{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:R2ZAVY6TN3O34OVT5RT5T7ISPW","short_pith_number":"pith:R2ZAVY6T","schema_version":"1.0","canonical_sha256":"8eb20ae3d36eddbe3ab3ec67d9fd127da3a2c0781d2ec5d6eb5b1695e5e2944d","source":{"kind":"arxiv","id":"2304.08465","version":1},"attestation_state":"computed","paper":{"title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingdeng Cao, Xiaohu Qie, Xintao Wang, Ying Shan, Yinqiang Zheng, Zhongang Qi","submitted_at":"2023-04-17T17:42:19Z","abstract_excerpt":"Despite the success in large-scale text-to-image generation and text-conditioned image editing, existing methods still struggle to produce consistent generation and editing results. For example, generation approaches usually fail to synthesize multiple images of the same objects/characters but with different views or poses. Meanwhile, existing editing methods either fail to achieve effective complex non-rigid editing while maintaining the overall textures and identity, or require time-consuming fine-tuning to capture the image-specific appearance. In this paper, we develop MasaCtrl, a tuning-f"},"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":"2304.08465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-04-17T17:42:19Z","cross_cats_sorted":[],"title_canon_sha256":"175927a2a5d964ec05a9a0a825203b2c35109e3d9cb8f08d2e2f5572a914c04c","abstract_canon_sha256":"13c370bf33306a665c7354f6ff67de386fa83ccdf6d422574c952635bc81505b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:01:52.721152Z","signature_b64":"uGPEsyqDe4te0DK8mkDjgBQr1M9ENgRp81AmjbK+DkeoXMYYO3U//iFb2VtGsVW+7sKBETUsaD6WAjz1RHU3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8eb20ae3d36eddbe3ab3ec67d9fd127da3a2c0781d2ec5d6eb5b1695e5e2944d","last_reissued_at":"2026-07-05T06:01:52.720700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:01:52.720700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mingdeng Cao, Xiaohu Qie, Xintao Wang, Ying Shan, Yinqiang Zheng, Zhongang Qi","submitted_at":"2023-04-17T17:42:19Z","abstract_excerpt":"Despite the success in large-scale text-to-image generation and text-conditioned image editing, existing methods still struggle to produce consistent generation and editing results. For example, generation approaches usually fail to synthesize multiple images of the same objects/characters but with different views or poses. Meanwhile, existing editing methods either fail to achieve effective complex non-rigid editing while maintaining the overall textures and identity, or require time-consuming fine-tuning to capture the image-specific appearance. In this paper, we develop MasaCtrl, a tuning-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08465","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/2304.08465/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":"2304.08465","created_at":"2026-07-05T06:01:52.720757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08465v1","created_at":"2026-07-05T06:01:52.720757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08465","created_at":"2026-07-05T06:01:52.720757+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2ZAVY6TN3O3","created_at":"2026-07-05T06:01:52.720757+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2ZAVY6TN3O34OVT","created_at":"2026-07-05T06:01:52.720757+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2ZAVY6T","created_at":"2026-07-05T06:01:52.720757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23682","citing_title":"Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.23679","citing_title":"Semantic Browsing: Controllable Diversity for Image Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18156","citing_title":"ReAge3D: Re-Aging 3D Faces with View Consistency","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28922","citing_title":"Cross-Sensor SAR Data Generation Using Diffusion Models and Feature Migration","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2403.05135","citing_title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08646","citing_title":"InsEdit: Towards Instruction-based Visual Editing via Data-Efficient Video Diffusion Models Adaptation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW","json":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW.json","graph_json":"https://pith.science/api/pith-number/R2ZAVY6TN3O34OVT5RT5T7ISPW/graph.json","events_json":"https://pith.science/api/pith-number/R2ZAVY6TN3O34OVT5RT5T7ISPW/events.json","paper":"https://pith.science/paper/R2ZAVY6T"},"agent_actions":{"view_html":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW","download_json":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW.json","view_paper":"https://pith.science/paper/R2ZAVY6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08465&json=true","fetch_graph":"https://pith.science/api/pith-number/R2ZAVY6TN3O34OVT5RT5T7ISPW/graph.json","fetch_events":"https://pith.science/api/pith-number/R2ZAVY6TN3O34OVT5RT5T7ISPW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW/action/storage_attestation","attest_author":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW/action/author_attestation","sign_citation":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW/action/citation_signature","submit_replication":"https://pith.science/pith/R2ZAVY6TN3O34OVT5RT5T7ISPW/action/replication_record"}},"created_at":"2026-07-05T06:01:52.720757+00:00","updated_at":"2026-07-05T06:01:52.720757+00:00"}