{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:3IIKHSP2G44WIOHHB3XTFWKEW2","short_pith_number":"pith:3IIKHSP2","schema_version":"1.0","canonical_sha256":"da10a3c9fa37396438e70eef32d944b6ab3835499a37efeff3e6e2cfb36eaed4","source":{"kind":"arxiv","id":"2305.16223","version":2},"attestation_state":"computed","paper":{"title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Humphrey Shi, Irfan Essa, Jiayi Guo, Xingqian Xu, Zhangyang Wang","submitted_at":"2023-05-25T16:30:07Z","abstract_excerpt":"Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: \"an image is worth a thousand words\" - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual do"},"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":"2305.16223","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-25T16:30:07Z","cross_cats_sorted":[],"title_canon_sha256":"e7f11b0930594cf672e8d5876bc53130e25566a7452fbbde27e7a4bb57e6a4d8","abstract_canon_sha256":"a3da599ff6714e295cd4eb0d0662da2cc87b5e16198406bb9966f8403f63ff6e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:18.832035Z","signature_b64":"kBG3qJcXLQVvq+DALR3FPwa2HyTDEfGXXaurIm54GlsLzgRpJJ31hgL+Knswd7wjf1JvaXsYInYjU6mzqmkWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da10a3c9fa37396438e70eef32d944b6ab3835499a37efeff3e6e2cfb36eaed4","last_reissued_at":"2026-07-05T06:16:18.831425Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:18.831425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prompt-Free Diffusion: Taking \"Text\" out of Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gao Huang, Humphrey Shi, Irfan Essa, Jiayi Guo, Xingqian Xu, Zhangyang Wang","submitted_at":"2023-05-25T16:30:07Z","abstract_excerpt":"Text-to-image (T2I) research has grown explosively in the past year, owing to the large-scale pre-trained diffusion models and many emerging personalization and editing approaches. Yet, one pain point persists: the text prompt engineering, and searching high-quality text prompts for customized results is more art than science. Moreover, as commonly argued: \"an image is worth a thousand words\" - the attempt to describe a desired image with texts often ends up being ambiguous and cannot comprehensively cover delicate visual details, hence necessitating more additional controls from the visual do"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.16223","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/2305.16223/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":"2305.16223","created_at":"2026-07-05T06:16:18.831496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.16223v2","created_at":"2026-07-05T06:16:18.831496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.16223","created_at":"2026-07-05T06:16:18.831496+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IIKHSP2G44W","created_at":"2026-07-05T06:16:18.831496+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IIKHSP2G44WIOHH","created_at":"2026-07-05T06:16:18.831496+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IIKHSP2","created_at":"2026-07-05T06:16:18.831496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.23690","citing_title":"SynMotion: Semantic-Visual Adaptation for Motion Customized Video Generation","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2308.06721","citing_title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2","json":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2.json","graph_json":"https://pith.science/api/pith-number/3IIKHSP2G44WIOHHB3XTFWKEW2/graph.json","events_json":"https://pith.science/api/pith-number/3IIKHSP2G44WIOHHB3XTFWKEW2/events.json","paper":"https://pith.science/paper/3IIKHSP2"},"agent_actions":{"view_html":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2","download_json":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2.json","view_paper":"https://pith.science/paper/3IIKHSP2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.16223&json=true","fetch_graph":"https://pith.science/api/pith-number/3IIKHSP2G44WIOHHB3XTFWKEW2/graph.json","fetch_events":"https://pith.science/api/pith-number/3IIKHSP2G44WIOHHB3XTFWKEW2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2/action/storage_attestation","attest_author":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2/action/author_attestation","sign_citation":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2/action/citation_signature","submit_replication":"https://pith.science/pith/3IIKHSP2G44WIOHHB3XTFWKEW2/action/replication_record"}},"created_at":"2026-07-05T06:16:18.831496+00:00","updated_at":"2026-07-05T06:16:18.831496+00:00"}