{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NC4BQLNSNOELF6DHALFU2LF7QL","short_pith_number":"pith:NC4BQLNS","schema_version":"1.0","canonical_sha256":"68b8182db26b88b2f86702cb4d2cbf82ef6136b1ffae7c06c2583b5087e107aa","source":{"kind":"arxiv","id":"2310.07419","version":1},"attestation_state":"computed","paper":{"title":"Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Hazarapet Tunanyan, Humphrey Shi, Shant Navasardyan, Zhangyang Wang","submitted_at":"2023-10-11T12:05:44Z","abstract_excerpt":"Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally, limiting their ability to visualize human imagination. While several recent works have attempted to address this issue, they either introduce additional training or adopt guidance at inference time. In this work, we consider a more ambitious goal: natural multi-concept generation using a pre-trained diffusion model, and with almost no extra cost. To achieve t"},"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":"2310.07419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-11T12:05:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"caa30d94386182fa0e60cb8ba0a6f81b6895b53b6954d9c33791b4f280e467a5","abstract_canon_sha256":"7e4e362c150a0589a8773a61fbe3fcb900e3882c15522aaaa570aaed4afa5f8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:45.434172Z","signature_b64":"+ZaxDs5l30gpZIqarXSsW/2joCJkKys9eyYxWbc1wwzf0h8al318UdS2L5/k07KRvfNHFwaExBv8PUw1kDtmDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68b8182db26b88b2f86702cb4d2cbf82ef6136b1ffae7c06c2583b5087e107aa","last_reissued_at":"2026-07-05T06:59:45.433749Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:45.433749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Concept T2I-Zero: Tweaking Only The Text Embeddings and Nothing Else","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Dejia Xu, Hazarapet Tunanyan, Humphrey Shi, Shant Navasardyan, Zhangyang Wang","submitted_at":"2023-10-11T12:05:44Z","abstract_excerpt":"Recent advances in text-to-image diffusion models have enabled the photorealistic generation of images from text prompts. Despite the great progress, existing models still struggle to generate compositional multi-concept images naturally, limiting their ability to visualize human imagination. While several recent works have attempted to address this issue, they either introduce additional training or adopt guidance at inference time. In this work, we consider a more ambitious goal: natural multi-concept generation using a pre-trained diffusion model, and with almost no extra cost. To achieve t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07419","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/2310.07419/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":"2310.07419","created_at":"2026-07-05T06:59:45.433811+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07419v1","created_at":"2026-07-05T06:59:45.433811+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07419","created_at":"2026-07-05T06:59:45.433811+00:00"},{"alias_kind":"pith_short_12","alias_value":"NC4BQLNSNOEL","created_at":"2026-07-05T06:59:45.433811+00:00"},{"alias_kind":"pith_short_16","alias_value":"NC4BQLNSNOELF6DH","created_at":"2026-07-05T06:59:45.433811+00:00"},{"alias_kind":"pith_short_8","alias_value":"NC4BQLNS","created_at":"2026-07-05T06:59:45.433811+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23178","citing_title":"Composing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL","json":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL.json","graph_json":"https://pith.science/api/pith-number/NC4BQLNSNOELF6DHALFU2LF7QL/graph.json","events_json":"https://pith.science/api/pith-number/NC4BQLNSNOELF6DHALFU2LF7QL/events.json","paper":"https://pith.science/paper/NC4BQLNS"},"agent_actions":{"view_html":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL","download_json":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL.json","view_paper":"https://pith.science/paper/NC4BQLNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07419&json=true","fetch_graph":"https://pith.science/api/pith-number/NC4BQLNSNOELF6DHALFU2LF7QL/graph.json","fetch_events":"https://pith.science/api/pith-number/NC4BQLNSNOELF6DHALFU2LF7QL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL/action/storage_attestation","attest_author":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL/action/author_attestation","sign_citation":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL/action/citation_signature","submit_replication":"https://pith.science/pith/NC4BQLNSNOELF6DHALFU2LF7QL/action/replication_record"}},"created_at":"2026-07-05T06:59:45.433811+00:00","updated_at":"2026-07-05T06:59:45.433811+00:00"}