{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:ADCGUUYLJINKKNEVOVVNQWMEMG","short_pith_number":"pith:ADCGUUYL","schema_version":"1.0","canonical_sha256":"00c46a530b4a1aa53495756ad8598461ae4ffc61cdb8b4ddb3435be900d793aa","source":{"kind":"arxiv","id":"2111.13792","version":3},"attestation_state":"computed","paper":{"title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Changyou Chen, Chris Tensmeyer, Chunyuan Li, Jinhui Xu, Jiuxiang Gu, Ruiyi Zhang, Tong Sun, Tong Yu, Yufan Zhou","submitted_at":"2021-11-27T01:54:45Z","abstract_excerpt":"One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs. While image samples are often easily accessible, the associated text descriptions typically require careful human captioning, which is particularly time- and cost-consuming. In this paper, we propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model: the requirement of text-conditioning is seamlessly alleviated via generating tex"},"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":"2111.13792","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-27T01:54:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9905f4c75168f5f1c48fa28af2de3587039244b8ad538636ef51e7a95fe56f93","abstract_canon_sha256":"e2319ae95ae1fb33a3d98af2b4f98c4be8e0aeeb601c72f05a04eda1f29fefe1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:04.513504Z","signature_b64":"YeakEky8gWbdwuA0WPtrGfmRrd+pNdDA1sC4+2D8sJajUacwQANGe+T12l8BaJShy0p0jb36zsa8HXg6+f6pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c46a530b4a1aa53495756ad8598461ae4ffc61cdb8b4ddb3435be900d793aa","last_reissued_at":"2026-07-05T04:08:04.513094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:04.513094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Changyou Chen, Chris Tensmeyer, Chunyuan Li, Jinhui Xu, Jiuxiang Gu, Ruiyi Zhang, Tong Sun, Tong Yu, Yufan Zhou","submitted_at":"2021-11-27T01:54:45Z","abstract_excerpt":"One of the major challenges in training text-to-image generation models is the need of a large number of high-quality image-text pairs. While image samples are often easily accessible, the associated text descriptions typically require careful human captioning, which is particularly time- and cost-consuming. In this paper, we propose the first work to train text-to-image generation models without any text data. Our method leverages the well-aligned multi-modal semantic space of the powerful pre-trained CLIP model: the requirement of text-conditioning is seamlessly alleviated via generating tex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13792","kind":"arxiv","version":3},"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/2111.13792/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":"2111.13792","created_at":"2026-07-05T04:08:04.513150+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13792v3","created_at":"2026-07-05T04:08:04.513150+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13792","created_at":"2026-07-05T04:08:04.513150+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADCGUUYLJINK","created_at":"2026-07-05T04:08:04.513150+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADCGUUYLJINKKNEV","created_at":"2026-07-05T04:08:04.513150+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADCGUUYL","created_at":"2026-07-05T04:08:04.513150+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2302.08453","citing_title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2205.11487","citing_title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":109,"is_internal_anchor":false},{"citing_arxiv_id":"2306.09341","citing_title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2112.10741","citing_title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2204.06125","citing_title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG","json":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG.json","graph_json":"https://pith.science/api/pith-number/ADCGUUYLJINKKNEVOVVNQWMEMG/graph.json","events_json":"https://pith.science/api/pith-number/ADCGUUYLJINKKNEVOVVNQWMEMG/events.json","paper":"https://pith.science/paper/ADCGUUYL"},"agent_actions":{"view_html":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG","download_json":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG.json","view_paper":"https://pith.science/paper/ADCGUUYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13792&json=true","fetch_graph":"https://pith.science/api/pith-number/ADCGUUYLJINKKNEVOVVNQWMEMG/graph.json","fetch_events":"https://pith.science/api/pith-number/ADCGUUYLJINKKNEVOVVNQWMEMG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG/action/storage_attestation","attest_author":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG/action/author_attestation","sign_citation":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG/action/citation_signature","submit_replication":"https://pith.science/pith/ADCGUUYLJINKKNEVOVVNQWMEMG/action/replication_record"}},"created_at":"2026-07-05T04:08:04.513150+00:00","updated_at":"2026-07-05T04:08:04.513150+00:00"}