{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XVLIHGZXMRABFRMMN4QGVSVD4R","short_pith_number":"pith:XVLIHGZX","schema_version":"1.0","canonical_sha256":"bd56839b37644012c58c6f206acaa3e4558896524634b4f6d55aa45b971f28ae","source":{"kind":"arxiv","id":"2410.20823","version":1},"attestation_state":"computed","paper":{"title":"Novel Object Synthesis via Adaptive Text-Image Harmony","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gan Sun, Jian Yang, Jun Li, Shuo Chen, Xiang Li, Zedong Zhang, Zeren Xiong, Zikun Chen","submitted_at":"2024-10-28T08:14:40Z","abstract_excerpt":"In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this task, \\textit{i.e.}, often generating an object that predominantly reflects either the text or the image due to an imbalance between their inputs. To address this issue, we propose a simple yet effective method called Adaptive Text-Image Harmony (ATIH) to generate novel and surprising objects. First, we introduce a scale factor and an injection step to balance text and image features in cross-attention and to preserve"},"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":"2410.20823","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T08:14:40Z","cross_cats_sorted":[],"title_canon_sha256":"20b762a7e38934986eef94789e60b34b82c96e46169d36d0859de63b75b61180","abstract_canon_sha256":"910414d91ae7ed8a24f3280116477c93a89429796a7df5937230a3b791ae3252"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:11.718279Z","signature_b64":"4uaaWn7to6UIzw/kKiWIKWsukDq4ZRKk6MEQksvFQAASFxBuQNLDnxK8te3fvozE6HjabGb4agAI40G2218GCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd56839b37644012c58c6f206acaa3e4558896524634b4f6d55aa45b971f28ae","last_reissued_at":"2026-07-05T09:27:11.717889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:11.717889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Novel Object Synthesis via Adaptive Text-Image Harmony","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gan Sun, Jian Yang, Jun Li, Shuo Chen, Xiang Li, Zedong Zhang, Zeren Xiong, Zikun Chen","submitted_at":"2024-10-28T08:14:40Z","abstract_excerpt":"In this paper, we study an object synthesis task that combines an object text with an object image to create a new object image. However, most diffusion models struggle with this task, \\textit{i.e.}, often generating an object that predominantly reflects either the text or the image due to an imbalance between their inputs. To address this issue, we propose a simple yet effective method called Adaptive Text-Image Harmony (ATIH) to generate novel and surprising objects. First, we introduce a scale factor and an injection step to balance text and image features in cross-attention and to preserve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20823","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/2410.20823/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":"2410.20823","created_at":"2026-07-05T09:27:11.717941+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20823v1","created_at":"2026-07-05T09:27:11.717941+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20823","created_at":"2026-07-05T09:27:11.717941+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVLIHGZXMRAB","created_at":"2026-07-05T09:27:11.717941+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVLIHGZXMRABFRMM","created_at":"2026-07-05T09:27:11.717941+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVLIHGZX","created_at":"2026-07-05T09:27:11.717941+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03667","citing_title":"Distribution-Conditional Generation: From Class Distribution to Creative Generation","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R","json":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R.json","graph_json":"https://pith.science/api/pith-number/XVLIHGZXMRABFRMMN4QGVSVD4R/graph.json","events_json":"https://pith.science/api/pith-number/XVLIHGZXMRABFRMMN4QGVSVD4R/events.json","paper":"https://pith.science/paper/XVLIHGZX"},"agent_actions":{"view_html":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R","download_json":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R.json","view_paper":"https://pith.science/paper/XVLIHGZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20823&json=true","fetch_graph":"https://pith.science/api/pith-number/XVLIHGZXMRABFRMMN4QGVSVD4R/graph.json","fetch_events":"https://pith.science/api/pith-number/XVLIHGZXMRABFRMMN4QGVSVD4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R/action/storage_attestation","attest_author":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R/action/author_attestation","sign_citation":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R/action/citation_signature","submit_replication":"https://pith.science/pith/XVLIHGZXMRABFRMMN4QGVSVD4R/action/replication_record"}},"created_at":"2026-07-05T09:27:11.717941+00:00","updated_at":"2026-07-05T09:27:11.717941+00:00"}