{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ADKCKNP7BHRS7TKELEPLQNBW5W","short_pith_number":"pith:ADKCKNP7","schema_version":"1.0","canonical_sha256":"00d42535ff09e32fcd44591eb83436ed9d778c36e1acf74851bc06fd326b463f","source":{"kind":"arxiv","id":"2303.13495","version":2},"attestation_state":"computed","paper":{"title":"ReVersion: Diffusion-Based Relation Inversion from Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kelvin C.K. Chan, Tianxing Wu, Yuming Jiang, Ziqi Huang, Ziwei Liu","submitted_at":"2023-03-23T17:56:10Z","abstract_excerpt":"Diffusion models gain increasing popularity for their generative capabilities. Recently, there have been surging needs to generate customized images by inverting diffusion models from exemplar images, and existing inversion methods mainly focus on capturing object appearances (i.e., the \"look\"). However, how to invert object relations, another important pillar in the visual world, remains unexplored. In this work, we propose the Relation Inversion task, which aims to learn a specific relation (represented as \"relation prompt\") from exemplar images. Specifically, we learn a relation prompt with"},"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":"2303.13495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-23T17:56:10Z","cross_cats_sorted":[],"title_canon_sha256":"684598a71f0d7a07cf8bd603f87b779cdc87aa37377336c94562b52caaa29946","abstract_canon_sha256":"afe72bbf142194409b33d5d444a0e610dc49e81c4caea8df0274f428ef0e21e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:18.660119Z","signature_b64":"BLXcz4NXtg6LRsGg4tZbv9xJRdEsJu4KYuF/gYO8kufA/7ws33amcqFwbHwigpl+gwimtd8sugFaUK4CQi+cDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00d42535ff09e32fcd44591eb83436ed9d778c36e1acf74851bc06fd326b463f","last_reissued_at":"2026-07-05T09:42:18.659587Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:18.659587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReVersion: Diffusion-Based Relation Inversion from Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kelvin C.K. Chan, Tianxing Wu, Yuming Jiang, Ziqi Huang, Ziwei Liu","submitted_at":"2023-03-23T17:56:10Z","abstract_excerpt":"Diffusion models gain increasing popularity for their generative capabilities. Recently, there have been surging needs to generate customized images by inverting diffusion models from exemplar images, and existing inversion methods mainly focus on capturing object appearances (i.e., the \"look\"). However, how to invert object relations, another important pillar in the visual world, remains unexplored. In this work, we propose the Relation Inversion task, which aims to learn a specific relation (represented as \"relation prompt\") from exemplar images. Specifically, we learn a relation prompt with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13495","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/2303.13495/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":"2303.13495","created_at":"2026-07-05T09:42:18.659644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.13495v2","created_at":"2026-07-05T09:42:18.659644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13495","created_at":"2026-07-05T09:42:18.659644+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADKCKNP7BHRS","created_at":"2026-07-05T09:42:18.659644+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADKCKNP7BHRS7TKE","created_at":"2026-07-05T09:42:18.659644+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADKCKNP7","created_at":"2026-07-05T09:42:18.659644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.12242","citing_title":"OmniPrism: Learning Disentangled Visual Concept for Image Generation","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W","json":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W.json","graph_json":"https://pith.science/api/pith-number/ADKCKNP7BHRS7TKELEPLQNBW5W/graph.json","events_json":"https://pith.science/api/pith-number/ADKCKNP7BHRS7TKELEPLQNBW5W/events.json","paper":"https://pith.science/paper/ADKCKNP7"},"agent_actions":{"view_html":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W","download_json":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W.json","view_paper":"https://pith.science/paper/ADKCKNP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.13495&json=true","fetch_graph":"https://pith.science/api/pith-number/ADKCKNP7BHRS7TKELEPLQNBW5W/graph.json","fetch_events":"https://pith.science/api/pith-number/ADKCKNP7BHRS7TKELEPLQNBW5W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W/action/storage_attestation","attest_author":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W/action/author_attestation","sign_citation":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W/action/citation_signature","submit_replication":"https://pith.science/pith/ADKCKNP7BHRS7TKELEPLQNBW5W/action/replication_record"}},"created_at":"2026-07-05T09:42:18.659644+00:00","updated_at":"2026-07-05T09:42:18.659644+00:00"}