{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SE4BUCEHY6W6AF33PCXUOQBBHM","short_pith_number":"pith:SE4BUCEH","schema_version":"1.0","canonical_sha256":"91381a0887c7ade0177b78af4740213b068d050b1b8110a3a720c828e601901e","source":{"kind":"arxiv","id":"2406.07209","version":3},"attestation_state":"computed","paper":{"title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Jiang, Qihan Huang, Siming Fu, Wanggui He, Xierui Wang","submitted_at":"2024-06-11T12:32:53Z","abstract_excerpt":"Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in multi-subject scenarios. However, these advances are hindered by two main challenges: firstly, the need to accurately maintain the details of each referenced subject in accordance with the textual descriptions; and secondly, the difficulty in achieving a cohesive representation of multiple subjects in a single image without introducing inconsistencies. To addre"},"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":"2406.07209","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T12:32:53Z","cross_cats_sorted":[],"title_canon_sha256":"cea097fd498725a296d2190f2fe58b61e3af8056885ff3af13da53d73fd67562","abstract_canon_sha256":"a04718979242c7ff03dd8858f2dbd8aecc9b0e60282501d30b365047407a5277"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:20.050878Z","signature_b64":"+UhbaGLiJmoVAbNAOVEO8vkP6/qkWx7JeW22bCkfVo2vEVCmImdTClmSP8bNR8h7xrOdYYu99fu2NcIkyW5BCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91381a0887c7ade0177b78af4740213b068d050b1b8110a3a720c828e601901e","last_reissued_at":"2026-07-05T10:23:20.050242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:20.050242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MS-Diffusion: Multi-subject Zero-shot Image Personalization with Layout Guidance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Jiang, Qihan Huang, Siming Fu, Wanggui He, Xierui Wang","submitted_at":"2024-06-11T12:32:53Z","abstract_excerpt":"Recent advancements in text-to-image generation models have dramatically enhanced the generation of photorealistic images from textual prompts, leading to an increased interest in personalized text-to-image applications, particularly in multi-subject scenarios. However, these advances are hindered by two main challenges: firstly, the need to accurately maintain the details of each referenced subject in accordance with the textual descriptions; and secondly, the difficulty in achieving a cohesive representation of multiple subjects in a single image without introducing inconsistencies. To addre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07209","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/2406.07209/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":"2406.07209","created_at":"2026-07-05T10:23:20.050311+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07209v3","created_at":"2026-07-05T10:23:20.050311+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07209","created_at":"2026-07-05T10:23:20.050311+00:00"},{"alias_kind":"pith_short_12","alias_value":"SE4BUCEHY6W6","created_at":"2026-07-05T10:23:20.050311+00:00"},{"alias_kind":"pith_short_16","alias_value":"SE4BUCEHY6W6AF33","created_at":"2026-07-05T10:23:20.050311+00:00"},{"alias_kind":"pith_short_8","alias_value":"SE4BUCEH","created_at":"2026-07-05T10:23:20.050311+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21395","citing_title":"Atomistic Language Models Understand and Generate Materials","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01383","citing_title":"MIBE: Multi-subject Interaction Benchmark and Evaluator for Personalized Image Generation","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11783","citing_title":"A Comprehensive Ecosystem for Open-Domain Customized Video Generation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00351","citing_title":"UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27235","citing_title":"MRT: Masked Region Transformer for Layered Image Generation and Editing at Scale","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23610","citing_title":"EM-Vid: Training-Free Entity-Centric Memory for Efficient and Consistent Multi-Shot Video Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04300","citing_title":"T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2504.15958","citing_title":"FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17816","citing_title":"Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2509.16702","citing_title":"Animalbooth: multimodal feature enhancement for animal subject personalization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.01236","citing_title":"PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2601.05127","citing_title":"LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2603.08090","citing_title":"DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13938","citing_title":"ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding","ref_index":40,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM","json":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM.json","graph_json":"https://pith.science/api/pith-number/SE4BUCEHY6W6AF33PCXUOQBBHM/graph.json","events_json":"https://pith.science/api/pith-number/SE4BUCEHY6W6AF33PCXUOQBBHM/events.json","paper":"https://pith.science/paper/SE4BUCEH"},"agent_actions":{"view_html":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM","download_json":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM.json","view_paper":"https://pith.science/paper/SE4BUCEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07209&json=true","fetch_graph":"https://pith.science/api/pith-number/SE4BUCEHY6W6AF33PCXUOQBBHM/graph.json","fetch_events":"https://pith.science/api/pith-number/SE4BUCEHY6W6AF33PCXUOQBBHM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM/action/storage_attestation","attest_author":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM/action/author_attestation","sign_citation":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM/action/citation_signature","submit_replication":"https://pith.science/pith/SE4BUCEHY6W6AF33PCXUOQBBHM/action/replication_record"}},"created_at":"2026-07-05T10:23:20.050311+00:00","updated_at":"2026-07-05T10:23:20.050311+00:00"}