{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WO3HRNRSV4V6TDNRKJ4STNTZBA","short_pith_number":"pith:WO3HRNRS","schema_version":"1.0","canonical_sha256":"b3b678b632af2be98db1527929b679082b2e77d7005533370808672beab29912","source":{"kind":"arxiv","id":"2210.14124","version":1},"attestation_state":"computed","paper":{"title":"Lafite2: Few-shot Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changyou Chen, Chunyuan Li, Jianfeng Gao, Jinhui Xu, Yufan Zhou","submitted_at":"2022-10-25T16:22:23Z","abstract_excerpt":"Text-to-image generation models have progressed considerably in recent years, which can now generate impressive realistic images from arbitrary text. Most of such models are trained on web-scale image-text paired datasets, which may not be affordable for many researchers. In this paper, we propose a novel method for pre-training text-to-image generation model on image-only datasets. It considers a retrieval-then-optimization procedure to synthesize pseudo text features: for a given image, relevant pseudo text features are first retrieved, then optimized for better alignment. The low requiremen"},"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":"2210.14124","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-10-25T16:22:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"195a9f58edf91107dde334dedde3ae0422f4a148b771be8af4a0c5ae929aca93","abstract_canon_sha256":"688c491aae2630a20c01bb0c29e3af72fda9c06a1d08f0d10965248a37efdae1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:26.373477Z","signature_b64":"dzXHoGbBaKcWQWzYY+ofs1T7uuvEN0yMZdVocaDXY3ricCW70fgjcgx4pjGXD1DNz2yw3wzb+/YOmrti+7U5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3b678b632af2be98db1527929b679082b2e77d7005533370808672beab29912","last_reissued_at":"2026-07-05T05:10:26.373062Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:26.373062Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lafite2: Few-shot Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Changyou Chen, Chunyuan Li, Jianfeng Gao, Jinhui Xu, Yufan Zhou","submitted_at":"2022-10-25T16:22:23Z","abstract_excerpt":"Text-to-image generation models have progressed considerably in recent years, which can now generate impressive realistic images from arbitrary text. Most of such models are trained on web-scale image-text paired datasets, which may not be affordable for many researchers. In this paper, we propose a novel method for pre-training text-to-image generation model on image-only datasets. It considers a retrieval-then-optimization procedure to synthesize pseudo text features: for a given image, relevant pseudo text features are first retrieved, then optimized for better alignment. The low requiremen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.14124","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/2210.14124/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":"2210.14124","created_at":"2026-07-05T05:10:26.373114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.14124v1","created_at":"2026-07-05T05:10:26.373114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.14124","created_at":"2026-07-05T05:10:26.373114+00:00"},{"alias_kind":"pith_short_12","alias_value":"WO3HRNRSV4V6","created_at":"2026-07-05T05:10:26.373114+00:00"},{"alias_kind":"pith_short_16","alias_value":"WO3HRNRSV4V6TDNR","created_at":"2026-07-05T05:10:26.373114+00:00"},{"alias_kind":"pith_short_8","alias_value":"WO3HRNRS","created_at":"2026-07-05T05:10:26.373114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.19939","citing_title":"LLMControl: Grounded Control of Text-to-Image Diffusion-based Synthesis with Multimodal LLMs","ref_index":53,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA","json":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA.json","graph_json":"https://pith.science/api/pith-number/WO3HRNRSV4V6TDNRKJ4STNTZBA/graph.json","events_json":"https://pith.science/api/pith-number/WO3HRNRSV4V6TDNRKJ4STNTZBA/events.json","paper":"https://pith.science/paper/WO3HRNRS"},"agent_actions":{"view_html":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA","download_json":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA.json","view_paper":"https://pith.science/paper/WO3HRNRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.14124&json=true","fetch_graph":"https://pith.science/api/pith-number/WO3HRNRSV4V6TDNRKJ4STNTZBA/graph.json","fetch_events":"https://pith.science/api/pith-number/WO3HRNRSV4V6TDNRKJ4STNTZBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA/action/storage_attestation","attest_author":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA/action/author_attestation","sign_citation":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA/action/citation_signature","submit_replication":"https://pith.science/pith/WO3HRNRSV4V6TDNRKJ4STNTZBA/action/replication_record"}},"created_at":"2026-07-05T05:10:26.373114+00:00","updated_at":"2026-07-05T05:10:26.373114+00:00"}