{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JAE2N33YWOTQISAETEHG4SDAOB","short_pith_number":"pith:JAE2N33Y","schema_version":"1.0","canonical_sha256":"4809a6ef78b3a7044804990e6e4860704cd42be8edebe87f94aa644dfd6031ed","source":{"kind":"arxiv","id":"2503.15283","version":2},"attestation_state":"computed","paper":{"title":"TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo-Kai Ruan, Hong-Han Shuai, Teng-Fang Hsiao, Tzu-Ling Lin, Yi-Lun Wu","submitted_at":"2025-03-19T15:03:19Z","abstract_excerpt":"Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point "},"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":"2503.15283","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-19T15:03:19Z","cross_cats_sorted":[],"title_canon_sha256":"3626e67b92ce88ab257ce01955e4adb6d34f5b6bf22b96f459dd8f574320c718","abstract_canon_sha256":"006d12dc685a4e6e3f6b0b6011774a6e6f5fb6ad228f897834df6beda55161d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:15:43.724204Z","signature_b64":"owJV984A1W11pvJcyumebtXRIc4xb7v4eDukveHk57j/83qbJjHs2fh8utH3tIMn9D5IvvGtOiVakVoPKyNTCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4809a6ef78b3a7044804990e6e4860704cd42be8edebe87f94aa644dfd6031ed","last_reissued_at":"2026-06-26T01:15:43.723707Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:15:43.723707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo-Kai Ruan, Hong-Han Shuai, Teng-Fang Hsiao, Tzu-Ling Lin, Yi-Lun Wu","submitted_at":"2025-03-19T15:03:19Z","abstract_excerpt":"Text-and-Image-To-Image (TI2I), an extension of Text-To-Image (T2I), integrates image inputs with textual instructions to enhance image generation. Existing methods often partially utilize image inputs, focusing on specific elements like objects or styles, or they experience a decline in generation quality with complex, multi-image instructions. To overcome these challenges, we introduce Training-Free Text-and-Image-to-Image (TF-TI2I), which adapts cutting-edge T2I models such as SD3 without the need for additional training. Our method capitalizes on the MM-DiT architecture, in which we point "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.15283","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/2503.15283/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":"2503.15283","created_at":"2026-06-26T01:15:43.723762+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.15283v2","created_at":"2026-06-26T01:15:43.723762+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.15283","created_at":"2026-06-26T01:15:43.723762+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAE2N33YWOTQ","created_at":"2026-06-26T01:15:43.723762+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAE2N33YWOTQISAE","created_at":"2026-06-26T01:15:43.723762+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAE2N33Y","created_at":"2026-06-26T01:15:43.723762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.04349","citing_title":"VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB","json":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB.json","graph_json":"https://pith.science/api/pith-number/JAE2N33YWOTQISAETEHG4SDAOB/graph.json","events_json":"https://pith.science/api/pith-number/JAE2N33YWOTQISAETEHG4SDAOB/events.json","paper":"https://pith.science/paper/JAE2N33Y"},"agent_actions":{"view_html":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB","download_json":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB.json","view_paper":"https://pith.science/paper/JAE2N33Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.15283&json=true","fetch_graph":"https://pith.science/api/pith-number/JAE2N33YWOTQISAETEHG4SDAOB/graph.json","fetch_events":"https://pith.science/api/pith-number/JAE2N33YWOTQISAETEHG4SDAOB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB/action/storage_attestation","attest_author":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB/action/author_attestation","sign_citation":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB/action/citation_signature","submit_replication":"https://pith.science/pith/JAE2N33YWOTQISAETEHG4SDAOB/action/replication_record"}},"created_at":"2026-06-26T01:15:43.723762+00:00","updated_at":"2026-06-26T01:15:43.723762+00:00"}