{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X4VXROWWAMZLW57BVB4BB6CAFI","short_pith_number":"pith:X4VXROWW","schema_version":"1.0","canonical_sha256":"bf2b78bad60332bb77e1a87810f8402a0815a64aa686b8d6cb35227299b68e96","source":{"kind":"arxiv","id":"2503.16418","version":2},"attestation_state":"computed","paper":{"title":"InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Kang, Liming Jiang, Qing Yan, Xin Lu, Yumin Jia, Zichuan Liu","submitted_at":"2025-03-20T17:59:34Z","abstract_excerpt":"Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX. We introduce InfiniteYou (InfU), one of the earliest robust frameworks leveraging DiTs for this task. InfU addresses significant issues of existing methods, such as insufficient identity similarity, poor text-image alignment, and low generation quality and aesthetics. Central to InfU is InfuseNet, a component that injects identity features into the DiT base model via residual connections, enhancing identity similarity while maintaining"},"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":"2503.16418","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-20T17:59:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"821d76787126a56df6299f9b76305f27ca1cb353575804b03bc5ac90457f19de","abstract_canon_sha256":"d0a396cb5d8a46ff45f672760259df9869fa1b86e22a785bc26390ceee4aeabe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:46.792819Z","signature_b64":"sra97INBDWuUrlM92eal2dWMgotsFHOVUw2f9xbwOTytvxXcKl9wgGNTigxcYfx3dRTEhxPqrrILecPTz+GiCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf2b78bad60332bb77e1a87810f8402a0815a64aa686b8d6cb35227299b68e96","last_reissued_at":"2026-07-05T11:44:46.792273Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:46.792273Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hao Kang, Liming Jiang, Qing Yan, Xin Lu, Yumin Jia, Zichuan Liu","submitted_at":"2025-03-20T17:59:34Z","abstract_excerpt":"Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX. We introduce InfiniteYou (InfU), one of the earliest robust frameworks leveraging DiTs for this task. InfU addresses significant issues of existing methods, such as insufficient identity similarity, poor text-image alignment, and low generation quality and aesthetics. Central to InfU is InfuseNet, a component that injects identity features into the DiT base model via residual connections, enhancing identity similarity while maintaining"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.16418","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/2503.16418/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":"2503.16418","created_at":"2026-07-05T11:44:46.792350+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.16418v2","created_at":"2026-07-05T11:44:46.792350+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.16418","created_at":"2026-07-05T11:44:46.792350+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4VXROWWAMZL","created_at":"2026-07-05T11:44:46.792350+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4VXROWWAMZLW57B","created_at":"2026-07-05T11:44:46.792350+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4VXROWW","created_at":"2026-07-05T11:44:46.792350+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.18871","citing_title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26583","citing_title":"Emu3.5: Native Multimodal Models are World Learners","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21788","citing_title":"InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09460","citing_title":"When Few Steps Are Enough: Training-Free Acceleration of Identity-Preserved Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21689","citing_title":"StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI","json":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI.json","graph_json":"https://pith.science/api/pith-number/X4VXROWWAMZLW57BVB4BB6CAFI/graph.json","events_json":"https://pith.science/api/pith-number/X4VXROWWAMZLW57BVB4BB6CAFI/events.json","paper":"https://pith.science/paper/X4VXROWW"},"agent_actions":{"view_html":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI","download_json":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI.json","view_paper":"https://pith.science/paper/X4VXROWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.16418&json=true","fetch_graph":"https://pith.science/api/pith-number/X4VXROWWAMZLW57BVB4BB6CAFI/graph.json","fetch_events":"https://pith.science/api/pith-number/X4VXROWWAMZLW57BVB4BB6CAFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI/action/storage_attestation","attest_author":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI/action/author_attestation","sign_citation":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI/action/citation_signature","submit_replication":"https://pith.science/pith/X4VXROWWAMZLW57BVB4BB6CAFI/action/replication_record"}},"created_at":"2026-07-05T11:44:46.792350+00:00","updated_at":"2026-07-05T11:44:46.792350+00:00"}