{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MMOO3XRGJOTIBJVRYHS426LB5U","short_pith_number":"pith:MMOO3XRG","schema_version":"1.0","canonical_sha256":"631cedde264ba680a6b1c1e5cd7961ed294e3294d6fbca96bc2fe31e3ba67f7c","source":{"kind":"arxiv","id":"2406.09162","version":1},"attestation_state":"computed","paper":{"title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Chi Zhang, Hanwang Zhang, Juntao Hu, Pei Cheng, Rui Wang, Yucheng Han","submitted_at":"2024-06-13T14:26:43Z","abstract_excerpt":"Recent advancements in image generation have enabled the creation of high-quality images from text conditions. However, when facing multi-modal conditions, such as text combined with reference appearances, existing methods struggle to balance multiple conditions effectively, typically showing a preference for one modality over others. To address this challenge, we introduce EMMA, a novel image generation model accepting multi-modal prompts built upon the state-of-the-art text-to-image (T2I) diffusion model, ELLA. EMMA seamlessly incorporates additional modalities alongside text to guide image "},"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":"2406.09162","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-13T14:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"6ae928b60ae1b8a2b9f3b52e9dc5402c6ffccdd8735b53cbf3b7a84c3641edaf","abstract_canon_sha256":"31dffee90dd832cba84e7a7b254d259425ad76d9983c8b5c427836163246c94b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:29.329968Z","signature_b64":"ejPPpKLnEjbq+95Nol1P//1qJF/O8fqeeDuNF9JpOMqiDAx5KPrHM/Pdi8T01xIoIwARHNXipxKoRvBr+Dk+Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"631cedde264ba680a6b1c1e5cd7961ed294e3294d6fbca96bc2fe31e3ba67f7c","last_reissued_at":"2026-07-05T08:31:29.329365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:29.329365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMMA: Your Text-to-Image Diffusion Model Can Secretly Accept Multi-Modal Prompts","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Chi Zhang, Hanwang Zhang, Juntao Hu, Pei Cheng, Rui Wang, Yucheng Han","submitted_at":"2024-06-13T14:26:43Z","abstract_excerpt":"Recent advancements in image generation have enabled the creation of high-quality images from text conditions. However, when facing multi-modal conditions, such as text combined with reference appearances, existing methods struggle to balance multiple conditions effectively, typically showing a preference for one modality over others. To address this challenge, we introduce EMMA, a novel image generation model accepting multi-modal prompts built upon the state-of-the-art text-to-image (T2I) diffusion model, ELLA. EMMA seamlessly incorporates additional modalities alongside text to guide image "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.09162","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/2406.09162/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":"2406.09162","created_at":"2026-07-05T08:31:29.329440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.09162v1","created_at":"2026-07-05T08:31:29.329440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.09162","created_at":"2026-07-05T08:31:29.329440+00:00"},{"alias_kind":"pith_short_12","alias_value":"MMOO3XRGJOTI","created_at":"2026-07-05T08:31:29.329440+00:00"},{"alias_kind":"pith_short_16","alias_value":"MMOO3XRGJOTIBJVR","created_at":"2026-07-05T08:31:29.329440+00:00"},{"alias_kind":"pith_short_8","alias_value":"MMOO3XRG","created_at":"2026-07-05T08:31:29.329440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10127","citing_title":"Fashion130K: An E-commerce Fashion Dataset for Outfit Generation with Unified Multi-modal Condition","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U","json":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U.json","graph_json":"https://pith.science/api/pith-number/MMOO3XRGJOTIBJVRYHS426LB5U/graph.json","events_json":"https://pith.science/api/pith-number/MMOO3XRGJOTIBJVRYHS426LB5U/events.json","paper":"https://pith.science/paper/MMOO3XRG"},"agent_actions":{"view_html":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U","download_json":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U.json","view_paper":"https://pith.science/paper/MMOO3XRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.09162&json=true","fetch_graph":"https://pith.science/api/pith-number/MMOO3XRGJOTIBJVRYHS426LB5U/graph.json","fetch_events":"https://pith.science/api/pith-number/MMOO3XRGJOTIBJVRYHS426LB5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U/action/storage_attestation","attest_author":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U/action/author_attestation","sign_citation":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U/action/citation_signature","submit_replication":"https://pith.science/pith/MMOO3XRGJOTIBJVRYHS426LB5U/action/replication_record"}},"created_at":"2026-07-05T08:31:29.329440+00:00","updated_at":"2026-07-05T08:31:29.329440+00:00"}