{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:6DKRFHICFFMRVLK5XUTVX7ZLYT","short_pith_number":"pith:6DKRFHIC","schema_version":"1.0","canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","source":{"kind":"arxiv","id":"2303.01000","version":1},"attestation_state":"computed","paper":{"title":"X&Fuse: Fusing Visual Information in Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Omer Levy, Yuval Kirstain","submitted_at":"2023-03-02T06:33:33Z","abstract_excerpt":"We introduce X&Fuse, a general approach for conditioning on visual information when generating images from text. We demonstrate the potential of X&Fuse in three different text-to-image generation scenarios. (i) When a bank of images is available, we retrieve and condition on a related image (Retrieve&Fuse), resulting in significant improvements on the MS-COCO benchmark, gaining a state-of-the-art FID score of 6.65 in zero-shot settings. (ii) When cropped-object images are at hand, we utilize them and perform subject-driven generation (Crop&Fuse), outperforming the textual inversion method whil"},"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":"2303.01000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-02T06:33:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"db4dfebc47ec245495ada7cf8afd07516a66899f7167ebd8c3c71aa767f36108","abstract_canon_sha256":"ffbcc4365dde7ca7826ed37de283e70aeb367a6fae4c862de381a5026eb61835"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:25.543966Z","signature_b64":"GuRyZQPdJySFI6Ys6KX1AlO15pbAqmiXSHIQhaO5XZZSE0B74NVUojNCkCT0kOUW8N61klRwOjlLeQ6cCy/4DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d5129d0229591aad5dbd275bff2bc4db46c2d9b5979523db82dd4928772f84","last_reissued_at":"2026-07-05T05:47:25.543524Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:25.543524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X&Fuse: Fusing Visual Information in Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Adam Polyak, Omer Levy, Yuval Kirstain","submitted_at":"2023-03-02T06:33:33Z","abstract_excerpt":"We introduce X&Fuse, a general approach for conditioning on visual information when generating images from text. We demonstrate the potential of X&Fuse in three different text-to-image generation scenarios. (i) When a bank of images is available, we retrieve and condition on a related image (Retrieve&Fuse), resulting in significant improvements on the MS-COCO benchmark, gaining a state-of-the-art FID score of 6.65 in zero-shot settings. (ii) When cropped-object images are at hand, we utilize them and perform subject-driven generation (Crop&Fuse), outperforming the textual inversion method whil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.01000","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/2303.01000/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":"2303.01000","created_at":"2026-07-05T05:47:25.543579+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.01000v1","created_at":"2026-07-05T05:47:25.543579+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.01000","created_at":"2026-07-05T05:47:25.543579+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DKRFHICFFMR","created_at":"2026-07-05T05:47:25.543579+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DKRFHICFFMRVLK5","created_at":"2026-07-05T05:47:25.543579+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DKRFHIC","created_at":"2026-07-05T05:47:25.543579+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.01104","citing_title":"VSC: Visual Search Compositional Text-to-Image Diffusion Model","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT","json":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT.json","graph_json":"https://pith.science/api/pith-number/6DKRFHICFFMRVLK5XUTVX7ZLYT/graph.json","events_json":"https://pith.science/api/pith-number/6DKRFHICFFMRVLK5XUTVX7ZLYT/events.json","paper":"https://pith.science/paper/6DKRFHIC"},"agent_actions":{"view_html":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT","download_json":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT.json","view_paper":"https://pith.science/paper/6DKRFHIC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.01000&json=true","fetch_graph":"https://pith.science/api/pith-number/6DKRFHICFFMRVLK5XUTVX7ZLYT/graph.json","fetch_events":"https://pith.science/api/pith-number/6DKRFHICFFMRVLK5XUTVX7ZLYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/action/storage_attestation","attest_author":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/action/author_attestation","sign_citation":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/action/citation_signature","submit_replication":"https://pith.science/pith/6DKRFHICFFMRVLK5XUTVX7ZLYT/action/replication_record"}},"created_at":"2026-07-05T05:47:25.543579+00:00","updated_at":"2026-07-05T05:47:25.543579+00:00"}