{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VJCADLX4LNCZCJU3L2PDTCFUUY","short_pith_number":"pith:VJCADLX4","schema_version":"1.0","canonical_sha256":"aa4401aefc5b4591269b5e9e3988b4a614e9ac204bd92d77406cffeeeb6bc18c","source":{"kind":"arxiv","id":"2111.14818","version":2},"attestation_state":"computed","paper":{"title":"Blended Diffusion for Text-driven Editing of Natural Images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dani Lischinski, Ohad Fried, Omri Avrahami","submitted_at":"2021-11-29T18:58:49Z","abstract_excerpt":"Natural language offers a highly intuitive interface for image editing. In this paper, we introduce the first solution for performing local (region-based) edits in generic natural images, based on a natural language description along with an ROI mask. We achieve our goal by leveraging and combining a pretrained language-image model (CLIP), to steer the edit towards a user-provided text prompt, with a denoising diffusion probabilistic model (DDPM) to generate natural-looking results. To seamlessly fuse the edited region with the unchanged parts of the image, we spatially blend noised versions o"},"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":"2111.14818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-29T18:58:49Z","cross_cats_sorted":["cs.GR","cs.LG"],"title_canon_sha256":"555328de6d1bd127a8cec4b962366f32aea6e64e9a1bd01ed038a8a9c09b944d","abstract_canon_sha256":"941fa8fd52ec9dc1ddcd7a584e0c98bc736a351a3c6c9583aa5ca2caf7491be8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:51.026046Z","signature_b64":"KDTzuORXrugT7pLTfY+egFBg3pLBYjdxUQ7P3LXx1AjjTw+cIxWCofX46y/AihTTD+cFlgeezAdQQv8yTi8xCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa4401aefc5b4591269b5e9e3988b4a614e9ac204bd92d77406cffeeeb6bc18c","last_reissued_at":"2026-07-05T05:52:51.025540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:51.025540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blended Diffusion for Text-driven Editing of Natural Images","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.GR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dani Lischinski, Ohad Fried, Omri Avrahami","submitted_at":"2021-11-29T18:58:49Z","abstract_excerpt":"Natural language offers a highly intuitive interface for image editing. In this paper, we introduce the first solution for performing local (region-based) edits in generic natural images, based on a natural language description along with an ROI mask. We achieve our goal by leveraging and combining a pretrained language-image model (CLIP), to steer the edit towards a user-provided text prompt, with a denoising diffusion probabilistic model (DDPM) to generate natural-looking results. To seamlessly fuse the edited region with the unchanged parts of the image, we spatially blend noised versions o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14818","kind":"arxiv","version":2},"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/2111.14818/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":"2111.14818","created_at":"2026-07-05T05:52:51.025606+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.14818v2","created_at":"2026-07-05T05:52:51.025606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14818","created_at":"2026-07-05T05:52:51.025606+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJCADLX4LNCZ","created_at":"2026-07-05T05:52:51.025606+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJCADLX4LNCZCJU3","created_at":"2026-07-05T05:52:51.025606+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJCADLX4","created_at":"2026-07-05T05:52:51.025606+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25568","citing_title":"Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2308.08089","citing_title":"DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00707","citing_title":"PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09715","citing_title":"MuPPet: Multi-person 2D-to-3D Pose Lifting","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY","json":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY.json","graph_json":"https://pith.science/api/pith-number/VJCADLX4LNCZCJU3L2PDTCFUUY/graph.json","events_json":"https://pith.science/api/pith-number/VJCADLX4LNCZCJU3L2PDTCFUUY/events.json","paper":"https://pith.science/paper/VJCADLX4"},"agent_actions":{"view_html":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY","download_json":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY.json","view_paper":"https://pith.science/paper/VJCADLX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.14818&json=true","fetch_graph":"https://pith.science/api/pith-number/VJCADLX4LNCZCJU3L2PDTCFUUY/graph.json","fetch_events":"https://pith.science/api/pith-number/VJCADLX4LNCZCJU3L2PDTCFUUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY/action/storage_attestation","attest_author":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY/action/author_attestation","sign_citation":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY/action/citation_signature","submit_replication":"https://pith.science/pith/VJCADLX4LNCZCJU3L2PDTCFUUY/action/replication_record"}},"created_at":"2026-07-05T05:52:51.025606+00:00","updated_at":"2026-07-05T05:52:51.025606+00:00"}