created_at":"2026-07-05T05:08:48.123677+00:00"},{"alias_kind":"pith_short_12","alias_value":"QJKDGRY7QLKY","created_at":"2026-07-05T05:08:48.123677+00:00"},{"alias_kind":"pith_short_16","alias_value":"QJKDGRY7QLKYXLTK","created_at":"2026-07-05T05:08:48.123677+00:00"},{"alias_kind":"pith_short_8","alias_value":"QJKDGRY7","created_at":"2026-07-05T05:08:48.123677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":40,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.17565","citing_title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25578","citing_title":"H-Adapter: Pose-Robust Hairstyle Transfer via Attention-Derived, Source-Aligned Hair Masks","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24441","citing_title":"S1-Omni-Image: A Unified Model for Scientific Image Understanding, Generation, and Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26872","citing_title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18906","citing_title":"BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12263","citing_title":"VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09901","citing_title":"On the Controllability-Fidelity Frontier in Diffusion Editing","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07145","citing_title":"Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07079","citing_title":"AsyncPatch Diffusion: spatially-flexible image generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00522","citing_title":"Restore3D: Breathing Life into Broken Objects with Shape and Texture Restoration","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14948","citing_title":"ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09233","citing_title":"Towards Robust Sequential Decomposition for Complex Image Editing","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29308","citing_title":"MirrorPPR: Exemplar-Based Portrait Photo Retouching","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30003","citing_title":"GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25568","citing_title":"Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26872","citing_title":"SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":253,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00310","citing_title":"Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2412.18158","citing_title":"Semantics Disentanglement and Composition for Universal Image Coding with Efficiently LLM Reasoning and Generative Diffusion","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13109","citing_title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22244","citing_title":"FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23622","citing_title":"DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19865","citing_title":"Landscape-Awareness for Geometric View Diffusion Model","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2506.14399","citing_title":"Factored Classifier-Free Guidance","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3","json":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3.json","graph_json":"https://pith.science/api/pith-number/QJKDGRY7QLKYXLTKGVKZLG3KL3/graph.json","events_json":"https://pith.science/api/pith-number/QJKDGRY7QLKYXLTKGVKZLG3KL3/events.json","paper":"https://pith.science/paper/QJKDGRY7"},"agent_actions":{"view_html":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3","download_json":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3.json","view_paper":"https://pith.science/paper/QJKDGRY7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11427&json=true","fetch_graph":"https://pith.science/api/pith-number/QJKDGRY7QLKYXLTKGVKZLG3KL3/graph.json","fetch_events":"https://pith.science/api/pith-number/QJKDGRY7QLKYXLTKGVKZLG3KL3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3/action/storage_attestation","attest_author":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3/action/author_attestation","sign_citation":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3/action/citation_signature","submit_replication":"https://pith.science/pith/QJKDGRY7QLKYXLTKGVKZLG3KL3/action/replication_record"}},"created_at":"2026-07-05T05:08:48.123677+00:00","updated_at":"2026-07-05T05:08:48.123677+00:00"}