{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:QXSD4O3556BG5ACPROUGBVJAHP","short_pith_number":"pith:QXSD4O35","schema_version":"1.0","canonical_sha256":"85e43e3b7def826e804f8ba860d5203bd823f792bb467376899c52640f8401d8","source":{"kind":"arxiv","id":"2211.07825","version":1},"attestation_state":"computed","paper":{"title":"Direct Inversion: Optimization-Free Text-Driven Real Image Editing with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adham Elarabawy, Harish Kamath, Samuel Denton","submitted_at":"2022-11-15T01:07:38Z","abstract_excerpt":"With the rise of large, publicly-available text-to-image diffusion models, text-guided real image editing has garnered much research attention recently. Existing methods tend to either rely on some form of per-instance or per-task fine-tuning and optimization, require multiple novel views, or they inherently entangle preservation of real image identity, semantic coherence, and faithfulness to text guidance. In this paper, we propose an optimization-free and zero fine-tuning framework that applies complex and non-rigid edits to a single real image via a text prompt, avoiding all the pitfalls de"},"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":"2211.07825","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-15T01:07:38Z","cross_cats_sorted":[],"title_canon_sha256":"805dd540b205436ef50824f28fc9fc74cfa8bdd2aa217541bf6a328319ce8147","abstract_canon_sha256":"7b7131c3fc0687d61c537f5a37b5e4e669835df26119e5cf629bae45d98ad6b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:16:06.722864Z","signature_b64":"wMoMwrRdwX7IZy3PAlLwCSBhSr6Jt3J7HhNnJriShTLbVjl/8vAbmWWnflacmXavIONlBD5ippZdrt/g6d6YBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85e43e3b7def826e804f8ba860d5203bd823f792bb467376899c52640f8401d8","last_reissued_at":"2026-07-05T05:16:06.722399Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:16:06.722399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct Inversion: Optimization-Free Text-Driven Real Image Editing with Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adham Elarabawy, Harish Kamath, Samuel Denton","submitted_at":"2022-11-15T01:07:38Z","abstract_excerpt":"With the rise of large, publicly-available text-to-image diffusion models, text-guided real image editing has garnered much research attention recently. Existing methods tend to either rely on some form of per-instance or per-task fine-tuning and optimization, require multiple novel views, or they inherently entangle preservation of real image identity, semantic coherence, and faithfulness to text guidance. In this paper, we propose an optimization-free and zero fine-tuning framework that applies complex and non-rigid edits to a single real image via a text prompt, avoiding all the pitfalls de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07825","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/2211.07825/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":"2211.07825","created_at":"2026-07-05T05:16:06.722468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07825v1","created_at":"2026-07-05T05:16:06.722468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07825","created_at":"2026-07-05T05:16:06.722468+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXSD4O3556BG","created_at":"2026-07-05T05:16:06.722468+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXSD4O3556BG5ACP","created_at":"2026-07-05T05:16:06.722468+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXSD4O35","created_at":"2026-07-05T05:16:06.722468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06228","citing_title":"SAM-Flow: Source-Anchored Masked Flow for Training-Free Image Editing","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP","json":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP.json","graph_json":"https://pith.science/api/pith-number/QXSD4O3556BG5ACPROUGBVJAHP/graph.json","events_json":"https://pith.science/api/pith-number/QXSD4O3556BG5ACPROUGBVJAHP/events.json","paper":"https://pith.science/paper/QXSD4O35"},"agent_actions":{"view_html":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP","download_json":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP.json","view_paper":"https://pith.science/paper/QXSD4O35","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07825&json=true","fetch_graph":"https://pith.science/api/pith-number/QXSD4O3556BG5ACPROUGBVJAHP/graph.json","fetch_events":"https://pith.science/api/pith-number/QXSD4O3556BG5ACPROUGBVJAHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP/action/storage_attestation","attest_author":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP/action/author_attestation","sign_citation":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP/action/citation_signature","submit_replication":"https://pith.science/pith/QXSD4O3556BG5ACPROUGBVJAHP/action/replication_record"}},"created_at":"2026-07-05T05:16:06.722468+00:00","updated_at":"2026-07-05T05:16:06.722468+00:00"}