{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3HF37LZXIZR7MNK74OSIKSHX46","short_pith_number":"pith:3HF37LZX","schema_version":"1.0","canonical_sha256":"d9cbbfaf374663f6355fe3a48548f7e7a0c73a46a576378fa0866aa6fe137c13","source":{"kind":"arxiv","id":"2210.09276","version":3},"attestation_state":"computed","paper":{"title":"Imagic: Text-Based Real Image Editing with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bahjat Kawar, Huiwen Chang, Inbar Mosseri, Michal Irani, Omer Tov, Oran Lang, Shiran Zada, Tali Dekel","submitted_at":"2022-10-17T17:27:32Z","abstract_excerpt":"Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently either limited to specific editing types (e.g., object overlay, style transfer), or apply to synthetically generated images, or require multiple input images of a common object. In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-guided semantic edits to a single real image. For example, we can change the posture and composition of one or multiple objects inside an image, while preserving its original characteristics. Our method"},"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":"2210.09276","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-17T17:27:32Z","cross_cats_sorted":[],"title_canon_sha256":"d748e27441699d59ba0cda21fd0d2dbc929e1d2eb756a035fd7fa94965339107","abstract_canon_sha256":"c24f8daadd9942cbbc87f570de08be89ec4f7297d88e4f920e56a231dc564102"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:46.579373Z","signature_b64":"8ftxfTYYsklu7bSuLhYqHXMhJSUZ9cxt9SLNwBb8iMUEboAPvNTVgW8ZbTiZBq8WqvW4AyZfftGEhCH4hg6dAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9cbbfaf374663f6355fe3a48548f7e7a0c73a46a576378fa0866aa6fe137c13","last_reissued_at":"2026-07-05T05:52:46.578934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:46.578934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imagic: Text-Based Real Image Editing with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bahjat Kawar, Huiwen Chang, Inbar Mosseri, Michal Irani, Omer Tov, Oran Lang, Shiran Zada, Tali Dekel","submitted_at":"2022-10-17T17:27:32Z","abstract_excerpt":"Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently either limited to specific editing types (e.g., object overlay, style transfer), or apply to synthetically generated images, or require multiple input images of a common object. In this paper we demonstrate, for the very first time, the ability to apply complex (e.g., non-rigid) text-guided semantic edits to a single real image. For example, we can change the posture and composition of one or multiple objects inside an image, while preserving its original characteristics. Our method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.09276","kind":"arxiv","version":3},"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/2210.09276/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":"2210.09276","created_at":"2026-07-05T05:52:46.578991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.09276v3","created_at":"2026-07-05T05:52:46.578991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.09276","created_at":"2026-07-05T05:52:46.578991+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HF37LZXIZR7","created_at":"2026-07-05T05:52:46.578991+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HF37LZXIZR7MNK7","created_at":"2026-07-05T05:52:46.578991+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HF37LZX","created_at":"2026-07-05T05:52:46.578991+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04306","citing_title":"Organizational Control Layer: Governance Infrastructure at the Execution Boundary of LLM Agent Systems","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01825","citing_title":"ROGLE: Robust Global-Local Alignment with Automated Region Supervision for Text-Based Person Search","ref_index":138,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07568","citing_title":"A Systematic Study of Behavioral Cloning for Scientific Data Annotation","ref_index":284,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18010","citing_title":"Functionalization via Structure Completion and Motion Rectification","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.05342","citing_title":"Delta Rectified Flow Sampling for Text-to-Image Editing","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2311.04145","citing_title":"I2VGen-XL: High-Quality Image-to-Video Synthesis via Cascaded Diffusion Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2302.05543","citing_title":"Adding Conditional Control to Text-to-Image Diffusion Models","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2211.11018","citing_title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2211.01324","citing_title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06571","citing_title":"ModelScope Text-to-Video Technical Report","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04887","citing_title":"HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15742","citing_title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02583","citing_title":"Stylistic Attribute Control in Latent Diffusion Models","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46","json":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46.json","graph_json":"https://pith.science/api/pith-number/3HF37LZXIZR7MNK74OSIKSHX46/graph.json","events_json":"https://pith.science/api/pith-number/3HF37LZXIZR7MNK74OSIKSHX46/events.json","paper":"https://pith.science/paper/3HF37LZX"},"agent_actions":{"view_html":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46","download_json":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46.json","view_paper":"https://pith.science/paper/3HF37LZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.09276&json=true","fetch_graph":"https://pith.science/api/pith-number/3HF37LZXIZR7MNK74OSIKSHX46/graph.json","fetch_events":"https://pith.science/api/pith-number/3HF37LZXIZR7MNK74OSIKSHX46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46/action/storage_attestation","attest_author":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46/action/author_attestation","sign_citation":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46/action/citation_signature","submit_replication":"https://pith.science/pith/3HF37LZXIZR7MNK74OSIKSHX46/action/replication_record"}},"created_at":"2026-07-05T05:52:46.578991+00:00","updated_at":"2026-07-05T05:52:46.578991+00:00"}