{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HEY7POI2AJW33ZATGQMCRAACAW","short_pith_number":"pith:HEY7POI2","schema_version":"1.0","canonical_sha256":"3931f7b91a026dbde413341828800205a49990e9df6511f9a60e49fb4a6b824c","source":{"kind":"arxiv","id":"2411.15466","version":2},"attestation_state":"computed","paper":{"title":"Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaehun Shin, Heeseung Kim, Jooyoung Choi, Sungroh Yoon","submitted_at":"2024-11-23T06:17:43Z","abstract_excerpt":"Subject-driven text-to-image generation aims to produce images of a new subject within a desired context by accurately capturing both the visual characteristics of the subject and the semantic content of a text prompt. Traditional methods rely on time- and resource-intensive fine-tuning for subject alignment, while recent zero-shot approaches leverage on-the-fly image prompting, often sacrificing subject alignment. In this paper, we introduce Diptych Prompting, a novel zero-shot approach that reinterprets as an inpainting task with precise subject alignment by leveraging the emergent property "},"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":"2411.15466","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T06:17:43Z","cross_cats_sorted":[],"title_canon_sha256":"fd9a318956e40cf94ba680b52d90abce3bfb453ee8faca56221dc18c7f0ae52b","abstract_canon_sha256":"9e80f82e30d4ba749e97f7f45eaffed8571342f13e82f0c2601bed8a4b952d78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:18.456632Z","signature_b64":"m8foWWwvzwigLYaqoyDnhbeisl3pn53tcsMbLwsDtHjx1dSC+5BVR45ahFustDMskDHAk7SLvBhIrhFY8iKVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3931f7b91a026dbde413341828800205a49990e9df6511f9a60e49fb4a6b824c","last_reissued_at":"2026-07-05T11:15:18.456211Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:18.456211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaehun Shin, Heeseung Kim, Jooyoung Choi, Sungroh Yoon","submitted_at":"2024-11-23T06:17:43Z","abstract_excerpt":"Subject-driven text-to-image generation aims to produce images of a new subject within a desired context by accurately capturing both the visual characteristics of the subject and the semantic content of a text prompt. Traditional methods rely on time- and resource-intensive fine-tuning for subject alignment, while recent zero-shot approaches leverage on-the-fly image prompting, often sacrificing subject alignment. In this paper, we introduce Diptych Prompting, a novel zero-shot approach that reinterprets as an inpainting task with precise subject alignment by leveraging the emergent property "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15466","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/2411.15466/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":"2411.15466","created_at":"2026-07-05T11:15:18.456266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15466v2","created_at":"2026-07-05T11:15:18.456266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15466","created_at":"2026-07-05T11:15:18.456266+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEY7POI2AJW3","created_at":"2026-07-05T11:15:18.456266+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEY7POI2AJW33ZAT","created_at":"2026-07-05T11:15:18.456266+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEY7POI2","created_at":"2026-07-05T11:15:18.456266+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.15958","citing_title":"FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18361","citing_title":"COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2504.20690","citing_title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW","json":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW.json","graph_json":"https://pith.science/api/pith-number/HEY7POI2AJW33ZATGQMCRAACAW/graph.json","events_json":"https://pith.science/api/pith-number/HEY7POI2AJW33ZATGQMCRAACAW/events.json","paper":"https://pith.science/paper/HEY7POI2"},"agent_actions":{"view_html":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW","download_json":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW.json","view_paper":"https://pith.science/paper/HEY7POI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15466&json=true","fetch_graph":"https://pith.science/api/pith-number/HEY7POI2AJW33ZATGQMCRAACAW/graph.json","fetch_events":"https://pith.science/api/pith-number/HEY7POI2AJW33ZATGQMCRAACAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW/action/storage_attestation","attest_author":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW/action/author_attestation","sign_citation":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW/action/citation_signature","submit_replication":"https://pith.science/pith/HEY7POI2AJW33ZATGQMCRAACAW/action/replication_record"}},"created_at":"2026-07-05T11:15:18.456266+00:00","updated_at":"2026-07-05T11:15:18.456266+00:00"}