{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:O7QYUR2KXAQA35FNL4MQX6SX27","short_pith_number":"pith:O7QYUR2K","schema_version":"1.0","canonical_sha256":"77e18a474ab8200df4ad5f190bfa57d7fc0c65999495e16dff98d24032a92166","source":{"kind":"arxiv","id":"2406.01388","version":3},"attestation_state":"computed","paper":{"title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baiqiao Yin, Hanhui Li, Junhao Cheng, Khun Loun Zai, Xiaodan Liang, Xi Lu, Yiqiang Yan, Yuhao Cheng","submitted_at":"2024-06-03T14:51:24Z","abstract_excerpt":"As cutting-edge Text-to-Image (T2I) generation models already excel at producing remarkable single images, an even more challenging task, i.e., multi-turn interactive image generation begins to attract the attention of related research communities. This task requires models to interact with users over multiple turns to generate a coherent sequence of images. However, since users may switch subjects frequently, current efforts struggle to maintain subject consistency while generating diverse images. To address this issue, we introduce a training-free multi-agent framework called AutoStudio. Aut"},"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":"2406.01388","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T14:51:24Z","cross_cats_sorted":[],"title_canon_sha256":"6a352c07abb10efe0cb5c41bc55e1972cefb1e9bbf49e1095293d1612c5b6b8c","abstract_canon_sha256":"7087d26f110cfd04daf6bb990cb7029c8b56c253f13871818f43aab563ac0c90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:17.994262Z","signature_b64":"61ZVLAFQoIAQscYWV1APsSuNbPHEUwdPAZFNPCJHaLOMeR3Wdxxcxht+OJpvxTIteU1T+rODFzfwQDVxokrdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77e18a474ab8200df4ad5f190bfa57d7fc0c65999495e16dff98d24032a92166","last_reissued_at":"2026-07-05T11:12:17.993779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:17.993779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Baiqiao Yin, Hanhui Li, Junhao Cheng, Khun Loun Zai, Xiaodan Liang, Xi Lu, Yiqiang Yan, Yuhao Cheng","submitted_at":"2024-06-03T14:51:24Z","abstract_excerpt":"As cutting-edge Text-to-Image (T2I) generation models already excel at producing remarkable single images, an even more challenging task, i.e., multi-turn interactive image generation begins to attract the attention of related research communities. This task requires models to interact with users over multiple turns to generate a coherent sequence of images. However, since users may switch subjects frequently, current efforts struggle to maintain subject consistency while generating diverse images. To address this issue, we introduce a training-free multi-agent framework called AutoStudio. Aut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01388","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/2406.01388/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":"2406.01388","created_at":"2026-07-05T11:12:17.993838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01388v3","created_at":"2026-07-05T11:12:17.993838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01388","created_at":"2026-07-05T11:12:17.993838+00:00"},{"alias_kind":"pith_short_12","alias_value":"O7QYUR2KXAQA","created_at":"2026-07-05T11:12:17.993838+00:00"},{"alias_kind":"pith_short_16","alias_value":"O7QYUR2KXAQA35FN","created_at":"2026-07-05T11:12:17.993838+00:00"},{"alias_kind":"pith_short_8","alias_value":"O7QYUR2K","created_at":"2026-07-05T11:12:17.993838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10620","citing_title":"Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20237","citing_title":"AnimeAdapter: A Modular Adapter for Appearance-Consistent Anime Character Generation","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2509.04123","citing_title":"TaleDiffusion: Multi-Character Story Generation with Dialogue Rendering","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27","json":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27.json","graph_json":"https://pith.science/api/pith-number/O7QYUR2KXAQA35FNL4MQX6SX27/graph.json","events_json":"https://pith.science/api/pith-number/O7QYUR2KXAQA35FNL4MQX6SX27/events.json","paper":"https://pith.science/paper/O7QYUR2K"},"agent_actions":{"view_html":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27","download_json":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27.json","view_paper":"https://pith.science/paper/O7QYUR2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01388&json=true","fetch_graph":"https://pith.science/api/pith-number/O7QYUR2KXAQA35FNL4MQX6SX27/graph.json","fetch_events":"https://pith.science/api/pith-number/O7QYUR2KXAQA35FNL4MQX6SX27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27/action/storage_attestation","attest_author":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27/action/author_attestation","sign_citation":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27/action/citation_signature","submit_replication":"https://pith.science/pith/O7QYUR2KXAQA35FNL4MQX6SX27/action/replication_record"}},"created_at":"2026-07-05T11:12:17.993838+00:00","updated_at":"2026-07-05T11:12:17.993838+00:00"}